working on dissected model, testing diff feature groups

scripts/ml/pnca_config_dissected.py

@@ -47,60 +47,78 @@ outdir_ml = outdir + 'ml/uq_v1/dissected'
 print('\nOutput directory:', outdir_ml)
 
 #%%###########################################################################
-print('\nSanity checks:'
-      , '\nTotal input features:', len(X.columns)
-      , '\n'
-      , '\nTraining data size:', X.shape
-      , '\nTest data size:', X_bts.shape
-      , '\n'
-      , '\nTarget feature numbers (training data):', Counter(y)
-      , '\nTarget features ratio (training data:', yc1_ratio
-      , '\n'
-      , '\nTarget feature numbers (test data):', Counter(y_bts)
-      , '\nTarget features ratio (test data):', yc2_ratio
-      
-      , '\n\n#####################################################################\n')
-
 print('\n================================================================\n')
 
-print('Strucutral features (n):'
-      , len(X_ssFN)
-      , '\nThese are:'
-      , '\nCommon stablity features:', X_stabilityN
-      , '\nFoldX columns:', X_foldX_cols
-      , '\nOther struc columns:', X_str
-      , '\n================================================================\n')
+          , '\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)
 
-# print('AAindex features (n):'
-#       , len(X_aaindexFN)
-#       , '\nThese are:\n'
-#       , X_aaindexFN
-#       , '\n================================================================\n')
+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('Evolutionary features (n):'
-      , len(X_evolFN)
-      , '\nThese are:\n'
-      , X_evolFN
-      , '\n================================================================\n')
+print('\n================================================================'
+      
+      , '\nTotal Evolutionary features (n):' , len(X_evolFN)
+      , '\n--------------Evol. feature colnames:', X_evolFN
+      
+      , '\n================================================================'
+      
+      , '\n\nTotal structural features (n):', len(X_structural_FN)
+      
+      , '\n--------Stability ncols:'                      , len(X_stability_FN)
+      , '\n--------------Common stability colnames:'      , X_common_stability_Fnum
+      , '\n--------------Foldx colnames:'                 , X_foldX_Fnum
+     
+      , '\n--------Affinity ncols:'                       , len(X_affinityFN)
+      , '\n--------------Common affinity colnames:'       , common_affinity_Fnum
+      , '\n--------------Gene specific affinity colnames:', gene_affinity_colnames
 
-print('Genomic features (n):'
-      , len(X_genomicFN)
-      , '\nThese are:\n'
-      , X_genomic_mafor, '\n'
-      , X_genomic_linegae
-      , '\n================================================================\n')
+      , '\n--------Residue prop ncols:'                   , len(X_resprop_FN)
+      , '\n--------------Residue Prop cols:'              , X_str_Fnum
+      , '\n--------------AA change Prop cols:'            , X_aap_Fcat
+      , '\n--------------AA index cols:'                  , X_aaindex_Fnum
+      
+      , '\n================================================================'
+      
+      , '\n\nTotal Genomic features (n):'   , len(X_genomicFN)
+      , '\n--------MAF+OR cols:'                         , len(X_gn_mafor_Fnum)
+      , '\n--------------MAF+OR colnames:'               , X_gn_mafor_Fnum
 
-print('Categorical features (n):'
-      , len(categorical_FN)
-      , '\nThese are:\n'
-      , categorical_FN
-      , '\n================================================================\n')
+      , '\n--------Lineage cols:'                        , len(X_gn_linegae_Fnum)
+      , '\n--------------Lineage cols:'                  , X_gn_linegae_Fnum
 
-#if ( len(X.columns) ==  len(X_ssFN) + len(X_aaindexFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
-if ( len(X.columns) ==  len(X_ssFN) + len(X_evolFN) + len(X_genomicFN) + len(categorical_FN) ):
+      , '\n--------Other cols:'                          , len(X_gn_Fcat)
+      , '\n--------------Other cols:'                    , X_gn_Fcat
+      
+      , '\n================================================================')
+
+# Sanity check
+if ( len(X.columns) ==  len(X_evolFN) + len(X_structural_FN) + len(X_genomicFN)):
     print('\nPass: No. of features match')
 else:
-    sys.exit('\nFail: Count of feature mismatch')
+    print('\nFail: Count of feature mismatch'
+          , '\nExpected:', len(X_evolFN) + len(X_structural_FN) + len(X_genomicFN)
+          , '\nGot:', len(X.columns))
+    sys.exit()
 
 print('\n#####################################################################\n')
 
@@ -108,7 +126,7 @@ print('\n#####################################################################\n
 # #==================
 # # Baseline models 
 # #==================
-# mm_skf_scoresD = MultModelsCl(input_df = X
+# mm_skf_scoresD = MultModelsCl_dissected(input_df = X
 #                                         , target = y
 #                                         , var_type = 'mixed'
 #                                         , skf_cv = skf_cv