Completed comments

model_selection/cv_metric_gen.py

+# CV Metric Generation
+# Author: Joaquín Torres Bravo
 """
     Metric generation for each tuned model.
     Done in a different script for perfomance and clarity purposes.
@@ -5,20 +7,25 @@
 
 # Libraries
 # --------------------------------------------------------------------------------------------------------
+# Basics
 import pandas as pd
 import numpy as np
+import matplotlib.pyplot as plt
+# Models
 from xgboost import XGBClassifier
-from sklearn.metrics import confusion_matrix
-from sklearn.metrics import f1_score, make_scorer, precision_score, recall_score, accuracy_score, roc_auc_score, average_precision_score
 from sklearn.ensemble import RandomForestClassifier, BaggingClassifier, AdaBoostClassifier
 from sklearn.neural_network import MLPClassifier
 from sklearn.svm import SVC
 from sklearn.linear_model import  LogisticRegression
 from sklearn.tree import DecisionTreeClassifier
-from sklearn.model_selection import StratifiedKFold
+# Metrics
+from sklearn.metrics import confusion_matrix
+from sklearn.metrics import f1_score, make_scorer, precision_score, recall_score, accuracy_score, roc_auc_score, average_precision_score
 from sklearn.metrics import RocCurveDisplay, auc
 from sklearn.metrics import PrecisionRecallDisplay, precision_recall_curve
-import matplotlib.pyplot as plt
+# CV
+from sklearn.model_selection import StratifiedKFold
+# Misc
 import ast # String to dictionary
 # --------------------------------------------------------------------------------------------------------
 
@@ -82,9 +89,9 @@ def get_tuned_models(group_str, method_str):
     # Iterate through each row of the DataFrame
     for _, row in tuned_models_df.iterrows():
         model_name = row.iloc[0]
-        # Read dictionary
+        # Read dictionary with parameters
         parameters = ast.literal_eval(row['Best Parameters'])
-        # Add extra parameters 
+        # Add extra parameters if needed
         if model_name == 'AB':
             parameters['algorithm'] = 'SAMME'
         elif model_name == 'LR':
@@ -140,24 +147,31 @@ def negative_recall_scorer(clf, X, y):
     TN_prop = cm[0,0]/(cm[0,1]+cm[0,0])
     return TN_prop
 
-# Custom scorers for AUROC and AUPRC
+# Custom scorers for AUROC (Area Under the Receiver Operating Characteristic Curve) and AUPRC (Area Under the Precision-Recall Curve)
 def AUROC_scorer(clf, X, y):
+    # Check if the classifier has a decision_function method
     if hasattr(clf, "decision_function"):
+        # If so, use the decision function to get the scores for X
         y_score = clf.decision_function(X)
     else:
+        # Otherwise, use predict_proba to get the probabilities, and take the probabilities for the positive class (index 1)
         y_score = clf.predict_proba(X)[:, 1]
+    # Compute and return the ROC AUC score using the true labels and the predicted scores
     return roc_auc_score(y, y_score)
 
 def AUPRC_scorer(clf, X, y):
+    # Check if the classifier has a decision_function method
     if hasattr(clf, "decision_function"):
+        # If so, use the decision function to get the scores for X
         y_score = clf.decision_function(X)
     else:
+        # Otherwise, use predict_proba to get the probabilities, and take the probabilities for the positive class (index 1)
         y_score = clf.predict_proba(X)[:, 1]
+    # Compute and return the average precision score using the true labels and the predicted scores
     return average_precision_score(y, y_score)
 # --------------------------------------------------------------------------------------------------------
 
 if __name__ == "__main__":
-
     # Setup
     # --------------------------------------------------------------------------------------------------------
     # Reading training data
@@ -188,7 +202,7 @@ if __name__ == "__main__":
     cmap = plt.get_cmap('tab10')  
     # --------------------------------------------------------------------------------------------------------
 
-    # Metric generation through cv for tuned models3
+    # Metric generation through cv for tuned models
     # --------------------------------------------------------------------------------------------------------
     scores_sheets = {} # To store score dfs as sheets in the same excel file
     for i, group in enumerate(['pre', 'post']):