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]

my_data7.py

@@ -29,6 +29,9 @@ from sklearn.metrics import classification_report
 from sklearn.feature_selection import RFE
 from sklearn.feature_selection import RFECV
 
+#############################
+# trying feature selection
+#############################
 #%%
 model= Pipeline(steps = [
     ('pre', MinMaxScaler()),
@@ -103,6 +106,11 @@ https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.Sequ
 https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.RFECV.html
 https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.f_regression.html
 https://www.scikit-yb.org/en/latest/api/model_selection/rfecv.html
+
+#GridSearchCV
+#ParameterGrid
+#RandomizedSearchCV
+#https://medium.com/analytics-vidhya/hyper-parameter-tuning-gridsearchcv-vs-randomizedsearchcv-499862e3ca5
 #%% RFE: Feature selection in classification
 # others in example
 # https://towardsdatascience.com/feature-selection-techniques-for-classification-and-python-tips-for-their-application-10c0ddd7918b
@@ -152,8 +160,8 @@ X_train, X_test, y_train, y_test = train_test_split(X_vars11,
                                                     test_size = 0.33, 
                                                     random_state = 42)
 
-model_logistic = LogisticRegression()
-sel_rfe_logistic = RFECV(estimator = model_logistic
+model_logistic2 = LogisticRegression()
+sel_rfe_logistic = RFECV(estimator = model_logistic2
                        , cv = 10
                        , step = 1)
 
@@ -162,3 +170,38 @@ print(sel_rfe_logistic.get_support())
 X_train.columns
 
 print(sel_rfe_logistic.ranking_)
+#%%
+# TODO: imputation
+# Find out the best way to impute values!
+#from sklearn.impute import SimpleImputer
+# https://towardsdatascience.com/whats-the-best-way-to-handle-nan-values-62d50f738fc
+#KNN and MICE
+my_df2 = pd.read_csv(infile_ml1)
+
+genomicF = ['af'
+        , 'beta_logistic'
+        , 'or_logistic'
+        , 'pval_logistic'
+        , 'se_logistic'
+        , 'zval_logistic'
+        , 'ci_low_logistic'
+        , 'ci_hi_logistic'
+        , 'or_mychisq'
+        , 'log10_or_mychisq'
+        , 'or_fisher'
+        , 'pval_fisher'
+        , 'neglog_pval_fisher'
+        , 'ci_low_fisher'
+        , 'ci_hi_fisher'
+        , 'est_chisq'
+        , 'pval_chisq']
+
+# X_genomicF =  ['af'
+#             , 'or_mychisq'
+#             , 'or_logistic'
+#             , 'or_fisher'
+#             , 'pval_fisher']
+
+my_df2[genomicF].isna().sum()
+
+my_df2[genomicF] = my_df2[genomicF].fillna(value='unknown')