Testing CV flow with DT and just PREC and REC

training_models/train_models.py

@@ -22,39 +22,6 @@ from sklearn.linear_model import  LogisticRegression
 from sklearn.tree import DecisionTreeClassifier
 # --------------------------------------------------------------------------------------------------------
 
-
-def negative_recall_scorer(clf, X, y):
-    """Gives the negative recall defined as the (number of true_negative_samples)/(total number of negative samples)"""
-    y_pred = clf.predict(X)
-    cm = confusion_matrix(y, y_pred)
-    TN_prop = cm[0,0]/(cm[0,1]+cm[0,0])
-    return TN_prop
-
-def TN_scorer(clf, X, y):
-    """Gives the number of samples predicted as true negatives"""
-    y_pred = clf.predict(X)
-    cm = confusion_matrix(y, y_pred)
-    TN = cm[0,0]
-    return TN
-def FN_scorer(clf, X, y):
-    """Gives the number of samples predicted as false negatives"""
-    y_pred = clf.predict(X)
-    cm = confusion_matrix(y, y_pred)
-    FN = cm[0,1]
-    return FN
-def FP_scorer(clf, X, y):
-    """Gives the number of samples predicted as false positive"""
-    y_pred = clf.predict(X)
-    cm = confusion_matrix(y, y_pred)
-    FP = cm[1,0]
-    return FP
-def TP_scorer(clf, X, y):
-    """Gives the number of samples predicted as true positive"""
-    y_pred = clf.predict(X)
-    cm = confusion_matrix(y, y_pred)
-    TP = cm[1,1]
-    return TP
-
 def read_data():
     import numpy as np
 
@@ -138,11 +105,22 @@ if __name__ == "__main__":
     # Setup
     # --------------------------------------------------------------------------------------------------------
     # Scorings to use for model evaluation
-    scorings = {'f1':make_scorer(f1_score), 'negative_recall': negative_recall_scorer, 'recall':make_scorer(recall_score), 'precision':make_scorer(precision_score), 'TN':TN_scorer, 'FN':FN_scorer, 'FP':FP_scorer, 'TP':TP_scorer}
+    scorings = {'recall':make_scorer(recall_score), 'precision':make_scorer(precision_score)}
     # Defining cross-validation protocol
     cv = StratifiedKFold(n_splits=10, shuffle=True, random_state=1)
+    result_cols = [f"{model}_{metric}" for model in models_1.keys() for metric in ['PREC', 'REC']]
+    method_names = {
+        0: "ORIG",
+        1: "ORIG_CW",
+        2: "OVER",
+        3: "UNDER"
+    }
     # --------------------------------------------------------------------------------------------------------
 
+    # Evaluating performance through cross validation and exporting results
+    # --------------------------------------------------------------------------------------------------------
+    # Store each df as a sheet in an excel file
+    sheets_dict = {}
     for i, group in enumerate(['pre', 'post']):
         for j, method in enumerate(['', '', 'over_', 'under_']):
             # Get dataset based on group and method
@@ -150,8 +128,20 @@ if __name__ == "__main__":
             y = data_dic['y_train_' + method + group]
             # Use group of models with class weight if needed
             models = models_2 if j == 2 else models_1 
-            # Create df to keep track of each group-method for all its models
-            results = pd.DataFrame()
+            # Save results in dataframe (10 columns since 10-fold cv)
+            res_df = pd.DataFrame(columns=range(1,11), index=result_cols)
             for model_name, model in models.items():
-                cv_results = cross_validate(model, X, y, scoring=scorings, cv=cv, return_train_score=True, n_jobs=1)
+                cv_scores = cross_validate(model, X, y, scoring=scorings, cv=cv, return_train_score=True, n_jobs=1)
+                res_df.loc[model_name + '_PREC'] = list(np.around(np.array(cv_scores["test_precision"]),4))
+                res_df.loc[model_name + '_REC'] = list(np.around(np.array(cv_scores["test_recall"]),4))
+            
+            # Store the DataFrame in the dictionary with a unique key for each sheet
+            sheet_name = f"{group}_{method_names[j]}"
+            sheets_dict[sheet_name] = res_df
+    # Write results to Excel file
+    with pd.ExcelWriter('./training_models/output/cross_val_res.xlsx') as writer:
+        for sheet_name, data in sheets_dict.items():
+            data.to_excel(writer, sheet_name=sheet_name)
+    # --------------------------------------------------------------------------------------------------------
+