saving work

scripts/ml/combined_model/cm_logo_skf.py

@@ -9,6 +9,72 @@ import sys, os
 import pandas as pd
 import numpy as np
 import re
+from copy import deepcopy
+from sklearn import linear_model
+from sklearn import datasets
+from collections import Counter
+
+from sklearn.linear_model import LogisticRegression, LogisticRegressionCV
+from sklearn.linear_model import RidgeClassifier, RidgeClassifierCV, SGDClassifier, PassiveAggressiveClassifier
+
+from sklearn.naive_bayes import BernoulliNB
+from sklearn.neighbors import KNeighborsClassifier
+from sklearn.svm import SVC
+from sklearn.tree import DecisionTreeClassifier, ExtraTreeClassifier
+from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, AdaBoostClassifier, GradientBoostingClassifier, BaggingClassifier
+from sklearn.naive_bayes import GaussianNB
+from sklearn.gaussian_process import GaussianProcessClassifier, kernels
+from sklearn.gaussian_process.kernels import RBF, DotProduct, Matern, RationalQuadratic, WhiteKernel
+
+from sklearn.discriminant_analysis import LinearDiscriminantAnalysis, QuadraticDiscriminantAnalysis
+from sklearn.neural_network import MLPClassifier
+
+from sklearn.svm import SVC
+from xgboost import XGBClassifier
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.preprocessing import StandardScaler, MinMaxScaler, OneHotEncoder
+
+from sklearn.compose import ColumnTransformer
+from sklearn.compose import make_column_transformer
+
+from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
+from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
+
+# added
+from sklearn.model_selection import train_test_split, cross_validate, cross_val_score, LeaveOneOut, KFold, RepeatedKFold, cross_val_predict
+
+from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
+from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
+
+from sklearn.pipeline import Pipeline, make_pipeline
+
+from sklearn.feature_selection import RFE, RFECV
+
+import itertools
+import seaborn as sns
+import matplotlib.pyplot as plt
+
+from statistics import mean, stdev, median, mode
+
+from imblearn.over_sampling import RandomOverSampler
+from imblearn.under_sampling import RandomUnderSampler
+from imblearn.over_sampling import SMOTE
+from sklearn.datasets import make_classification
+from imblearn.combine import SMOTEENN
+from imblearn.combine import SMOTETomek
+
+from imblearn.over_sampling import SMOTENC
+from imblearn.under_sampling import EditedNearestNeighbours
+from imblearn.under_sampling import RepeatedEditedNearestNeighbours
+
+from sklearn.model_selection import GridSearchCV
+from sklearn.base import BaseEstimator
+from sklearn.impute import KNNImputer as KNN
+import json
+import argparse
+import re
+import itertools
+from sklearn.model_selection import LeaveOneGroupOut
 ###############################################################################
 homedir = os.path.expanduser("~")
 sys.path.append(homedir + '/git/LSHTM_analysis/scripts/ml/ml_functions')
@@ -22,7 +88,7 @@ from MultClfs_logo_skf import *
 #from GetMLData import *
 #from SplitTTS import *
 
-skf_cv = StratifiedKFold(n_splits = 10 , shuffle = True,**rs)
+skf_cv = StratifiedKFold(n_splits = 10 , shuffle = True, random_state = 42)
 
 #logo = LeaveOneGroupOut()
 
@@ -38,13 +104,17 @@ def CMLogoSkf(combined_df
 
     for bts_gene in bts_genes:
         print('\n BTS gene:', bts_gene)
+        if not std_gene_omit:
+            training_genesL = ['alr']
+        else:
+            training_genesL = []
             
         tr_gene_omit = std_gene_omit + [bts_gene]
         n_tr_genes = (len(bts_genes) - (len(std_gene_omit)))
         #n_total_genes = (len(bts_genes) - len(std_gene_omit))
         n_total_genes = len(all_genes)
         
-        training_genesL = std_gene_omit + list(set(bts_genes) - set(tr_gene_omit))
+        training_genesL = training_genesL + list(set(bts_genes) - set(tr_gene_omit))
         #training_genesL = [element for element in bts_genes if element not in tr_gene_omit]
     
         print('\nTotal genes: ', n_total_genes
@@ -53,7 +123,7 @@ def CMLogoSkf(combined_df
               , '\nOmitted genes:', tr_gene_omit
               , '\nBlind test gene:', bts_gene) 
             
-        tts_split_type = "logoBT_" + bts_gene
+        tts_split_type = "logo_skf_BT_" + bts_gene
         
         outFile = "/home/tanu/git/Data/ml_combined/" + str(n_tr_genes+1) + "genes_" + tts_split_type + ".csv"
         print(outFile)
@@ -67,7 +137,6 @@ def CMLogoSkf(combined_df
         #cm_y = cm_training_df.loc[:,'dst_mode']
         cm_y = cm_training_df.loc[:, target_var]
     
-    
         gene_group = cm_training_df.loc[:,'gene_name']
         
         print('\nTraining data dim:', cm_X.shape
@@ -87,14 +156,14 @@ def CMLogoSkf(combined_df
         #cm_bts_y = cm_test_df.loc[:, 'dst_mode']
         cm_bts_y = cm_test_df.loc[:, target_var]
     
-        print('\nTraining data dim:', cm_bts_X.shape
+        print('\nTEST data dim:', cm_bts_X.shape
-              , '\nTraining Target dim:', cm_bts_y.shape)
+              , '\nTEST Target dim:', cm_bts_y.shape)
         
         
         #%%:Running Multiple models on LOGO with SKF
         cD3_v2 = MultModelsCl_logo_skf(input_df = cm_X
                         , target = cm_y
-                        , group = 'none'
+                        #, group = 'none'
                         , sel_cv = skf_cv
         
                         , blind_test_df = cm_bts_X
@@ -116,5 +185,5 @@ def CMLogoSkf(combined_df
         cD3_v2.to_csv(outFile)
 
 #%%
-CMLogoSkf(combined_df)
+#CMLogoSkf(combined_df)
 CMLogoSkf(combined_df, std_gene_omit=['alr'])

scripts/ml/ml_functions/FS.py

@@ -77,6 +77,7 @@ import re
 #####################################
 rs = {'random_state': 42}
 njobs = {'n_jobs': 10}
+    
 
 scoring_fn =  ({ 'mcc'        : make_scorer(matthews_corrcoef)
                 , 'fscore'    : make_scorer(f1_score)
@@ -87,6 +88,9 @@ scoring_fn =  ({ 'mcc'        : make_scorer(matthews_corrcoef)
                 , 'jcc'       : make_scorer(jaccard_score)
             }) 
   
+
+mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
+jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
 skf_cv = StratifiedKFold(n_splits = 10
                           #, shuffle = False, random_state= None)
                            , shuffle = True,**rs)
@@ -95,9 +99,6 @@ rskf_cv = RepeatedStratifiedKFold(n_splits = 10
                                   , n_repeats = 3
                                   , **rs)
 
-mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
-jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
-
 ###############################################################################
 def fsgs_rfecv(input_df
          , target
@@ -109,7 +110,10 @@ def fsgs_rfecv(input_df
          , custom_fs = RFECV(DecisionTreeClassifier(**rs) , cv =  skf_cv, scoring = 'matthews_corrcoef')
          , cv_method =  skf_cv
          , var_type = ['numerical', 'categorical' , 'mixed']
+         , resampling_type = 'none'
          , verbose = 3
+         , random_state = 42
+         , n_jobs = 10
          ):
     '''
     returns
@@ -120,6 +124,10 @@ def fsgs_rfecv(input_df
     optimised/selected based on mcc
     
     '''
+    rs = {'random_state': random_state}
+    njobs = {'n_jobs': n_jobs}
+
+    
     ###########################################################################
     #================================================
     # Determine categorical and numerical features
@@ -375,6 +383,8 @@ def fsgs_rfecv(input_df
     output_modelD['train_score (MCC)'] = train_bscore
     output_modelD['bts_mcc'] = bts_mcc_score
     output_modelD['train_bts_diff'] = round(train_test_diff,2)
+    output_modelD['resampling'] = resampling_type
+
     print(output_modelD)
     
     nlen = len(output_modelD)

scripts/ml/ml_functions/MultClfs_logo_skf.py

@@ -77,9 +77,6 @@ import re
 import itertools
 from sklearn.model_selection import LeaveOneGroupOut
 #%% GLOBALS
-rs = {'random_state': 42}
-njobs = {'n_jobs': 10}
-
 scoring_fn =  ({ 'mcc'        : make_scorer(matthews_corrcoef)
                 , 'fscore'    : make_scorer(f1_score)
                 , 'precision' : make_scorer(precision_score)
@@ -146,7 +143,7 @@ def MultModelsCl_logo_skf(input_df
                        , blind_test_df = pd.DataFrame()
                        , blind_test_target = pd.Series(dtype = int)
                        , tts_split_type = "none"
-                       , group = 'none'
+                       #, group = 'none'
 
                        , resampling_type = 'none' # default
                        , add_cm = True # adds confusion matrix based on cross_val_predict
@@ -188,11 +185,11 @@ def MultModelsCl_logo_skf(input_df
                                       , **rs)
     logo = LeaveOneGroupOut()
 
-    # select CV type:           
+    # # select CV type:           
-    if group == 'none':
+    # if group == 'none':
-        sel_cv = skf_cv
+    #     sel_cv = skf_cv
-    else: 
+    # else: 
-        sel_cv = logo
+    #     sel_cv = logo
     #======================================================
     # Determine categorical and numerical features
     #======================================================
@@ -277,7 +274,7 @@ def MultModelsCl_logo_skf(input_df
                               , input_df
                               , target
                               , cv = sel_cv
-                              , groups = group
+                              #, groups = group
                               , scoring = scoring_fn
                               , return_train_score = True)
         #==============================
@@ -306,7 +303,12 @@ def MultModelsCl_logo_skf(input_df
            cmD = {}
 
             # Calculate cm         
-           y_pred   = cross_val_predict(model_pipeline, input_df, target, cv = sel_cv, groups = group, **njobs)
+           y_pred   = cross_val_predict(model_pipeline
+                                        , input_df
+                                        , target
+                                        , cv = sel_cv
+                                        #, groups = group
+                                        , **njobs)
             #_tn, _fp, _fn, _tp = confusion_matrix(y_pred, y).ravel() # internally
            tn, fp, fn, tp = confusion_matrix(y_pred, target).ravel()