made var names more meaniningful

my_data6.py

@@ -28,8 +28,8 @@ os.chdir(homedir + "/git/ML_AI_training/")
 # my function
 from MultClassPipe import MultClassPipeline 
 
-#gene = 'pncA'
-#drug = 'pyrazinamide'
+gene = 'pncA'
+drug = 'pyrazinamide'
 
 #==============
 # directories
@@ -48,10 +48,10 @@ my_df = pd.read_csv(infile_ml1)
 my_df.dtypes
 my_df_cols = my_df.columns
 
-geneL_basic = ['pnca']
-geneL_na   = ['gid']
+geneL_basic     = ['pnca']
+geneL_na        = ['gid']
 geneL_na_ppi2   = ['rpob']
-geneL_ppi2 = ['alr', 'embb', 'katg']
+geneL_ppi2      = ['alr', 'embb', 'katg']
 #%% get cols
 mycols = my_df.columns
 
@@ -82,6 +82,17 @@ my_df[drtype_labels] = my_df['drtype'].map({'Sensitive' : 0
 # target3 = my_df['drtype']
 target3 = my_df[drtype_labels]
 
+# target4
+drtype_labels2 = 'drtype_labels2'
+my_df[drtype_labels2] = my_df['drtype'].map({'Sensitive'     : 0
+                                                 , 'Other'   : 0
+                                                 , 'Pre-MDR' : 1
+                                                 , 'MDR'     : 1
+                                                 , 'Pre-XDR' : 2
+                                                 , 'XDR'     : 2})
+
+target4 = my_df[drtype_labels2]
+
 # sanity checks
 target1.value_counts()
 my_df['mutation_info_labels'].value_counts()
@@ -91,6 +102,8 @@ my_df[drug_labels].value_counts()
 
 target3.value_counts()
 my_df['drtype'].value_counts()
+target4.value_counts()
+my_df['drtype'].value_counts()
 
 #%%
 # GET X
@@ -147,9 +160,30 @@ X_vars6  = my_df[x_stability_cols + X_evolF]
 X_vars8  = my_df[X_strF + X_evolF]
 #X_vars9  = my_df[X_strF + X_genomicF]
 #X_vars10 = my_df[X_evolF + X_genomicF]
-X_vars11 = my_df[x_stability_cols + X_strF + X_evolF ]
+X_vars11 = my_df[x_stability_cols + X_strF + X_evolF]
 #X_vars12 = my_df[x_stability_cols + X_strF + X_evolF + X_genomicF]
 
+numerical_features_names = x_stability_cols + X_strF + X_evolF
+
+# separate ones for foldx?
+categorical_features_names = ['ss_class'
+                           , 'wt_prop_water'
+                          # , 'lineage_labels' # misleading if using merged_df3
+                           , 'mut_prop_water'
+                           , 'wt_prop_polarity'
+                           , 'mut_prop_polarity'
+                           , 'wt_calcprop'
+                           , 'mut_calcprop'
+                           , 'active_aa_pos']
+
+numerical_features_df = my_df[numerical_features_names]
+numerical_features_df.shape
+
+categorical_features_df = my_df[categorical_features_names]
+categorical_features_df.shape
+
+all_features_df = my_df[numerical_features_names + categorical_features_names]
+all_features_df.shape
 #%%
 X_vars1.shape[1]
 X_vars5.shape[1]