changed blind_test_input_df to blind_test_df in MultModelsCl

scripts/ml/MultModelsCl.py

@@ -101,7 +101,7 @@ jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
 #%%
 # Multiple Classification - Model Pipeline
 def MultModelsCl(input_df, target, skf_cv
-                       , blind_test_input_df
+                       , blind_test_df
                        , blind_test_target
                        , add_cm = True # adds confusion matrix based on cross_val_predict
                        , add_yn = True  # adds target var class numbers
@@ -155,32 +155,32 @@ def MultModelsCl(input_df, target, skf_cv
             , ('Logistic RegressionCV'     , LogisticRegressionCV(**rs) )
             , ('Gaussian NB'               , GaussianNB() )
             , ('Naive Bayes'               , BernoulliNB() )
-            # , ('K-Nearest Neighbors'       , KNeighborsClassifier() ) 
-            # , ('SVC'                       , SVC(**rs) ) 
-            # , ('MLP'                       , MLPClassifier(max_iter = 500, **rs) ) 
-            # , ('Decision Tree'             , DecisionTreeClassifier(**rs) ) 
-            # , ('Extra Trees'               , ExtraTreesClassifier(**rs) ) 
-            # , ('Extra Tree'                , ExtraTreeClassifier(**rs) )
-            # , ('Random Forest'             , RandomForestClassifier(**rs, n_estimators = 1000 ) ) 
-            # , ('Random Forest2'            , RandomForestClassifier(min_samples_leaf = 5
-            #                                                         , n_estimators     = 1000
-            #                                                         , bootstrap        = True
-            #                                                         , oob_score        = True
-            #                                                         , **njobs
-            #                                                         , **rs
-            #                                                         , max_features     = 'auto') ) 
-            # , ('XGBoost'                   , XGBClassifier(**rs, verbosity = 0, use_label_encoder =False) )
-            # , ('LDA'                       , LinearDiscriminantAnalysis() )
-            # , ('Multinomial'               , MultinomialNB() )
-            # , ('Passive Aggresive'         , PassiveAggressiveClassifier(**rs, **njobs) )
-            # , ('Stochastic GDescent'       , SGDClassifier(**rs, **njobs) )
-            # , ('AdaBoost Classifier'       , AdaBoostClassifier(**rs) )
-            # , ('Bagging Classifier'        , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True) )
-            # , ('Gaussian Process'          , GaussianProcessClassifier(**rs) )
-            # , ('Gradient Boosting'         , GradientBoostingClassifier(**rs) )
-            # , ('QDA'                       , QuadraticDiscriminantAnalysis() )
-            # , ('Ridge Classifier'          , RidgeClassifier(**rs)  )
-            # , ('Ridge ClassifierCV'        , RidgeClassifierCV(cv = 10) )
+            , ('K-Nearest Neighbors'       , KNeighborsClassifier() ) 
+            , ('SVC'                       , SVC(**rs) ) 
+            , ('MLP'                       , MLPClassifier(max_iter = 500, **rs) ) 
+            , ('Decision Tree'             , DecisionTreeClassifier(**rs) ) 
+            , ('Extra Trees'               , ExtraTreesClassifier(**rs) ) 
+            , ('Extra Tree'                , ExtraTreeClassifier(**rs) )
+            , ('Random Forest'             , RandomForestClassifier(**rs, n_estimators = 1000 ) ) 
+            , ('Random Forest2'            , RandomForestClassifier(min_samples_leaf = 5
+                                                                    , n_estimators     = 1000
+                                                                    , bootstrap        = True
+                                                                    , oob_score        = True
+                                                                    , **njobs
+                                                                    , **rs
+                                                                    , max_features     = 'auto') ) 
+            , ('XGBoost'                   , XGBClassifier(**rs, verbosity = 0, use_label_encoder =False) )
+            , ('LDA'                       , LinearDiscriminantAnalysis() )
+            , ('Multinomial'               , MultinomialNB() )
+            , ('Passive Aggresive'         , PassiveAggressiveClassifier(**rs, **njobs) )
+            , ('Stochastic GDescent'       , SGDClassifier(**rs, **njobs) )
+            , ('AdaBoost Classifier'       , AdaBoostClassifier(**rs) )
+            , ('Bagging Classifier'        , BaggingClassifier(**rs, **njobs, bootstrap = True, oob_score = True) )
+            , ('Gaussian Process'          , GaussianProcessClassifier(**rs) )
+            , ('Gradient Boosting'         , GradientBoostingClassifier(**rs) )
+            , ('QDA'                       , QuadraticDiscriminantAnalysis() )
+            , ('Ridge Classifier'          , RidgeClassifier(**rs)  )
+            , ('Ridge ClassifierCV'        , RidgeClassifierCV(cv = 10) )
             ]
                 
     mm_skf_scoresD = {}
@@ -293,9 +293,9 @@ def MultModelsCl(input_df, target, skf_cv
         # Blind test: BTS results
         #=========================
         # Build the final results with all scores for the model
-        #bts_predict = gscv_fs.predict(blind_test_input_df)
+        #bts_predict = gscv_fs.predict(blind_test_df)
         model_pipeline.fit(input_df, target)
-        bts_predict = model_pipeline.predict(blind_test_input_df)
+        bts_predict = model_pipeline.predict(blind_test_df)
         
         bts_mcc_score = round(matthews_corrcoef(blind_test_target, bts_predict),2)
         print('\nMCC on Blind test:'     , bts_mcc_score)

scripts/ml/alr_7030.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'alr'
-drug  = 'cycloserine'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_7030 import *
-setvars(gene,drug)
-from ml_data_7030 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_7030/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/alr_8020.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'alr'
-drug  = 'cycloserine'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_8020 import *
-setvars(gene,drug)
-from ml_data_8020 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: 80/20 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_8020/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/alr_cd_7030.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'alr'
-drug  = 'cycloserine'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_7030 import *
-setvars(gene,drug)
-from ml_data_cd_7030 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_7030/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/alr_cd_8020.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'alr'
-drug  = 'cycloserine'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_8020 import *
-setvars(gene,drug)
-from ml_data_cd_8020 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 80/20 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_8020/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/alr_cd_sl.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'alr'
-drug  = 'cycloserine'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_sl import *
-setvars(gene,drug)
-from ml_data_cd_sl import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_sl/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/alr_config.py

@@ -1,210 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'alr'
-drug  = 'cycloserine'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-#---------------------------
-# Version 1: no AAindex
-#from UQ_ML_data import *
-#setvars(gene,drug)
-#from UQ_ML_data import *
-#---------------------------
-
-from ml_data import *
-setvars(gene,drug)
-from ml_data import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: UQ [without AA  index but with active site annotations]'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/uq_v1/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-# print('AAindex features (n):'
-#       , len(X_aaindexFN)
-#       , '\nThese are:\n'
-#       , X_aaindexFN
-#       , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-#if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-if ( len(X.columns) ==  len(X_ssFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/alr_orig.py

@@ -1,202 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'alr'
-drug  = 'cycloserine'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_orig import *
-setvars(gene,drug)
-from ml_data_orig import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: ORIGINAL'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_orig/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/alr_rt.py

@@ -1,202 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'alr'
-drug  = 'cycloserine'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_rt import *
-setvars(gene,drug)
-from ml_data_rt import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: REVERSE training\n'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_rt/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/alr_sl.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'alr'
-drug  = 'cycloserine'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_sl import *
-setvars(gene,drug)
-from ml_data_sl import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: scaling law split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_sl/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/embb_7030.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'embB'
-drug  = 'ethambutol'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_7030 import *
-setvars(gene,drug)
-from ml_data_7030 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_7030/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/embb_8020.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'embB'
-drug  = 'ethambutol'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_8020 import *
-setvars(gene,drug)
-from ml_data_8020 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: 80/20 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_8020/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/embb_cd_7030.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'embB'
-drug  = 'ethambutol'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_7030 import *
-setvars(gene,drug)
-from ml_data_cd_7030 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_7030/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/embb_cd_8020.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'embB'
-drug  = 'ethambutol'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_8020 import *
-setvars(gene,drug)
-from ml_data_cd_8020 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 80/20 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_8020/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/embb_cd_sl.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'embB'
-drug  = 'ethambutol'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_sl import *
-setvars(gene,drug)
-from ml_data_cd_sl import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_sl/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/embb_config.py

@@ -1,210 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'embB'
-drug  = 'ethambutol'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-#---------------------------
-# Version 1: no AAindex
-#from UQ_ML_data import *
-#setvars(gene,drug)
-#from UQ_ML_data import *
-#---------------------------
-
-from ml_data import *
-setvars(gene,drug)
-from ml_data import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: UQ [without AA  index but with active site annotations]'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/uq_v1/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-# print('AAindex features (n):'
-#       , len(X_aaindexFN)
-#       , '\nThese are:\n'
-#       , X_aaindexFN
-#       , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-#if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-if ( len(X.columns) ==  len(X_ssFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/embb_orig.py

@@ -1,202 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'embB'
-drug  = 'ethambutol'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_orig import *
-setvars(gene,drug)
-from ml_data_orig import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: ORIGINAL'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_orig/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/embb_rt.py

@@ -1,202 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'embB'
-drug  = 'ethambutol'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_rt import *
-setvars(gene,drug)
-from ml_data_rt import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: REVERSE training\n'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_rt/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/embb_sl.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'embB'
-drug  = 'ethambutol'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_sl import *
-setvars(gene,drug)
-from ml_data_sl import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: scaling law split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_sl/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/gid_7030.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'gid'
-drug  = 'streptomycin'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_7030 import *
-setvars(gene,drug)
-from ml_data_7030 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_7030/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/gid_8020.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'gid'
-drug  = 'streptomycin'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_8020 import *
-setvars(gene,drug)
-from ml_data_8020 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: 80/20 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_8020/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/gid_cd_7030.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'gid'
-drug  = 'streptomycin'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_7030 import *
-setvars(gene,drug)
-from ml_data_cd_7030 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_7030/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/gid_cd_8020.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'gid'
-drug  = 'streptomycin'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_8020 import *
-setvars(gene,drug)
-from ml_data_cd_8020 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 80/20 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_8020/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/gid_cd_sl.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'gid'
-drug  = 'streptomycin'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_sl import *
-setvars(gene,drug)
-from ml_data_cd_sl import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_sl/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/gid_config.py

@@ -1,210 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'gid'
-drug  = 'streptomycin'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-#---------------------------
-# Version 1: no AAindex
-#from UQ_ML_data import *
-#setvars(gene,drug)
-#from UQ_ML_data import *
-#---------------------------
-
-from ml_data import *
-setvars(gene,drug)
-from ml_data import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: UQ [without AA  index but with active site annotations]'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/uq_v1/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-# print('AAindex features (n):'
-#       , len(X_aaindexFN)
-#       , '\nThese are:\n'
-#       , X_aaindexFN
-#       , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-#if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-if ( len(X.columns) ==  len(X_ssFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/gid_orig.py

@@ -1,202 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'gid'
-drug  = 'streptomycin'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_orig import *
-setvars(gene,drug)
-from ml_data_orig import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: ORIGINAL'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_orig/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/gid_rt.py

@@ -1,202 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'gid'
-drug  = 'streptomycin'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_rt import *
-setvars(gene,drug)
-from ml_data_rt import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: REVERSE training\n'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_rt/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/gid_sl.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'gid'
-drug  = 'streptomycin'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_sl import *
-setvars(gene,drug)
-from ml_data_sl import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: scaling law split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_sl/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/katg_7030.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'katG'
-drug  = 'isoniazid'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_7030 import *
-setvars(gene,drug)
-from ml_data_7030 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_7030/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/katg_8020.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'katG'
-drug  = 'isoniazid'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_8020 import *
-setvars(gene,drug)
-from ml_data_8020 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: 80/20 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_8020/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/katg_cd_7030.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'katG'
-drug  = 'isoniazid'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_7030 import *
-setvars(gene,drug)
-from ml_data_cd_7030 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_7030/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/katg_cd_8020.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'katG'
-drug  = 'isoniazid'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_8020 import *
-setvars(gene,drug)
-from ml_data_cd_8020 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 80/20 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_8020/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/katg_cd_sl.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'katG'
-drug  = 'isoniazid'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_sl import *
-setvars(gene,drug)
-from ml_data_cd_sl import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_sl/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/katg_config.py

@@ -1,210 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'katG'
-drug  = 'isoniazid'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-#---------------------------
-# Version 1: no AAindex
-#from UQ_ML_data import *
-#setvars(gene,drug)
-#from UQ_ML_data import *
-#---------------------------
-
-from ml_data import *
-setvars(gene,drug)
-from ml_data import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: UQ [without AA  index but with active site annotations]'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/uq_v1/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-# print('AAindex features (n):'
-#       , len(X_aaindexFN)
-#       , '\nThese are:\n'
-#       , X_aaindexFN
-#       , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-#if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-if ( len(X.columns) ==  len(X_ssFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/katg_orig.py

@@ -1,202 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'katG'
-drug  = 'isoniazid'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_orig import *
-setvars(gene,drug)
-from ml_data_orig import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: ORIGINAL'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_orig/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/katg_rt.py

@@ -1,202 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'katG'
-drug  = 'isoniazid'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_rt import *
-setvars(gene,drug)
-from ml_data_rt import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: REVERSE training\n'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_rt/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/katg_sl.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'katG'
-drug  = 'isoniazid'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_sl import *
-setvars(gene,drug)
-from ml_data_sl import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: scaling law split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_sl/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/log_alr_7030.txt

@@ -1,4 +1,4 @@
-/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_7030.py:548: SettingWithCopyWarning: 
+/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_7030.py:464: SettingWithCopyWarning: 
 A value is trying to be set on a copy of a slice from a DataFrame
 
 See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
@@ -55,16 +55,13 @@ PASS: OR values imputed, data ready for ML
 
 Total no. of features for aaindex: 123
 
-No. of numerical features: 168 
-No. of categorical features: 7
-
 PASS: x_features has no target variable
 
-No. of columns for x_features: 175
+No. of columns for x_features: 174
 Traceback (most recent call last):
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/./alr_7030.py", line 19, in <module>
+  File "/home/tanu/git/LSHTM_analysis/scripts/ml/./run_7030.py", line 35, in <module>
     setvars(gene,drug)
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_7030.py", line 658, in setvars
+  File "/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_7030.py", line 636, in setvars
     X, X_bts, y, y_bts = train_test_split(x_features, y_target
   File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py", line 2454, in train_test_split
     train, test = next(cv.split(X=arrays[0], y=stratify))

scripts/ml/log_alr_8020.txt

@@ -1,75 +0,0 @@
-/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_8020.py:549: SettingWithCopyWarning: 
-A value is trying to be set on a copy of a slice from a DataFrame
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
-1.22.4
-1.4.1
-
-aaindex_df contains non-numerical data
-
-Total no. of non-numerial columns: 2
-
-Selecting numerical data only
-
-PASS: successfully selected numerical columns only for aaindex_df
-
-Now checking for NA in the remaining aaindex_cols
-
-Counting aaindex_df cols with NA 
-ncols with NA: 4 columns 
-Dropping these... 
-Original ncols: 127
-
-Revised df ncols: 123
-
-Checking NA in revised df...
-
-PASS: cols with NA successfully dropped from aaindex_df 
-Proceeding with combining aa_df with other features_df
-
-PASS: ncols match 
-Expected ncols: 123 
-Got: 123
-
-Total no. of columns in clean aa_df: 123
-
-Proceeding to merge, expected nrows in merged_df: 271
-
-PASS: my_features_df and aa_df successfully combined 
-nrows: 271 
-ncols: 269
-count of NULL values before imputation
-
-or_mychisq          256
-log10_or_mychisq    256
-dtype: int64
-count of NULL values AFTER imputation
-
-mutationinformation    0
-or_rawI                0
-logorI                 0
-dtype: int64
-
-PASS: OR values imputed, data ready for ML
-
-Total no. of features for aaindex: 123
-
-No. of numerical features: 168 
-No. of categorical features: 7
-
-PASS: x_features has no target variable
-
-No. of columns for x_features: 175
-Traceback (most recent call last):
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/./alr_8020.py", line 19, in <module>
-    setvars(gene,drug)
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_8020.py", line 656, in setvars
-    X, X_bts, y, y_bts = train_test_split(x_features, y_target
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py", line 2454, in train_test_split
-    train, test = next(cv.split(X=arrays[0], y=stratify))
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py", line 1613, in split
-    for train, test in self._iter_indices(X, y, groups):
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py", line 1953, in _iter_indices
-    raise ValueError(
-ValueError: The least populated class in y has only 1 member, which is too few. The minimum number of groups for any class cannot be less than 2.

scripts/ml/log_alr_cd_7030.txt

@@ -1,113 +0,0 @@
-/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_cd_7030.py:548: SettingWithCopyWarning: 
-A value is trying to be set on a copy of a slice from a DataFrame
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
-1.22.4
-1.4.1
-
-aaindex_df contains non-numerical data
-
-Total no. of non-numerial columns: 2
-
-Selecting numerical data only
-
-PASS: successfully selected numerical columns only for aaindex_df
-
-Now checking for NA in the remaining aaindex_cols
-
-Counting aaindex_df cols with NA 
-ncols with NA: 4 columns 
-Dropping these... 
-Original ncols: 127
-
-Revised df ncols: 123
-
-Checking NA in revised df...
-
-PASS: cols with NA successfully dropped from aaindex_df 
-Proceeding with combining aa_df with other features_df
-
-PASS: ncols match 
-Expected ncols: 123 
-Got: 123
-
-Total no. of columns in clean aa_df: 123
-
-Proceeding to merge, expected nrows in merged_df: 271
-
-PASS: my_features_df and aa_df successfully combined 
-nrows: 271 
-ncols: 269
-count of NULL values before imputation
-
-or_mychisq          256
-log10_or_mychisq    256
-dtype: int64
-count of NULL values AFTER imputation
-
-mutationinformation    0
-or_rawI                0
-logorI                 0
-dtype: int64
-
-PASS: OR values imputed, data ready for ML
-
-Total no. of features for aaindex: 123
-
-No. of numerical features: 168 
-No. of categorical features: 7
-
-PASS: x_features has no target variable
-
-No. of columns for x_features: 175
-
-------------------------------------------------------------- 
-Successfully split data with stratification [COMPLETE data]: 70/30 
-Original data size: (271, 175) 
-Train data size: (181, 175) 
-Test data size: (90, 175) 
-y_train numbers: Counter({0: 180, 1: 1}) 
-y_train ratio: 180.0 
- 
-y_test_numbers: Counter({0: 89, 1: 1}) 
-y_test ratio: 89.0 
--------------------------------------------------------------
-
-index: 0 
-ind: 1
-
-Mask count check: True
-
-index: 1 
-ind: 2
-
-Mask count check: True
-Original Data
- Counter({0: 180, 1: 1}) Data dim: (181, 175)
-
-Simple Random OverSampling
- Counter({0: 180, 1: 180})
-(360, 175)
-
-Simple Random UnderSampling
- Counter({0: 1, 1: 1})
-(2, 175)
-
-Simple Combined Over and UnderSampling
- Counter({0: 180, 1: 180})
-(360, 175)
-Traceback (most recent call last):
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/./alr_cd_7030.py", line 19, in <module>
-    setvars(gene,drug)
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_cd_7030.py", line 745, in setvars
-    X_smnc, y_smnc = sm_nc.fit_resample(X, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/base.py", line 83, in fit_resample
-    output = self._fit_resample(X, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/over_sampling/_smote/base.py", line 533, in _fit_resample
-    X_resampled, y_resampled = super()._fit_resample(X_encoded, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/over_sampling/_smote/base.py", line 324, in _fit_resample
-    nns = self.nn_k_.kneighbors(X_class, return_distance=False)[:, 1:]
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neighbors/_base.py", line 749, in kneighbors
-    raise ValueError(
-ValueError: Expected n_neighbors <= n_samples,  but n_samples = 1, n_neighbors = 6

scripts/ml/log_alr_cd_8020.txt

@@ -1,69 +0,0 @@
-/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_cd_8020.py:548: SettingWithCopyWarning: 
-A value is trying to be set on a copy of a slice from a DataFrame
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
-1.22.4
-1.4.1
-
-aaindex_df contains non-numerical data
-
-Total no. of non-numerial columns: 2
-
-Selecting numerical data only
-
-PASS: successfully selected numerical columns only for aaindex_df
-
-Now checking for NA in the remaining aaindex_cols
-
-Counting aaindex_df cols with NA 
-ncols with NA: 4 columns 
-Dropping these... 
-Original ncols: 127
-
-Revised df ncols: 123
-
-Checking NA in revised df...
-
-PASS: cols with NA successfully dropped from aaindex_df 
-Proceeding with combining aa_df with other features_df
-
-PASS: ncols match 
-Expected ncols: 123 
-Got: 123
-
-Total no. of columns in clean aa_df: 123
-
-Proceeding to merge, expected nrows in merged_df: 271
-
-PASS: my_features_df and aa_df successfully combined 
-nrows: 271 
-ncols: 269
-count of NULL values before imputation
-
-or_mychisq          256
-log10_or_mychisq    256
-dtype: int64
-count of NULL values AFTER imputation
-
-mutationinformation    0
-or_rawI                0
-logorI                 0
-dtype: int64
-
-PASS: OR values imputed, data ready for ML
-
-Total no. of features for aaindex: 123
-
-No. of numerical features: 168 
-No. of categorical features: 7
-
-PASS: x_features has no target variable
-
-No. of columns for x_features: 175
-Traceback (most recent call last):
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/./alr_cd_8020.py", line 19, in <module>
-    setvars(gene,drug)
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_cd_8020.py", line 666, in setvars
-    yc2_ratio = yc2[0]/yc2[1]
-ZeroDivisionError: division by zero

scripts/ml/log_alr_cd_sl.txt

@@ -1,69 +0,0 @@
-/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_cd_sl.py:548: SettingWithCopyWarning: 
-A value is trying to be set on a copy of a slice from a DataFrame
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
-1.22.4
-1.4.1
-
-aaindex_df contains non-numerical data
-
-Total no. of non-numerial columns: 2
-
-Selecting numerical data only
-
-PASS: successfully selected numerical columns only for aaindex_df
-
-Now checking for NA in the remaining aaindex_cols
-
-Counting aaindex_df cols with NA 
-ncols with NA: 4 columns 
-Dropping these... 
-Original ncols: 127
-
-Revised df ncols: 123
-
-Checking NA in revised df...
-
-PASS: cols with NA successfully dropped from aaindex_df 
-Proceeding with combining aa_df with other features_df
-
-PASS: ncols match 
-Expected ncols: 123 
-Got: 123
-
-Total no. of columns in clean aa_df: 123
-
-Proceeding to merge, expected nrows in merged_df: 271
-
-PASS: my_features_df and aa_df successfully combined 
-nrows: 271 
-ncols: 269
-count of NULL values before imputation
-
-or_mychisq          256
-log10_or_mychisq    256
-dtype: int64
-count of NULL values AFTER imputation
-
-mutationinformation    0
-or_rawI                0
-logorI                 0
-dtype: int64
-
-PASS: OR values imputed, data ready for ML
-
-Total no. of features for aaindex: 123
-
-No. of numerical features: 168 
-No. of categorical features: 7
-
-PASS: x_features has no target variable
-
-No. of columns for x_features: 175
-Traceback (most recent call last):
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/./alr_cd_sl.py", line 19, in <module>
-    setvars(gene,drug)
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_cd_sl.py", line 669, in setvars
-    yc2_ratio = yc2[0]/yc2[1]
-ZeroDivisionError: division by zero

scripts/ml/log_alr_config.txt

@@ -1,105 +0,0 @@
-/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data.py:550: SettingWithCopyWarning: 
-A value is trying to be set on a copy of a slice from a DataFrame
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
-1.22.4
-1.4.1
-
-aaindex_df contains non-numerical data
-
-Total no. of non-numerial columns: 2
-
-Selecting numerical data only
-
-PASS: successfully selected numerical columns only for aaindex_df
-
-Now checking for NA in the remaining aaindex_cols
-
-Counting aaindex_df cols with NA 
-ncols with NA: 4 columns 
-Dropping these... 
-Original ncols: 127
-
-Revised df ncols: 123
-
-Checking NA in revised df...
-
-PASS: cols with NA successfully dropped from aaindex_df 
-Proceeding with combining aa_df with other features_df
-
-PASS: ncols match 
-Expected ncols: 123 
-Got: 123
-
-Total no. of columns in clean aa_df: 123
-
-Proceeding to merge, expected nrows in merged_df: 271
-
-PASS: my_features_df and aa_df successfully combined 
-nrows: 271 
-ncols: 269
-count of NULL values before imputation
-
-or_mychisq          256
-log10_or_mychisq    256
-dtype: int64
-count of NULL values AFTER imputation
-
-mutationinformation    0
-or_rawI                0
-logorI                 0
-dtype: int64
-
-PASS: OR values imputed, data ready for ML
-
-No. of numerical features: 45 
-No. of categorical features: 7
-
-index: 0 
-ind: 1
-
-Mask count check: True
-
-index: 1 
-ind: 2
-
-Mask count check: True
-Original Data
- Counter({0: 7, 1: 1}) Data dim: (8, 52)
-
-------------------------------------------------------------- 
-Successfully split data: UQ [no aa_index but active site included] training 
-actual values: training set 
-imputed values: blind test set 
-Train data size: (8, 52) 
-Test data size: (263, 52) 
-y_train numbers: Counter({0: 7, 1: 1}) 
-y_train ratio: 7.0 
- 
-y_test_numbers: Counter({0: 262, 1: 1}) 
-y_test ratio: 262.0 
--------------------------------------------------------------
-Simple Random OverSampling
- Counter({0: 7, 1: 7})
-(14, 52)
-Simple Random UnderSampling
- Counter({0: 1, 1: 1})
-(2, 52)
-Simple Combined Over and UnderSampling
- Counter({0: 7, 1: 7})
-(14, 52)
-Traceback (most recent call last):
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/./alr_config.py", line 26, in <module>
-    setvars(gene,drug)
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data.py", line 701, in setvars
-    X_smnc, y_smnc = sm_nc.fit_resample(X, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/base.py", line 83, in fit_resample
-    output = self._fit_resample(X, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/over_sampling/_smote/base.py", line 533, in _fit_resample
-    X_resampled, y_resampled = super()._fit_resample(X_encoded, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/over_sampling/_smote/base.py", line 324, in _fit_resample
-    nns = self.nn_k_.kneighbors(X_class, return_distance=False)[:, 1:]
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neighbors/_base.py", line 749, in kneighbors
-    raise ValueError(
-ValueError: Expected n_neighbors <= n_samples,  but n_samples = 1, n_neighbors = 6

scripts/ml/log_alr_orig.txt

@@ -1,107 +0,0 @@
-/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_orig.py:550: SettingWithCopyWarning: 
-A value is trying to be set on a copy of a slice from a DataFrame
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
-1.22.4
-1.4.1
-
-aaindex_df contains non-numerical data
-
-Total no. of non-numerial columns: 2
-
-Selecting numerical data only
-
-PASS: successfully selected numerical columns only for aaindex_df
-
-Now checking for NA in the remaining aaindex_cols
-
-Counting aaindex_df cols with NA 
-ncols with NA: 4 columns 
-Dropping these... 
-Original ncols: 127
-
-Revised df ncols: 123
-
-Checking NA in revised df...
-
-PASS: cols with NA successfully dropped from aaindex_df 
-Proceeding with combining aa_df with other features_df
-
-PASS: ncols match 
-Expected ncols: 123 
-Got: 123
-
-Total no. of columns in clean aa_df: 123
-
-Proceeding to merge, expected nrows in merged_df: 271
-
-PASS: my_features_df and aa_df successfully combined 
-nrows: 271 
-ncols: 269
-count of NULL values before imputation
-
-or_mychisq          256
-log10_or_mychisq    256
-dtype: int64
-count of NULL values AFTER imputation
-
-mutationinformation    0
-or_rawI                0
-logorI                 0
-dtype: int64
-
-PASS: OR values imputed, data ready for ML
-
-Total no. of features for aaindex: 123
-
-No. of numerical features: 168 
-No. of categorical features: 7
-
-index: 0 
-ind: 1
-
-Mask count check: True
-
-index: 1 
-ind: 2
-
-Mask count check: True
-Original Data
- Counter({0: 7, 1: 1}) Data dim: (8, 175)
-
-------------------------------------------------------------- 
-Successfully split data: ORIGINAL training 
-actual values: training set 
-imputed values: blind test set 
-Train data size: (8, 175) 
-Test data size: (263, 175) 
-y_train numbers: Counter({0: 7, 1: 1}) 
-y_train ratio: 7.0 
- 
-y_test_numbers: Counter({0: 262, 1: 1}) 
-y_test ratio: 262.0 
--------------------------------------------------------------
-Simple Random OverSampling
- Counter({0: 7, 1: 7})
-(14, 175)
-Simple Random UnderSampling
- Counter({0: 1, 1: 1})
-(2, 175)
-Simple Combined Over and UnderSampling
- Counter({0: 7, 1: 7})
-(14, 175)
-Traceback (most recent call last):
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/./alr_orig.py", line 19, in <module>
-    setvars(gene,drug)
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_orig.py", line 701, in setvars
-    X_smnc, y_smnc = sm_nc.fit_resample(X, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/base.py", line 83, in fit_resample
-    output = self._fit_resample(X, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/over_sampling/_smote/base.py", line 533, in _fit_resample
-    X_resampled, y_resampled = super()._fit_resample(X_encoded, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/over_sampling/_smote/base.py", line 324, in _fit_resample
-    nns = self.nn_k_.kneighbors(X_class, return_distance=False)[:, 1:]
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neighbors/_base.py", line 749, in kneighbors
-    raise ValueError(
-ValueError: Expected n_neighbors <= n_samples,  but n_samples = 1, n_neighbors = 6

scripts/ml/log_alr_rt.txt

@@ -1,107 +0,0 @@
-/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_rt.py:550: SettingWithCopyWarning: 
-A value is trying to be set on a copy of a slice from a DataFrame
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
-1.22.4
-1.4.1
-
-aaindex_df contains non-numerical data
-
-Total no. of non-numerial columns: 2
-
-Selecting numerical data only
-
-PASS: successfully selected numerical columns only for aaindex_df
-
-Now checking for NA in the remaining aaindex_cols
-
-Counting aaindex_df cols with NA 
-ncols with NA: 4 columns 
-Dropping these... 
-Original ncols: 127
-
-Revised df ncols: 123
-
-Checking NA in revised df...
-
-PASS: cols with NA successfully dropped from aaindex_df 
-Proceeding with combining aa_df with other features_df
-
-PASS: ncols match 
-Expected ncols: 123 
-Got: 123
-
-Total no. of columns in clean aa_df: 123
-
-Proceeding to merge, expected nrows in merged_df: 271
-
-PASS: my_features_df and aa_df successfully combined 
-nrows: 271 
-ncols: 269
-count of NULL values before imputation
-
-or_mychisq          256
-log10_or_mychisq    256
-dtype: int64
-count of NULL values AFTER imputation
-
-mutationinformation    0
-or_rawI                0
-logorI                 0
-dtype: int64
-
-PASS: OR values imputed, data ready for ML
-
-Total no. of features for aaindex: 123
-
-No. of numerical features: 168 
-No. of categorical features: 7
-
-index: 0 
-ind: 1
-
-Mask count check: True
-
-index: 1 
-ind: 2
-
-Mask count check: True
-Original Data
- Counter({0: 262, 1: 1}) Data dim: (263, 175)
-
-------------------------------------------------------------- 
-Successfully split data: REVERSE training 
-imputed values: training set 
-actual values: blind test set 
-Train data size: (263, 175) 
-Test data size: (8, 175) 
-y_train numbers: Counter({0: 262, 1: 1}) 
-y_train ratio: 262.0 
- 
-y_test_numbers: Counter({0: 7, 1: 1}) 
-y_test ratio: 7.0 
--------------------------------------------------------------
-Simple Random OverSampling
- Counter({0: 262, 1: 262})
-(524, 175)
-Simple Random UnderSampling
- Counter({0: 1, 1: 1})
-(2, 175)
-Simple Combined Over and UnderSampling
- Counter({0: 262, 1: 262})
-(524, 175)
-Traceback (most recent call last):
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/./alr_rt.py", line 19, in <module>
-    setvars(gene,drug)
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_rt.py", line 701, in setvars
-    X_smnc, y_smnc = sm_nc.fit_resample(X, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/base.py", line 83, in fit_resample
-    output = self._fit_resample(X, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/over_sampling/_smote/base.py", line 533, in _fit_resample
-    X_resampled, y_resampled = super()._fit_resample(X_encoded, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/over_sampling/_smote/base.py", line 324, in _fit_resample
-    nns = self.nn_k_.kneighbors(X_class, return_distance=False)[:, 1:]
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neighbors/_base.py", line 749, in kneighbors
-    raise ValueError(
-ValueError: Expected n_neighbors <= n_samples,  but n_samples = 1, n_neighbors = 6

scripts/ml/log_alr_sl.txt

@@ -1,75 +0,0 @@
-/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_sl.py:549: SettingWithCopyWarning: 
-A value is trying to be set on a copy of a slice from a DataFrame
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
-1.22.4
-1.4.1
-
-aaindex_df contains non-numerical data
-
-Total no. of non-numerial columns: 2
-
-Selecting numerical data only
-
-PASS: successfully selected numerical columns only for aaindex_df
-
-Now checking for NA in the remaining aaindex_cols
-
-Counting aaindex_df cols with NA 
-ncols with NA: 4 columns 
-Dropping these... 
-Original ncols: 127
-
-Revised df ncols: 123
-
-Checking NA in revised df...
-
-PASS: cols with NA successfully dropped from aaindex_df 
-Proceeding with combining aa_df with other features_df
-
-PASS: ncols match 
-Expected ncols: 123 
-Got: 123
-
-Total no. of columns in clean aa_df: 123
-
-Proceeding to merge, expected nrows in merged_df: 271
-
-PASS: my_features_df and aa_df successfully combined 
-nrows: 271 
-ncols: 269
-count of NULL values before imputation
-
-or_mychisq          256
-log10_or_mychisq    256
-dtype: int64
-count of NULL values AFTER imputation
-
-mutationinformation    0
-or_rawI                0
-logorI                 0
-dtype: int64
-
-PASS: OR values imputed, data ready for ML
-
-Total no. of features for aaindex: 123
-
-No. of numerical features: 168 
-No. of categorical features: 7
-
-PASS: x_features has no target variable
-
-No. of columns for x_features: 175
-Traceback (most recent call last):
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/./alr_sl.py", line 19, in <module>
-    setvars(gene,drug)
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_sl.py", line 660, in setvars
-    X, X_bts, y, y_bts = train_test_split(x_features, y_target
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py", line 2454, in train_test_split
-    train, test = next(cv.split(X=arrays[0], y=stratify))
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py", line 1613, in split
-    for train, test in self._iter_indices(X, y, groups):
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/model_selection/_split.py", line 1953, in _iter_indices
-    raise ValueError(
-ValueError: The least populated class in y has only 1 member, which is too few. The minimum number of groups for any class cannot be less than 2.

scripts/ml/log_gid_rt_v1.txt

@@ -1,107 +0,0 @@
-/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_rt.py:550: SettingWithCopyWarning: 
-A value is trying to be set on a copy of a slice from a DataFrame
-
-See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
-  mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
-1.22.4
-1.4.1
-
-aaindex_df contains non-numerical data
-
-Total no. of non-numerial columns: 2
-
-Selecting numerical data only
-
-PASS: successfully selected numerical columns only for aaindex_df
-
-Now checking for NA in the remaining aaindex_cols
-
-Counting aaindex_df cols with NA 
-ncols with NA: 4 columns 
-Dropping these... 
-Original ncols: 127
-
-Revised df ncols: 123
-
-Checking NA in revised df...
-
-PASS: cols with NA successfully dropped from aaindex_df 
-Proceeding with combining aa_df with other features_df
-
-PASS: ncols match 
-Expected ncols: 123 
-Got: 123
-
-Total no. of columns in clean aa_df: 123
-
-Proceeding to merge, expected nrows in merged_df: 531
-
-PASS: my_features_df and aa_df successfully combined 
-nrows: 531 
-ncols: 286
-count of NULL values before imputation
-
-or_mychisq          263
-log10_or_mychisq    263
-dtype: int64
-count of NULL values AFTER imputation
-
-mutationinformation    0
-or_rawI                0
-logorI                 0
-dtype: int64
-
-PASS: OR values imputed, data ready for ML
-
-Total no. of features for aaindex: 123
-
-No. of numerical features: 167 
-No. of categorical features: 7
-
-index: 0 
-ind: 1
-
-Mask count check: True
-
-index: 1 
-ind: 2
-
-Mask count check: True
-Original Data
- Counter({0: 409, 1: 3}) Data dim: (412, 174)
-
-------------------------------------------------------------- 
-Successfully split data: REVERSE training 
-imputed values: training set 
-actual values: blind test set 
-Train data size: (412, 174) 
-Test data size: (119, 174) 
-y_train numbers: Counter({0: 409, 1: 3}) 
-y_train ratio: 136.33333333333334 
- 
-y_test_numbers: Counter({0: 76, 1: 43}) 
-y_test ratio: 1.7674418604651163 
--------------------------------------------------------------
-Simple Random OverSampling
- Counter({0: 409, 1: 409})
-(818, 174)
-Simple Random UnderSampling
- Counter({0: 3, 1: 3})
-(6, 174)
-Simple Combined Over and UnderSampling
- Counter({0: 409, 1: 409})
-(818, 174)
-Traceback (most recent call last):
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/./gid_rt.py", line 19, in <module>
-    setvars(gene,drug)
-  File "/home/tanu/git/LSHTM_analysis/scripts/ml/ml_data_rt.py", line 701, in setvars
-    X_smnc, y_smnc = sm_nc.fit_resample(X, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/base.py", line 83, in fit_resample
-    output = self._fit_resample(X, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/over_sampling/_smote/base.py", line 533, in _fit_resample
-    X_resampled, y_resampled = super()._fit_resample(X_encoded, y)
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/imblearn/over_sampling/_smote/base.py", line 324, in _fit_resample
-    nns = self.nn_k_.kneighbors(X_class, return_distance=False)[:, 1:]
-  File "/home/tanu/anaconda3/envs/UQ/lib/python3.9/site-packages/sklearn/neighbors/_base.py", line 749, in kneighbors
-    raise ValueError(
-ValueError: Expected n_neighbors <= n_samples,  but n_samples = 3, n_neighbors = 6

scripts/ml/ml_data_7030.py

@@ -572,9 +572,10 @@ def setvars(gene,drug):
                           , 'lineage_count_unique'
                           ]
     
-    X_gn_Fcat = ['drtype_mode_labels'  # beware then you can't use it to predict [USED it for uq_v1, not v2]
-                   #, 'gene_name' # will be required for the combined stuff
-                 ]
+    # X_gn_Fcat = ['drtype_mode_labels'  # beware then you can't use it to predict [USED it for uq_v1, not v2]
+    #                #, 'gene_name' # will be required for the combined stuff
+    #              ]
+    X_gn_Fcat = []
     
     X_genomicFN = X_gn_mafor_Fnum + X_gn_linegae_Fnum + X_gn_Fcat
     ###############################################################################

scripts/ml/pnca_7030.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'pncA'
-drug  = 'pyrazinamide'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_7030 import *
-setvars(gene,drug)
-from ml_data_7030 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_7030/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/pnca_8020.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'pncA'
-drug  = 'pyrazinamide'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_8020 import *
-setvars(gene,drug)
-from ml_data_8020 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: 80/20 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_8020/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/pnca_cd_7030.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'pncA'
-drug  = 'pyrazinamide'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_7030 import *
-setvars(gene,drug)
-from ml_data_cd_7030 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_7030/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/pnca_cd_8020.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'pncA'
-drug  = 'pyrazinamide'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_8020 import *
-setvars(gene,drug)
-from ml_data_cd_8020 import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 80/20 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_8020/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/pnca_cd_sl.py

@@ -1,203 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'pncA'
-drug  = 'pyrazinamide'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_cd_sl import *
-setvars(gene,drug)
-from ml_data_cd_sl import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-################################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis [COMPLETE DATA]: 70/30 split'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-      
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_cd_sl/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      #, '\nML source data size:', x_features.shape
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-################################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/pnca_config.py

@@ -1,210 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'pncA'
-drug  = 'pyrazinamide'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-#---------------------------
-# Version 1: no AAindex
-#from UQ_ML_data import *
-#setvars(gene,drug)
-#from UQ_ML_data import *
-#---------------------------
-
-from ml_data import *
-setvars(gene,drug)
-from ml_data import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: UQ [without AA  index but with active site annotations]'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/uq_v1/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-# print('AAindex features (n):'
-#       , len(X_aaindexFN)
-#       , '\nThese are:\n'
-#       , X_aaindexFN
-#       , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-#if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-if ( len(X.columns) ==  len(X_ssFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')

scripts/ml/pnca_orig.py

@@ -1,202 +0,0 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Sat May 28 05:25:30 2022
-
-@author: tanu
-"""
-
-import os
-
-gene  = 'pncA'
-drug  = 'pyrazinamide'
-#total_mtblineage_uc = 8
-
-homedir = os.path.expanduser("~")
-os.chdir( homedir + '/git/LSHTM_analysis/scripts/ml/')
-
-from ml_data_orig import *
-setvars(gene,drug)
-from ml_data_orig import *
-
-# from YC run_all_ML: run locally
-#from UQ_yc_RunAllClfs import run_all_ML
-
-# TT run all ML clfs: baseline mode
-from MultModelsCl import MultModelsCl
-
-############################################################################
-print('\n#####################################################################\n'
-      , '\nRunning ML analysis: ORIGINAL'
-      , '\nGene name:', gene
-      , '\nDrug name:', drug)
-
-#==================
-# Specify outdir 
-#==================
-
-outdir_ml = outdir + 'ml/tts_orig/'
-
-print('\nOutput directory:', outdir_ml)
-
-#%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
-print('\n================================================================\n')
-
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
-
-print('AAindex features (n):'
-      , len(X_aaindexFN)
-      , '\nThese are:\n'
-      , X_aaindexFN
-      , '\n================================================================\n')
-
-print('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
-
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
-
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
-
-if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-    print('\nPass: No. of features match')
-else:
-    sys.exit('\nFail: Count of feature mismatch')
-
-print('\n#####################################################################\n')
-
-###############################################################################
-#==================
-# Baseline models 
-#==================
-mm_skf_scoresD = MultModelsCl(input_df = X
-                                        , target = y
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-
-baseline_all = pd.DataFrame(mm_skf_scoresD)
-baseline_all = baseline_all.T
-#baseline_train = baseline_all.filter(like='train_', axis=1)
-baseline_CT = baseline_all.filter(like='test_', axis=1)
-baseline_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-baseline_BT = baseline_all.filter(like='bts_', axis=1)
-baseline_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-baseline_CT.to_csv(outdir_ml + gene.lower() + '_baseline_CT_allF.csv')
-baseline_BT.to_csv(outdir_ml + gene.lower() + '_baseline_BT_allF.csv')
-
-
-#%% SMOTE NC: Oversampling [Numerical + categorical]
-mm_skf_scoresD7 = MultModelsCl(input_df = X_smnc
-                                        , target = y_smnc
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-smnc_all = pd.DataFrame(mm_skf_scoresD7)
-smnc_all = smnc_all.T
-
-smnc_CT = smnc_all.filter(like='test_', axis=1)
-smnc_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-smnc_BT = smnc_all.filter(like='bts_', axis=1)
-smnc_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-smnc_CT.to_csv(outdir_ml + gene.lower() + '_smnc_CT_allF.csv')
-smnc_BT.to_csv(outdir_ml + gene.lower() + '_smnc_BT_allF.csv')
-
-#%% ROS: Numerical + categorical
-mm_skf_scoresD3 = MultModelsCl(input_df = X_ros
-                                        , target = y_ros
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-ros_all = pd.DataFrame(mm_skf_scoresD3)
-ros_all = ros_all.T
-
-ros_CT  = ros_all.filter(like='test_', axis=1)
-ros_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-ros_BT  = ros_all.filter(like='bts_', axis=1)
-ros_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-ros_CT.to_csv(outdir_ml + gene.lower() + '_ros_CT_allF.csv')
-ros_BT.to_csv(outdir_ml + gene.lower() + '_ros_BT_allF.csv')
-
-#%% RUS: Numerical + categorical
-mm_skf_scoresD4 = MultModelsCl(input_df = X_rus
-                                        , target = y_rus
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rus_all = pd.DataFrame(mm_skf_scoresD4)
-rus_all = rus_all.T
-
-rus_CT = rus_all.filter(like='test_', axis=1)
-rus_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rus_BT = rus_all.filter(like='bts_' , axis=1)
-rus_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rus_CT.to_csv(outdir_ml + gene.lower() + '_rus_CT_allF.csv')
-rus_BT.to_csv(outdir_ml + gene.lower() + '_rus_BT_allF.csv')
-
-#%% ROS + RUS Combined: Numerical + categorical
-mm_skf_scoresD8 = MultModelsCl(input_df = X_rouC
-                                        , target = y_rouC
-                                        , var_type = 'mixed'
-                                        , skf_cv = skf_cv
-                                        , blind_test_input_df = X_bts
-                                        , blind_test_target = y_bts)
-rouC_all = pd.DataFrame(mm_skf_scoresD8)
-rouC_all = rouC_all.T
-
-rouC_CT = rouC_all.filter(like='test_', axis=1)
-rouC_CT.sort_values(by = ['test_mcc'], ascending = False, inplace = True)
-
-rouC_BT = rouC_all.filter(like='bts_', axis=1)
-rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
-# Write csv
-rouC_CT.to_csv(outdir_ml + gene.lower() + '_rouC_CT_allF.csv')
-rouC_BT.to_csv(outdir_ml + gene.lower() + '_rouC_BT_allF.csv')