various changes

LR_FS.json

@@ -0,0 +1 @@
+{"model_name": "GradientBoostingClassifier(n_estimators=10, random_state=42, subsample=0.7)", "model_refit_param": "mcc", "Best_model_params": {"clf__learning_rate": 0.1, "clf__max_depth": 3, "clf__n_estimators": 10, "clf__subsample": 0.7}, "n_all_features": 13, "fs_method": "RFECV(cv=RepeatedStratifiedKFold(n_repeats=3, n_splits=10, random_state=42),\n      estimator=LogisticRegression(random_state=42),\n      scoring='matthews_corrcoef')", "fs_res_array": "[False, False, False, False, True, False, False, True, False, False, False, False, True]", "fs_res_array_rank": [3, 5, 8, 2, 1, 10, 7, 1, 6, 4, 9, 11, 1], "all_feature_names": ["ligand_distance", "ligand_affinity_change", "duet_stability_change", "ddg_foldx", "deepddg", "ddg_dynamut2", "contacts", "rsa", "kd_values", "rd_values", "consurf_score", "snap2_score", "maf"], "n_sel_features": 2, "sel_features_names": ["ddg_foldx", "rd_values"], "bts_fscore": 0.7, "bts_precision": 0.56, "bts_recall": 0.93, "bts_accuracy": 0.61, "bts_roc_auc": 0.61, "bts_jaccard": 0.54, "train_score (MCC)": 0.23, "bts_mcc": 0.28, "train_bts_diff": -0.05}

MLfeature_types.py

@@ -9,11 +9,11 @@ Created on Sun May 29 06:46:19 2022
 #%% Build X: input for ML
     
 print('Strucutral features (n):'
-      , len(common_cols_stabiltyN) + len(foldX_cols)  + len(X_strFN)
+      , len(X_ssFN)
       , '\nThese are:'
-      , '\nCommon stablity features:', common_cols_stabiltyN
+      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', foldX_cols
+      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_strFN
+      , '\nOther struc columns:', X_str
       , '\n================================================================\n')
 
 print('Evolutionary features (n):'
@@ -36,3 +36,7 @@ print('Categorical features (n):'
       , categorical_FN
       , '\n================================================================\n')
 
+if ( len(X.columns) ==  len(X_ssFN) +len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
+    print('\nPass: No. of features match')
+else:
+    print('\nFail: Count of feature mismatch')

MultModelsCl_CALL.py

@@ -6,36 +6,36 @@ Created on Tue Mar 15 11:09:50 2022
 @author: tanu
 """
 
-from sklearn.metrics import make_scorer, confusion_matrix, accuracy_score, balanced_accuracy_score, precision_score, average_precision_score, recall_score
+# 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
+# from sklearn.metrics import roc_auc_score, roc_curve, f1_score, matthews_corrcoef, jaccard_score, classification_report
 
-from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
+# from sklearn.model_selection import train_test_split, cross_validate, cross_val_score
-from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
+# from sklearn.model_selection import StratifiedKFold,RepeatedStratifiedKFold, RepeatedKFold
 
-from sklearn.pipeline import Pipeline, make_pipeline
+# from sklearn.pipeline import Pipeline, make_pipeline
-#%% GLOBALS
+# #%% GLOBALS
-rs = {'random_state': 42}
+# rs = {'random_state': 42}
-njobs = {'n_jobs': 10}
+# njobs = {'n_jobs': 10}
 
-scoring_fn =  ({'accuracy'      : make_scorer(accuracy_score)
+# scoring_fn =  ({'accuracy'      : make_scorer(accuracy_score)
-                 , 'fscore'     : make_scorer(f1_score)
+#                  , 'fscore'     : make_scorer(f1_score)
-                 , 'mcc'        : make_scorer(matthews_corrcoef)
+#                  , 'mcc'        : make_scorer(matthews_corrcoef)
-                 , 'precision'  : make_scorer(precision_score)
+#                  , 'precision'  : make_scorer(precision_score)
-                 , 'recall'     : make_scorer(recall_score)
+#                  , 'recall'     : make_scorer(recall_score)
-                 , 'roc_auc'    : make_scorer(roc_auc_score)
+#                  , 'roc_auc'    : make_scorer(roc_auc_score)
-                 , 'jcc'        : make_scorer(jaccard_score)
+#                  , 'jcc'        : make_scorer(jaccard_score)
-            }) 
+#             }) 
   
-skf_cv = StratifiedKFold(n_splits = 10
+# skf_cv = StratifiedKFold(n_splits = 10
-                          #, shuffle = False, random_state= None)
+#                           #, shuffle = False, random_state= None)
-                           , shuffle = True,**rs)
+#                            , shuffle = True,**rs)
 
-rskf_cv = RepeatedStratifiedKFold(n_splits = 10
+# rskf_cv = RepeatedStratifiedKFold(n_splits = 10
-                                  , n_repeats = 3
+#                                   , n_repeats = 3
-                                  , **rs)
+#                                   , **rs)
 
-mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
+# mcc_score_fn = {'mcc': make_scorer(matthews_corrcoef)}
-jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
+# jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
 
 ###############################################################################
 #%% MultModelsCl: function call()
@@ -55,6 +55,9 @@ 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_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
@@ -70,6 +73,10 @@ 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_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
@@ -85,6 +92,9 @@ 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_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
@@ -100,6 +110,9 @@ 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_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
@@ -116,6 +129,8 @@ 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_BT.to_csv(outdir + 'ml/' + gene.lower() + '_rouC_BT_allF.csv')
 #%% SMOTE OS: Numerical only
 # mm_skf_scoresD2 = MultModelsCl(input_df = X_sm
 #                                         , target = y_sm
@@ -130,6 +145,8 @@ rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
 # sm_BT = sm_all.filter(like='bts_', axis=1)
 #sm_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
 
+# Write csv
+#sm_BT.to_csv(outdir + 'ml/' + gene.lower() + '_sm_BT_allF.csv')
 #%% SMOTE ENN: Over + Undersampling combined: Numerical ONLY
 # mm_skf_scoresD5 = MultModelsCl(input_df = X_enn
 #                                         , target = y_enn
@@ -146,6 +163,9 @@ rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
 # enn_BT = enn_all.filter(like='bts_', axis=1)
 #enn_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
 
+# Write csv
+#enn_BT.to_csv(outdir + 'ml/' + gene.lower() + '_enn_BT_allF.csv')
+
 #%% Repeated ENN
 # mm_skf_scoresD6 = MultModelsCl(input_df = X_renn
 #                                         , target = y_renn
@@ -161,5 +181,6 @@ rouC_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
 
 # renn_BT = renn_all.filter(like='bts_', axis=1)
 # renn_BT.sort_values(by = ['bts_mcc'], ascending = False, inplace = True)
-
+###############################################################################
-
+# end of script
+##############################################################################

UQ_ML_data.py

@@ -27,6 +27,37 @@ def setvars(gene,drug):
     from imblearn.under_sampling import EditedNearestNeighbours
     from imblearn.under_sampling import RepeatedEditedNearestNeighbours
     
+    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
+
+    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
+    #%% GLOBALS
+    rs = {'random_state': 42}
+    njobs = {'n_jobs': 10}
+
+    scoring_fn =  ({ 'mcc'         : make_scorer(matthews_corrcoef)
+                    , 'accuracy'   : make_scorer(accuracy_score)
+                    , 'fscore'     : make_scorer(f1_score)
+                    , 'precision'  : make_scorer(precision_score)
+                    , 'recall'     : make_scorer(recall_score)
+                    , 'roc_auc'    : make_scorer(roc_auc_score)
+                    , 'jcc'        : make_scorer(jaccard_score)
+                }) 
+      
+    skf_cv = StratifiedKFold(n_splits = 10
+                              #, shuffle = False, random_state= None)
+                               , shuffle = True,**rs)
+
+    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)}
+
     #%% FOR LATER: Combine ED logo data
     #%% FOR LARER: active aa site annotations
     ###########################################################################
@@ -52,31 +83,41 @@ def setvars(gene,drug):
     my_df_cols = my_df.columns
     
     geneL_basic     = ['pnca']
-    
+    geneL_na        = ['gid']
-    # -- CHECK script -- imports.py
+    geneL_na_ppi2   = ['rpob']
+    geneL_ppi2      = ['alr', 'embb', 'katg']
     #%% get cols
     mycols = my_df.columns
-    mycols
     
-    # change from numberic to 
+    # # change from numberic to 
-    num_type = ['int64', 'float64']
+    # num_type = ['int64', 'float64']
-    cat_type = ['object', 'bool']
+    # cat_type = ['object', 'bool']
     
-    #TODO:
-    # #Treat active site aa pos as category and not numerical: This needs to be part of merged_df3!
     # if my_df['active_aa_pos'].dtype in num_type:
     #     my_df['active_aa_pos'] = my_df['active_aa_pos'].astype(object)
     #     my_df['active_aa_pos'].dtype
     
-    # -- CHECK script -- imports.py
+    # FIXME: if this is not structural, remove from source..
+    # Drop NA where numerical cols have them
+    if gene.lower() in geneL_na_ppi2:
+        #D1148 get rid of
+        na_index = my_df['mutationinformation'].index[my_df['mcsm_na_affinity'].apply(np.isnan)]
+        my_df = my_df.drop(index=na_index)
+    
+    # FIXME: either impute or remove!
+    # for embb (L114M, F115L, V123L, V125I, V131M) delete for now
+    if gene.lower() in ['embb']:
+        na_index = my_df['mutationinformation'].index[my_df['ligand_distance'].apply(np.isnan)]
+        my_df = my_df.drop(index=na_index)# RERUN embb with the 5 values now present
+       
     ###########################################################################
     #%% Add lineage calculation columns
     #FIXME: Check if this can be imported from config?
-    total_mtblineage_u = 8
+    total_mtblineage_uc = 8
     lineage_colnames = ['lineage_list_all', 'lineage_count_all', 'lineage_count_unique', 'lineage_list_unique', 'lineage_multimode']
     #bar = my_df[lineage_colnames]
     my_df['lineage_proportion']      = my_df['lineage_count_unique']/my_df['lineage_count_all']
-    my_df['dist_lineage_proportion'] = my_df['lineage_count_unique']/total_mtblineage_u
+    my_df['dist_lineage_proportion'] = my_df['lineage_count_unique']/total_mtblineage_uc
     ###########################################################################
     #%% AA property change
     #--------------------
@@ -219,15 +260,6 @@ def setvars(gene,drug):
     #==========================
     my_df_ml = my_df.copy()
     
-    #%% Masking columns (mCSM-lig, mCSM-NA, mCSM-ppi2) values for lig_dist >10
-    my_df_ml['mutationinformation'][my_df['ligand_distance']>10].value_counts()
-    my_df_ml.groupby('mutationinformation')['ligand_distance'].apply(lambda x: (x>10)).value_counts()
-    my_df_ml.groupby(['mutationinformation'])['ligand_distance'].apply(lambda x: (x>10)).value_counts()
-    
-    my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), 'ligand_affinity_change'] = 0
-    (my_df_ml['ligand_affinity_change'] == 0).sum()
-    
-    #%%########################################################################
     #==========================
     #     BLIND test set
     #==========================
@@ -254,7 +286,31 @@ def setvars(gene,drug):
                , 'mmcsm_lig'
                , 'contacts']
     
-    foldX_cols = [ 'electro_rr', 'electro_mm', 'electro_sm', 'electro_ss'
+    # Build stability columns ~ gene
+    if gene.lower() in geneL_basic:
+        X_stabilityN = common_cols_stabiltyN
+        cols_to_mask = ['ligand_affinity_change']
+        
+    if gene.lower() in geneL_ppi2:
+    #    X_stabilityN = common_cols_stabiltyN + ['mcsm_ppi2_affinity' , 'interface_dist'] 
+        geneL_ppi2_st_cols = ['mcsm_ppi2_affinity', 'interface_dist'] 
+        X_stabilityN = common_cols_stabiltyN + geneL_ppi2_st_cols
+        cols_to_mask = ['ligand_affinity_change', 'mcsm_ppi2_affinity']
+    
+    if gene.lower() in geneL_na:
+    #    X_stabilityN = common_cols_stabiltyN + ['mcsm_na_affinity'] 
+        geneL_na_st_cols =  ['mcsm_na_affinity'] 
+        X_stabilityN = common_cols_stabiltyN + geneL_na_st_cols
+        cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity']
+    
+    if gene.lower() in geneL_na_ppi2:
+    #    X_stabilityN = common_cols_stabiltyN + ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist'] 
+        geneL_na_ppi2_st_cols = ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist'] 
+        X_stabilityN = common_cols_stabiltyN + geneL_na_ppi2_st_cols
+        cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity', 'mcsm_ppi2_affinity']
+    
+
+    X_foldX_cols = [ 'electro_rr', 'electro_mm', 'electro_sm', 'electro_ss'
     , 'disulfide_rr', 'disulfide_mm', 'disulfide_sm', 'disulfide_ss'
     , 'hbonds_rr', 'hbonds_mm', 'hbonds_sm', 'hbonds_ss'
     , 'partcov_rr', 'partcov_mm', 'partcov_sm', 'partcov_ss'
@@ -262,11 +318,13 @@ def setvars(gene,drug):
     , 'volumetric_rr', 'volumetric_mm', 'volumetric_ss'
     ]
     
-    X_strFN =  ['rsa'
+    X_str =  ['rsa'
                #, 'asa'
                , 'kd_values'
                , 'rd_values']    
     
+    X_ssFN = X_stabilityN + X_str + X_foldX_cols
+    
     X_evolFN =  ['consurf_score'
                , 'snap2_score'
                , 'provean_score']
@@ -291,7 +349,9 @@ def setvars(gene,drug):
     
     #%% Construct numerical and categorical column names
     # numerical feature names
-    numerical_FN = common_cols_stabiltyN + foldX_cols + X_strFN + X_evolFN + X_genomicFN 
+#    numerical_FN = common_cols_stabiltyN + foldX_cols + X_strFN + X_evolFN + X_genomicFN 
+    
+    numerical_FN = X_ssFN  + X_evolFN + X_genomicFN 
 
     #categorical feature names
     categorical_FN = ['ss_class'
@@ -308,6 +368,31 @@ def setvars(gene,drug):
                 , 'drtype_mode_labels' # beware then you can use it to predict 
                 #, 'active_aa_pos' # TODO?
                  ]
+    ###########################################################################
+    #=======================
+    # Masking columns:
+    # (mCSM-lig, mCSM-NA, mCSM-ppi2) values for lig_dist >10
+    #=======================
+    #%% Masking columns 
+    # my_df_ml['mutationinformation'][my_df['ligand_distance']>10].value_counts()
+    # my_df_ml.groupby('mutationinformation')['ligand_distance'].apply(lambda x: (x>10)).value_counts()
+    
+    # my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), 'ligand_affinity_change'] = 0
+    # (my_df_ml['ligand_affinity_change'] == 0).sum()
+    
+    my_df_ml['mutationinformation'][my_df_ml['ligand_distance']>10].value_counts()
+    my_df_ml.groupby('mutationinformation')['ligand_distance'].apply(lambda x: (x>10)).value_counts()
+    my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), cols_to_mask].value_counts()
+    
+    # mask the column ligand distance > 10
+    my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), cols_to_mask] = 0
+    (my_df_ml['ligand_affinity_change'] == 0).sum()
+    
+    mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask]  
+    
+    # write file for check
+    mask_check.sort_values(by = ['ligand_distance'], ascending = True, inplace = True)
+    mask_check.to_csv(outdir + 'ml/' + gene.lower() + '_mask_check.csv')
 
     #%% extracting dfs based on numerical, categorical column names
     #----------------------------------
@@ -335,12 +420,12 @@ def setvars(gene,drug):
     
     all_df_wtgt = training_df[numerical_FN + categorical_FN + ['dst_mode']]
     all_df_wtgt.shape
-    #%%================================================================
+    #%%########################################################################
-    #%% Apply ML
+    #============
-    
+    # ML data
-    #%% Data
+    #============
     #------
-    # X
+    # X: Training and Blind test (BTS)
     #------
     X     = all_df_wtgt[numerical_FN + categorical_FN] # training data ALL
     X_bts = blind_test_df[numerical_FN + categorical_FN] # blind test data ALL
@@ -353,16 +438,17 @@ def setvars(gene,drug):
     y = all_df_wtgt['dst_mode'] # training data y
     y_bts = blind_test_df['dst_mode'] # blind data test y
 
-    #Blind test data {same format}
+    #X_bts_wt = blind_test_df[numerical_FN + ['dst_mode']] 
-    #X_bts = blind_test_df[numerical_FN]
-    #X_bts = blind_test_df[numerical_FN + categorical_FN]
-    #y_bts = blind_test_df['dst_mode']
-    
-    X_bts_wt = blind_test_df[numerical_FN + ['dst_mode']] 
     
     # Quick check
-    (X['ligand_affinity_change']==0).sum() == (X['ligand_distance']>10).sum()
+    #(X['ligand_affinity_change']==0).sum() == (X['ligand_distance']>10).sum()
-    ##############################################################################
+    for i in range(len(cols_to_mask)):
+        ind = i+1
+        print('\nindex:', i, '\nind:', ind)
+        print('\nMask count check:'
+              , (my_df_ml[cols_to_mask[i]]==0).sum() == (my_df_ml['ligand_distance']>10).sum()
+              )
+    
     print('Original Data\n', Counter(y)
           , 'Data dim:', X.shape)
     

UQ_MultModelsCl.py

@@ -74,9 +74,9 @@ import json
 rs = {'random_state': 42}
 njobs = {'n_jobs': 10}
 
-scoring_fn =  ({'accuracy'      : make_scorer(accuracy_score)
+scoring_fn =  ({ 'mcc'        : make_scorer(matthews_corrcoef)
+                , 'accuracy'      : make_scorer(accuracy_score)
                 , 'fscore'     : make_scorer(f1_score)
-                 , 'mcc'        : make_scorer(matthews_corrcoef)
                 , 'precision'  : make_scorer(precision_score)
                 , 'recall'     : make_scorer(recall_score)
                 , 'roc_auc'    : make_scorer(roc_auc_score)

UQ_yc_RunAllClfs_CALL.py

@@ -0,0 +1,101 @@
+
+from UQ_yc_RunAllClfs import run_all_ML
+
+#%% CALL function
+#run_all_ML(input_pd=X, target_label=y, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
+# Baseline_data
+
+YC_resD2 = run_all_ML(input_pd=X, target_label=y, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
+CVResultsDF_baseline = YC_resD2['CrossValResultsDF']
+CVResultsDF_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+BTSResultsDF_baseline = YC_resD2['BlindTestResultsDF']
+BTSResultsDF_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+
+# from sklearn.utils import all_estimators
+# for name, algorithm in all_estimators(type_filter="classifier"):
+#     clf = algorithm()
+#     print('Name:', name, '\nAlgo:', clf)
+
+# Random Oversampling
+YC_resD_ros = run_all_ML(input_pd=X_ros, target_label=y_ros, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
+CVResultsDF_ros = YC_resD_ros['CrossValResultsDF']
+CVResultsDF_ros.sort_values(by=['matthew'], ascending=False, inplace=True)
+BTSResultsDF_ros = YC_resD_ros['BlindTestResultsDF']
+BTSResultsDF_ros.sort_values(by=['matthew'], ascending=False, inplace=True)
+
+# Random Undersampling
+YC_resD_rus = run_all_ML(input_pd=X_rus, target_label=y_rus, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
+CVResultsDF_rus = YC_resD_rus['CrossValResultsDF']
+CVResultsDF_rus.sort_values(by=['matthew'], ascending=False, inplace=True)
+BTSResultsDF_rus = YC_resD_rus['BlindTestResultsDF']
+BTSResultsDF_rus.sort_values(by=['matthew'], ascending=False, inplace=True)
+
+# Random Oversampling+Undersampling
+YC_resD_rouC = run_all_ML(input_pd=X_rouC, target_label=y_rouC, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
+CVResultsDF_rouC = YC_resD_rouC['CrossValResultsDF']
+CVResultsDF_rouC.sort_values(by=['matthew'], ascending=False, inplace=True)
+BTSResultsDF_rouC = YC_resD_rouC['BlindTestResultsDF']
+BTSResultsDF_rouC.sort_values(by=['matthew'], ascending=False, inplace=True)
+
+# SMOTE NC
+YC_resD_smnc = run_all_ML(input_pd=X_smnc, target_label=y_smnc, blind_test_input_df=X_bts, blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
+CVResultsDF_smnc = YC_resD_smnc['CrossValResultsDF']
+CVResultsDF_smnc.sort_values(by=['matthew'], ascending=False, inplace=True)
+BTSResultsDF_smnc = YC_resD_smnc['BlindTestResultsDF']
+BTSResultsDF_smnc.sort_values(by=['matthew'], ascending=False, inplace=True)
+##############################################################################
+#============================================
+# BASELINE models with dissected featues
+#============================================
+# Genomics
+yC_gf = run_all_ML(input_pd=X[X_genomicFN], target_label=y, blind_test_input_df=X_bts[X_genomicFN], blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
+yc_gfCT_baseline= yC_gf['CrossValResultsDF']
+yc_gfCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+yc_gfBT_baseline = yC_gf['BlindTestResultsDF']
+yc_gfBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+
+# Evolutionary
+yC_ev = run_all_ML(input_pd=X[X_evolFN], target_label=y, blind_test_input_df=X_bts[X_evolFN], blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
+yc_evCT_baseline= yC_ev['CrossValResultsDF']
+yc_evCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+yc_evBT_baseline = yC_ev['BlindTestResultsDF']
+yc_evBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+
+# strucF:All
+yC_sfall = run_all_ML(input_pd=X[X_strFN], target_label=y, blind_test_input_df=X_bts[X_strFN], blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
+yc_sfallCT_baseline= yC_sfall['CrossValResultsDF']
+yc_sfallCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+yc_sfallBT_baseline = yC_sfall['BlindTestResultsDF']
+yc_sfallBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+
+# strucF:Common ONLY
+c = [x for x in X_ssFN if x not in X_foldX_cols]
+yC_sfco= run_all_ML(input_pd=X[X_stabilityN], target_label=y
+                   , blind_test_input_df=X_bts[x_stabilityN]
+                   , blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
+yc_sfcoCT_baseline= yC_sfco['CrossValResultsDF']
+yc_sfcoCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+yc_sfcoBT_baseline = yC_sfco['BlindTestResultsDF']
+yc_sfcoBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+
+# strucF:common_stability + foldX_cols i.e interaction
+yC_fxss= run_all_ML(input_pd=X[common_cols_stabiltyN+foldX_cols], target_label=y
+                   , blind_test_input_df=X_bts[common_cols_stabiltyN+foldX_cols]
+                   , blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
+yc_fxssCT_baseline= yC_fxss['CrossValResultsDF']
+yc_fxssCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+yc_fxssBT_baseline = yC_fxss['BlindTestResultsDF']
+yc_fxssBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+
+# categorical
+yC_cat= run_all_ML(input_pd=X[categorical_FN], target_label=y
+                   , blind_test_input_df=X_bts[categorical_FN]
+                   , blind_test_target=y_bts, preprocess = True, var_type = 'mixed')
+yc_catCT_baseline= yC_cat['CrossValResultsDF']
+yc_catCT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+yc_catBT_baseline = yC_cat['BlindTestResultsDF']
+yc_catBT_baseline.sort_values(by=['matthew'], ascending=False, inplace=True)
+
+#=================================================
+# Dissected features with Over and Undersampling
+#=================================================

alr_config.py

@@ -0,0 +1,176 @@
+#!/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_u = 8
+
+homedir = os.path.expanduser("~")
+os.chdir( homedir + '/git/ML_AI_training/')
+
+from UQ_ML_data import *
+setvars(gene,drug)
+from UQ_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 UQ_MultModelsCl import MultModelsCl
+
+#%%###########################################################################
+
+print('\n#####################################################################\n')
+
+print('TESTING cmd:'
+      , '\nGene name:', gene
+      , '\nDrug name:', drug
+      , '\nTotal input features:', X.shape
+      , '\n', Counter(y))
+
+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('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_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
+    print('\nPass: No. of features match')
+else:
+    print('\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')

embb_config.py

@@ -0,0 +1,176 @@
+#!/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_u = 8
+
+homedir = os.path.expanduser("~")
+os.chdir( homedir + '/git/ML_AI_training/')
+
+from UQ_ML_data import *
+setvars(gene,drug)
+from UQ_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 UQ_MultModelsCl import MultModelsCl
+
+#%%###########################################################################
+
+print('\n#####################################################################\n')
+
+print('TESTING cmd:'
+      , '\nGene name:', gene
+      , '\nDrug name:', drug
+      , '\nTotal input features:', X.shape
+      , '\n', Counter(y))
+
+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('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_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
+    print('\nPass: No. of features match')
+else:
+    print('\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')

gid_config.py

@@ -0,0 +1,176 @@
+#!/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_u = 8
+
+homedir = os.path.expanduser("~")
+os.chdir( homedir + '/git/ML_AI_training/')
+
+from UQ_ML_data import *
+setvars(gene,drug)
+from UQ_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 UQ_MultModelsCl import MultModelsCl
+
+#%%###########################################################################
+
+print('\n#####################################################################\n')
+
+print('TESTING cmd:'
+      , '\nGene name:', gene
+      , '\nDrug name:', drug
+      , '\nTotal input features:', X.shape
+      , '\n', Counter(y))
+
+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('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_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
+    print('\nPass: No. of features match')
+else:
+    print('\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')

imports.py

@@ -99,8 +99,8 @@ from MultClassPipe2 import MultClassPipeline2
 from loopity_loop import MultClassPipeSKFLoop
 from MultClassPipe3 import MultClassPipeSKFCV
 
-gene = 'pncA'
+#gene = 'pncA'
-drug = 'pyrazinamide'
+#drug = 'pyrazinamide'
 
 #==============
 # directories
@@ -119,10 +119,10 @@ my_df = pd.read_csv(infile_ml1)
 my_df.dtypes
 my_df_cols = my_df.columns
 
-geneL_basic     = ['pnca']
+geneL_basic     = ['pncA']
 geneL_na        = ['gid']
-geneL_na_ppi2   = ['rpob']
+geneL_na_ppi2   = ['rpoB']
-geneL_ppi2      = ['alr', 'embb', 'katg']
+geneL_ppi2      = ['alr', 'embB', 'katG']
 #%% get cols
 mycols = my_df.columns
 

katg_config.py

@@ -0,0 +1,174 @@
+#!/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_u = 8
+
+homedir = os.path.expanduser("~")
+os.chdir( homedir + '/git/ML_AI_training/')
+
+from UQ_ML_data import *
+setvars(gene,drug)
+from UQ_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 UQ_MultModelsCl import MultModelsCl
+
+#%%###########################################################################
+
+print('\n#####################################################################\n')
+
+print('TESTING cmd:'
+      , '\nGene name:', gene
+      , '\nDrug name:', drug
+      , '\nTotal input features:', X.shape
+      , '\n', Counter(y))
+
+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('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_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
+    print('\nPass: No. of features match')
+else:
+    print('\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')

pnca_config.py

@@ -10,7 +10,7 @@ import os
 
 gene  = 'pncA'
 drug  = 'pyrazinamide'
-#total_mtblineage_u = 8
+#total_mtblineage_uc = 8
 
 homedir = os.path.expanduser("~")
 os.chdir( homedir + '/git/ML_AI_training/')
@@ -20,7 +20,7 @@ setvars(gene,drug)
 from UQ_ML_data import *
 
 # from YC run_all_ML: run locally
-from UQ_yc_RunAllClfs import run_all_ML
+#from UQ_yc_RunAllClfs import run_all_ML
 
 # TT run all ML clfs: baseline mode
 from UQ_MultModelsCl import MultModelsCl
@@ -28,6 +28,7 @@ from UQ_MultModelsCl import MultModelsCl
 #%%###########################################################################
 
 print('\n#####################################################################\n')
+
 print('TESTING cmd:'
       , '\nGene name:', gene
       , '\nDrug name:', drug
@@ -35,11 +36,11 @@ print('TESTING cmd:'
       , '\n', Counter(y))
 
 print('Strucutral features (n):'
-      , len(common_cols_stabiltyN) + len(foldX_cols) + len(X_strFN)
+      , len(X_ssFN)
       , '\nThese are:'
-      , '\nCommon stablity features:', common_cols_stabiltyN
+      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', foldX_cols
+      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_strFN
+      , '\nOther struc columns:', X_str
       , '\n================================================================\n')
 
 print('Evolutionary features (n):'
@@ -60,7 +61,115 @@ print('Categorical features (n):'
       , '\nThese are:\n'
       , categorical_FN
       , '\n================================================================\n')
+
+if ( len(X.columns) ==  len(X_ssFN) +len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
+    print('\nPass: No. of features match')
+else:
+    print('\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')

rfecv_vis.py

@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Sun May 29 12:21:34 2022
+
+@author: tanu
+"""
+from sklearn.svm import SVC
+from sklearn.datasets import make_classification
+
+from yellowbrick.model_selection import RFECV
+
+# Instantiate RFECV visualizer with a linear SVM classifier
+visualizer = RFECV(SVC(kernel='linear', C=1))
+
+visualizer.fit(X[numerical_FN], y)        # Fit the data to the visualizer
+visualizer.show()       
+
+
+numerical_ix = X.select_dtypes(include=['int64', 'float64']).columns
+numerical_ix
+categorical_ix = X.select_dtypes(include=['object', 'bool']).columns
+categorical_ix    
+
+# Determine preprocessing steps ~ var_type
+var_type = 'mixed'
+var_type = 'numerical'
+
+if var_type == 'numerical':
+    t = [('num', MinMaxScaler(), numerical_ix)]
+
+if var_type == 'categorical':
+    t = [('cat', OneHotEncoder(), categorical_ix)]
+
+if var_type == 'mixed':
+    t = [('cat', OneHotEncoder(), categorical_ix)
+         , ('num', MinMaxScaler(), numerical_ix)]
+    
+    t = [('num', MinMaxScaler(), numerical_ix)
+         , ('cat', OneHotEncoder(), categorical_ix)]
+    
+col_transform = ColumnTransformer(transformers = t
+                                   , remainder='passthrough')
+#--------------ALEX help
+# col_transform
+# col_transform.fit(X)
+# test = col_transform.transform(X)
+# print(col_transform.get_feature_names_out())
+
+# foo = col_transform.fit_transform(X)
+Xm = col_transform.fit_transform(X)
+# (foo == test).all()
+#-----------------------
+
+visualizer.fit(Xm, y)        # Fit the data to the visualizer
+visualizer.show()
+
+
+visualizer.fit(X[numerical_FN], y)        # Fit the data to the visualizer
+visualizer.show()       

rpob_config.py

@@ -0,0 +1,176 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Sat May 28 05:25:30 2022
+
+@author: tanu
+"""
+
+import os
+
+gene  = 'rpoB'
+drug  = 'rifampicin'
+#total_mtblineage_u = 8
+
+homedir = os.path.expanduser("~")
+os.chdir( homedir + '/git/ML_AI_training/')
+
+from UQ_ML_data import *
+setvars(gene,drug)
+from UQ_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 UQ_MultModelsCl import MultModelsCl
+
+#%%###########################################################################
+
+print('\n#####################################################################\n')
+
+print('TESTING cmd:'
+      , '\nGene name:', gene
+      , '\nDrug name:', drug
+      , '\nTotal input features:', X.shape
+      , '\n', Counter(y))
+
+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('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_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
+    print('\nPass: No. of features match')
+else:
+    print('\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')

temp.py

@@ -0,0 +1,92 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Sun May 29 09:22:51 2022
+
+@author: tanu
+"""
+
+geneL_basic     = ['pncA']
+geneL_na        = ['gid']
+geneL_na_ppi2   = ['rpoB']
+geneL_ppi2      = ['alr', 'embB', 'katG']
+#%% get cols
+mycols = my_df.columns
+
+# # change from numberic to 
+# num_type = ['int64', 'float64']
+# cat_type = ['object', 'bool']
+
+# if my_df['active_aa_pos'].dtype in num_type:
+#     my_df['active_aa_pos'] = my_df['active_aa_pos'].astype(object)
+#     my_df['active_aa_pos'].dtype
+
+# FIXME: if this is not structural, remove from source..
+# Drop NA where numerical cols have them
+if gene.lower() in geneL_na_ppi2:
+    #D1148 get rid of
+    na_index = my_df['mutationinformation'].index[my_df['mcsm_na_affinity'].apply(np.isnan)]
+    my_df = my_df.drop(index=na_index)
+
+# FIXME: either impute or remove!
+# for embb (L114M, F115L, V123L, V125I, V131M) delete for now
+if gene.lower() in ['embb']:
+    na_index = my_df['mutationinformation'].index[my_df['ligand_distance'].apply(np.isnan)]
+    #my_df = my_df.drop(index=na_index))# RERUN embb with the 5 values now present
+#%%===========================================================================
+
+#%%
+# GET X
+common_cols_stabiltyN = ['ligand_distance'
+           , 'ligand_affinity_change'
+           , 'duet_stability_change'
+           , 'ddg_foldx'
+           , 'deepddg'
+           , 'ddg_dynamut2'
+           , 'contacts']
+
+# Build stability columns ~ gene
+if gene.lower() in geneL_basic:
+    x_stabilityN = common_cols_stabiltyN
+    cols_to_mask = ['ligand_affinity_change']
+    
+if gene.lower() in geneL_ppi2:
+#    x_stabilityN = common_cols_stabiltyN + ['mcsm_ppi2_affinity' , 'interface_dist'] 
+    geneL_ppi2_st_cols = ['mcsm_ppi2_affinity', 'interface_dist'] 
+    x_stabilityN = common_cols_stabiltyN + geneL_ppi2_st_cols
+    cols_to_mask = ['ligand_affinity_change', 'mcsm_ppi2_affinity']
+
+if gene.lower() in geneL_na:
+#    x_stabilityN = common_cols_stabiltyN + ['mcsm_na_affinity'] 
+    geneL_na_st_cols =  ['mcsm_na_affinity'] 
+    x_stabilityN = common_cols_stabiltyN + geneL_na_st_cols
+    cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity']
+
+if gene.lower() in geneL_na_ppi2:
+#    x_stabilityN = common_cols_stabiltyN + ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist'] 
+    geneL_na_ppi2_st_cols = ['mcsm_na_affinity'] + ['mcsm_ppi2_affinity', 'interface_dist'] 
+    x_stabilityN = common_cols_stabiltyN + geneL_na_ppi2_st_cols
+    cols_to_mask = ['ligand_affinity_change', 'mcsm_na_affinity', 'mcsm_ppi2_affinity']
+
+
+#%% Masking columns (mCSM-lig, mCSM-NA, mCSM-ppi2) values for lig_dist >10
+my_df_ml['mutationinformation'][my_df_ml['ligand_distance']>10].value_counts()
+my_df_ml.groupby('mutationinformation')['ligand_distance'].apply(lambda x: (x>10)).value_counts()
+my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), cols_to_mask].value_counts()
+
+# mask the column ligand distance > 10
+my_df_ml.loc[(my_df_ml['ligand_distance'] > 10), cols_to_mask] = 0
+(my_df_ml['ligand_affinity_change'] == 0).sum()
+
+mask_check = my_df_ml[['mutationinformation', 'ligand_distance'] + cols_to_mask]
+
+
+for i in range(len(cols_to_mask)):
+    ind = i+1
+    print('\nindex:', i, '\nind:', ind)
+    print('\nMask count check:'
+          , (my_df_ml[cols_to_mask[i]]==0).sum() == (my_df_ml['ligand_distance']>10).sum()
+          )
+
+(my_df_ml[cols_to_mask[0]]==0).sum() == (my_df_ml['ligand_distance']>10).sum()
+(my_df_ml[cols_to_mask[1]]==0).sum() == (my_df_ml['ligand_distance']>10).sum()