added OR impute code in UQ_pnca_ML

UQ_pnca_ML.py

@@ -14,6 +14,7 @@ import pprint as pp
 from copy import deepcopy
 from sklearn import linear_model
 from sklearn import datasets
+from collections import Counter
 
 from sklearn.linear_model import LogisticRegression, LinearRegression
 from sklearn.naive_bayes import BernoulliNB
@@ -62,8 +63,8 @@ from sklearn.model_selection import StratifiedKFold
 from sklearn.pipeline import Pipeline
 from sklearn.pipeline import make_pipeline
 
-#from sklearn.feature_selection import RFE
-#from sklearn.feature_selection import RFECV
+from sklearn.feature_selection import RFE
+from sklearn.feature_selection import RFECV
 import itertools
 #import seaborn as sns
 import matplotlib.pyplot as plt
@@ -87,11 +88,12 @@ from imblearn.over_sampling import SMOTENC
 from imblearn.under_sampling import EditedNearestNeighbours
 from imblearn.under_sampling import RepeatedEditedNearestNeighbours
 
-
 from sklearn.model_selection import GridSearchCV
 from sklearn.base import BaseEstimator
 import json
+from sklearn.impute import KNNImputer as KNN
 
+# My functions and globals
 scoring_fn =  ({'accuracy'      : make_scorer(accuracy_score)
                  , 'fscore'     : make_scorer(f1_score)
                  , 'mcc'        : make_scorer(matthews_corrcoef)
@@ -124,8 +126,8 @@ from loopity_loop import MultClassPipeSKFLoop
 #from MultClassPipe3 import MultClassPipeSKFCV
 from UQ_MultClassPipe4 import MultClassPipeSKFCV
 
-gene = 'pncA'
-drug = 'pyrazinamide'
+#gene = 'pncA'
+#drug = 'pyrazinamide'
 
 #gene = 'katG'
 #drug = 'isoniazid'
@@ -167,7 +169,32 @@ cat_type = ['object', 'bool']
 
 # -- CHECK script -- imports.py
 #%%============================================================================
-#%% IMPUTE values for OR
+#%% IMPUTE values for OR [check script for exploration: UQ_or_imputer]
+#or_cols = ['or_mychisq', 'log10_or_mychisq', 'or_fisher']
+sel_cols = ['mutationinformation', 'or_mychisq', 'log10_or_mychisq']
+or_cols = ['or_mychisq', 'log10_or_mychisq']
+
+print("count of NULL values before imputation\n")
+my_df[or_cols].isnull().sum()
+
+my_dfI = pd.DataFrame(index = my_df['mutationinformation'] )
+
+    
+my_dfI = pd.DataFrame(KNN(n_neighbors= 5, weights="uniform").fit_transform(my_df[or_cols])
+                      , index =  my_df['mutationinformation']
+                      , columns = or_cols )
+my_dfI.columns = ['or_rawI', 'logorI']
+my_dfI.columns
+my_dfI = my_dfI.reset_index(drop = False) # prevents old index from being added as a column
+my_dfI.head()
+
+# merge with original based on index
+my_df['index_bm'] = my_df.index
+mydf_imputed = pd.merge(my_df
+                    , my_dfI
+                    , on = 'mutationinformation')
+mydf_imputed = mydf_imputed.set_index(['index_bm'])
+
 
 #%% Combine mmCSM_lig Data