adding formatting to get all output from ML for feature grpups starting with genomics

scripts/ml/MultModelsCl_dissected.py

@@ -305,7 +305,7 @@ def MultModelsCl_dissected(input_df, target, skf_cv
         mm_skf_scoresD[model_name]['bts_recall']    = round(recall_score(blind_test_target, bts_predict),2)
         mm_skf_scoresD[model_name]['bts_accuracy']  = round(accuracy_score(blind_test_target, bts_predict),2)
         mm_skf_scoresD[model_name]['bts_roc_auc']   = round(roc_auc_score(blind_test_target, bts_predict),2)
-        mm_skf_scoresD[model_name]['bts_jaccard']   = round(jaccard_score(blind_test_target, bts_predict),2)
+        mm_skf_scoresD[model_name]['bts_jcc']   = round(jaccard_score(blind_test_target, bts_predict),2)
         #mm_skf_scoresD[model_name]['diff_mcc']      = train_test_diff_MCC
 
     return(mm_skf_scoresD)

scripts/ml/Mult_dissected_CALL.py

@@ -5,21 +5,47 @@ Created on Mon Jun 20 13:05:23 2022
 
 @author: tanu
 """
+import re
+#all_featuresN   = X_evolFN + X_structural_FN + X_genomicFN
+#    X_structural_FN =  X_stability_FN + X_affinityFN + X_resprop_FN
+#    X_resprop_FN    = X_aaindex_Fnum + X_str_Fnum + X_aap_Fcat
+    
+   
+score_type_ordermapD = { 'mcc'           : 1
+                   , 'fscore'       : 2
+                   , 'jcc'          : 3
+                   , 'precision'    : 4
+                   , 'recall'       : 5      
+                   , 'accuracy'     : 6  
+                   , 'roc_auc'      : 7
+                   , 'TN'           : 8
+                   , 'FP'           : 9
+                   , 'FN'           : 10
+                   , 'TP'           : 11  
+                   , 'trainingY_neg': 12  
+                   , 'trainingY_pos': 13    
+                   , 'blindY_neg'   : 14
+                   , 'blindY_pos'   : 15
+                   , 'fit_time'     : 16
+                   , 'score_time'   : 17
+                   }
+     
+     
 #==================
 # Baseline models 
 #==================
-cm_di2 = MultModelsCl_dissected(input_df = X
+# cm_di2 = MultModelsCl_dissected(input_df = X
-                    , target = y
+#                     , target = y
-                    , var_type = 'mixed'
+#                     , var_type = 'mixed'
-                    , skf_cv = skf_cv
+#                     , skf_cv = skf_cv
-                    , blind_test_input_df = X_bts
+#                     , blind_test_input_df = X_bts
-                    , blind_test_target = y_bts
+#                     , blind_test_target = y_bts
-                    , add_cm = True 
+#                     , add_cm = True 
-                    , add_yn = True)
+#                     , add_yn = True)
 
-baseline_all2 = pd.DataFrame(cm_di2)
+# baseline_all2 = pd.DataFrame(cm_di2)
-baseline_all2 = baseline_all2.T
+# baseline_all2T = baseline_all2.T
-baseline_CTBT2 = baseline_all2.filter(regex = 'test_.*|bts_.*|TN|FP|FN|TP|.*_neg|.*_pos' , axis = 1)
+# baseline_CTBT2 = baseline_all2T.filter(regex = 'test_.*|bts_.*|TN|FP|FN|TP|.*_neg|.*_pos' , axis = 1)
 
 #================
 # Stability cols
@@ -52,35 +78,68 @@ scores_mm_gn = MultModelsCl_dissected(input_df = X[X_genomicFN]
                     , add_yn = True)
 
 baseline_all_gn = pd.DataFrame(scores_mm_gn)
-baseline_CTBT_gn = baseline_all_gn.filter(regex = '.*_time|test_.*|bts_.*|TN|FP|FN|TP|.*_neg|.*_pos' , axis = 0)
-baseline_CTBT_gn['feature_group'] = feature_gp_name
 
+baseline_GN = baseline_all_gn.filter(regex = 'bts_.*|test_.*|.*_time|TN|FP|FN|TP|.*_neg|.*_pos', axis = 0)
+baseline_GN = baseline_GN.reset_index()
+baseline_GN.rename(columns = {'index': 'original_names'}, inplace = True)
 
+# Indicate whether BT or CT
+bt_pattern = re.compile(r'bts_.*')
+baseline_GN['data_source'] = baseline_GN.apply(lambda row: 'BT' if bt_pattern.search(row.original_names) else 'CV' , axis = 1)
 
-baseline_CT = baseline_CTBT_gn.filter(regex = '.*_time|test_.*|TN|FP|FN|TP|.*_neg|.*_pos', axis = 0)
+baseline_GN['score_type'] = baseline_GN['original_names'].str.replace('bts_|test_', '', regex = True)
 
-baseline_CT = baseline_CT.reset_index()
+score_type_uniqueN = set(baseline_GN['score_type'])
-baseline_CT.rename(columns = {'index': 'original_index'}, inplace = True)
+cL1 = list(score_type_ordermapD.keys())
-baseline_CT['score_type'] = baseline_CT['original_index'] 
+cL2 = list(score_type_uniqueN)
-baseline_CT['score_type'] = baseline_CT['score_type'].str.replace('test_*', '', regex = True)
-baseline_CT['data_source'] = 'CT_score'
 
+if set(cL1).issubset(cL2):
+    print('\nPASS: sorting df by score that is mapped onto the order I want')
+    baseline_GN['score_order'] = baseline_GN['score_type'].map(score_type_ordermapD)
+    baseline_GN.sort_values(by = ['data_source', 'score_order'], ascending = [True, True], inplace = True)
+else:
+    sys.exit('\nFAIL: could not sort df as score mapping for ordering failed')
     
-baseline_BT = baseline_CTBT_gn.filter(regex = 'bts_', axis = 0)
+baseline_GN['feature_group'] = feature_gp_name
+    
+#-------------
+# Blind test
+#-------------
+baseline_BT = baseline_all_gn.filter(regex = 'bts_', axis = 0)
 baseline_BT = baseline_BT.reset_index()
-baseline_BT.rename(columns = {'index': 'original_index'}, inplace = True)
+baseline_BT.rename(columns = {'index': 'original_names'}, inplace = True)
-baseline_BT['score_type'] = baseline_BT['original_index'] 
+baseline_BT['score_type'] = baseline_BT['original_names'] 
 baseline_BT['score_type'] = baseline_BT['score_type'].str.replace('bts_*', '', regex = True)
 baseline_BT['data_source'] = 'BT_score'
 
-# rpow bind 
+#--------
-if all(baseline_CT.columns == baseline_BT.columns):
+# CV
-    print('\nPASS:colnames match, proceeding to rowbind')
+#--------
-    comb_df = pd.concat([baseline_BT,baseline_CT], axis = 0, ignore_index = True ) 
+baseline_CT = baseline_all_gn.filter(regex = '.*_time|test_.*|TN|FP|FN|TP|.*_neg|.*_pos', axis = 0)
+baseline_CT = baseline_CT.reset_index()
+baseline_CT.rename(columns = {'index': 'original_names'}, inplace = True)
+baseline_CT['score_type'] = baseline_CT['original_names'] 
+baseline_CT['score_type'] = baseline_CT['score_type'].str.replace('test_*', '', regex = True)
+baseline_CT['data_source'] = 'CT_score'
 
-baseline_CT
+#----------------------
-baseline_CT
+# rpow bind: CT and BT
+#----------------------
+if all(baseline_BT.columns == baseline_CT.columns):
+    print('\nPASS: Colnames match, proceeding to row bind for data:', feature_gp_name
+          , '\nDim of df1 (BT):', baseline_BT.shape
+          , '\nDim of df2 (CT):', baseline_CT.shape)
+    comb_df_gn = pd.concat([baseline_BT, baseline_CT], axis = 0, ignore_index = True) 
+    comb_df_gn['feature_group'] = feature_gp_name
+    print('\nDim of combined df:', comb_df_gn.shape)
+else:
+    print('\nFAIL: colnames mismatch, cannot combine')
     
+# good way but I don't like to  have to rearrange the columns later
+#frames_tocombine = [baseline_BT, baseline_CT]
+#common_cols = list(set.intersection(*(set(df.columns) for df in frames_tocombine)))
+#a = pd.concat([df[common_cols] for df in frames_tocombine], ignore_index=True)
+###############################################################################
 #================
 # Evolution
 #================

scripts/ml/ml_data_dissected.py

@@ -578,9 +578,15 @@ X_gn_Fcat = ['drtype_mode_labels'  # beware then you can't use it to predict [US
 
 X_genomicFN = X_gn_mafor_Fnum + X_gn_linegae_Fnum + X_gn_Fcat
 ###############################################################################
-# Feature groups further collaps:
+#========================
+# FG6 collapsed: Structural : Atability + Affinity + ResidueProp
+#========================
 X_structural_FN =  X_stability_FN + X_affinityFN + X_resprop_FN
 
+###############################################################################
+#========================
+# BUILDING all features
+#========================
 all_featuresN = X_evolFN + X_structural_FN + X_genomicFN
 
 ###############################################################################

scripts/ml/pnca_config_dissected.py

@@ -49,32 +49,11 @@ print('\nOutput directory:', outdir_ml)
 #%%###########################################################################
 print('\n================================================================\n')
 
-          , '\n\nTotal no. of evolutionary features:' , len(X_evolFN)
-          
-          , '\n\nTotal no. of stability features:'    , len(X_stability_FN)
-          , '\n--------Common stabilty cols:'         , len(X_common_stability_Fnum)
-          , '\n--------Foldx cols:'                   , len(X_foldX_Fnum)
-          
-          , '\n\nTotal no. of affinity features:'     , len(X_affinityFN)
-          , '\n--------Common affinity cols:'         , len(common_affinity_Fnum)
-          , '\n--------Gene specific affinity cols:'  , len(gene_affinity_colnames)
-          
-          , '\n\nTotal no. of residue level features:', len(X_resprop_FN)
-          , '\n--------AA index cols:'                , len(X_aaindex_Fnum)
-          , '\n--------Residue Prop cols:'            , len(X_str_Fnum)
-          , '\n--------AA change Prop cols:'          , len(X_aap_Fcat)
-          
-          , '\n\nTotal no. of genomic features:'      , len(X_genomicFN)
-          , '\n--------MAF+OR cols:'                  , len(X_gn_mafor_Fnum)
-          , '\n--------Lineage cols:'                 , len(X_gn_linegae_Fnum)
-          , '\n--------Other cols:'                   , len(X_gn_Fcat)
 
 X_structural_FN =  X_stability_FN + X_affinityFN + X_resprop_FN
  X_aaindex_Fnum + X_str_Fnum + X_aap_Fcat
 all_featuresN = X_evolFN + X_structural_FN + X_genomicFN
      
-###############################################################################
-
 print('\n================================================================'
       
       , '\nTotal Evolutionary features (n):' , len(X_evolFN)