added run_7030.py that runs as cmd for all gene targets and sampling methods and outputs a single csv

scripts/ml/ml_data_fg.py

@@ -61,7 +61,6 @@ def setvars(gene,drug):
     jacc_score_fn = {'jcc': make_scorer(jaccard_score)}
     
     #%% FOR LATER: Combine ED logo data
-    #%% DONE: active aa site annotations **DONE on 15/05/2022 as part of generating merged_dfs
     ###########################################################################
     rs = {'random_state': 42}
     njobs = {'n_jobs': 10}
@@ -419,7 +418,7 @@ def setvars(gene,drug):
     #---------------------------------------
     #!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
     
-    #%% Data for ML
+    #%%########################################################################
     #==========================
     #     Data for ML
     #==========================
@@ -551,8 +550,7 @@ def setvars(gene,drug):
                 , 'polarity_change'
                 , 'water_change'
                 , 'active_site']
-    
-    
+       
     X_resprop_FN = X_aaindex_Fnum + X_str_Fnum + X_aap_Fcat
     ###############################################################################
     #========================
@@ -594,8 +592,7 @@ def setvars(gene,drug):
     ###############################################################################
     #%% Define training and test data
     #======================================================
-    # Training and BLIND test set [UQ]: actual vs imputed
-    # No aa index but active_site included
+    # Training and BLIND test set: actual vs imputed
     # dst with actual values  : training set
     # dst with imputed values : blind test
     #======================================================
@@ -612,9 +609,9 @@ def setvars(gene,drug):
     training_df['dst_mode'].value_counts()
     
     ####################################################################
-    #============
-    # ML data
-    #============
+    #=====================================
+    # ML data: actual vs imputed 
+    #=====================================
     #------
     # X: Training and Blind test (BTS)
     #------
@@ -625,20 +622,8 @@ def setvars(gene,drug):
     # y
     #------
     y     = training_df['dst_mode']
-    y_bts = blind_test_df['dst_mode']
-    
-    # Quick check
-    #(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)
-    
+    y_bts = blind_test_df['dst_mode']  
+   
     yc1 = Counter(y)
     yc1_ratio = yc1[0]/yc1[1]
     
@@ -705,7 +690,18 @@ def setvars(gene,drug):
           , '\ny_test ratio:', yc2_ratio
           , '\n-------------------------------------------------------------'
           )
+    ##########################################################################    
+    # Quick check
+    #(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)
     ###########################################################################
     #%% 
     ###########################################################################
@@ -760,7 +756,7 @@ def setvars(gene,drug):
     k_sm = 5 # 5 is deafult
     sm_nc = SMOTENC(categorical_features=categorical_colind, k_neighbors = k_sm, **rs, **njobs)
     X_smnc, y_smnc = sm_nc.fit_resample(X, y)
-    print('SMOTE_NC OverSampling\n', Counter(y_smnc))
+    print('\nSMOTE_NC OverSampling\n', Counter(y_smnc))
     print(X_smnc.shape)
     globals().update(locals()) # TROLOLOLOLOLOLS
     #print("i did a horrible hack :-)")
@@ -774,7 +770,7 @@ def setvars(gene,drug):
     # sm = SMOTE(sampling_strategy = 'auto', k_neighbors = k_sm, **rs)
     # X_sm, y_sm = sm.fit_resample(X, y)
     # print(X_sm.shape)
-    # print('SMOTE OverSampling\n', Counter(y_sm))
+    # print('\nSMOTE OverSampling\n', Counter(y_sm))
     # y_sm_df = y_sm.to_frame()
     # y_sm_df.value_counts().plot(kind = 'bar')
     
@@ -785,7 +781,7 @@ def setvars(gene,drug):
     # sm_enn = SMOTEENN(enn=EditedNearestNeighbours(sampling_strategy='all', **rs, **njobs ))
     # X_enn, y_enn = sm_enn.fit_resample(X, y)
     # print(X_enn.shape)
-    # print('SMOTE Over+Under Sampling combined\n', Counter(y_enn))
+    # print('\nSMOTE Over+Under Sampling combined\n', Counter(y_enn))
     
     ###############################################################################
     # TODO: Find over and undersampling JUST for categorical data