update Part_B.py

Part_A.py

@@ -14,46 +14,54 @@ from sklearn.ensemble import RandomForestClassifier
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.neighbors import KNeighborsClassifier
 
+# This function performs cross-validation on a given classifier
 def cross_validation(classifier, features, labels, scoring_metrics):
+    # Perform cross-validation using the given classifier, features, labels, and scoring metrics
     scores = cross_val_score(classifier, features, labels, cv=5, scoring=scoring_metrics)
+    # Return the mean score of the cross-validation
     return scores.mean()
 
 def main():
     best_classifier_average = 0
+
+    # Read the training data
     train_data = pd.read_csv("TrainingDataBinary.csv", header = None)
 
+    # Shuffle the training data
     train_data_shuffled = shuffle(train_data)
 
+    # Split the training data into features and labels
     train_features = train_data_shuffled.iloc[:, :-1] # Select everything apart from the last column
     train_labels = train_data_shuffled.iloc[:, -1] # Select the last column
 
+    # Scale the training features
     scaler = StandardScaler()
     train_features_scaled = scaler.fit_transform(train_features)
 
-    
-
+    # Define the hyperparameters for the Bayes search
     parameters = {
         "solver" : ["lbfgs", "sgd", "adam"],
         "activation" : ["relu", "logistic", "tanh"],
         "learning_rate" : ["constant", "invscaling", "adaptive"]
     }
 
+    # Perform Bayesian optimization to find the best hyperparameters
     search = BayesSearchCV(MLPClassifier(max_iter = 10000), parameters, n_iter = 50, n_jobs = -1, cv = 5, scoring = "accuracy").fit(train_features_scaled, train_labels)
     print(f"Best Score: {search.best_score_}")
     print(f"Best Hyperparameters: {search.best_params_}")
 
-    """
     
+    # Train the classifiers
     classifiers = [
-                   #LogisticRegression(max_iter = 10000, solver = "newton-cg", C = 9.416).fit(train_features_scaled, train_labels),
+        LogisticRegression(max_iter = 10000, solver = "newton-cg", C = 9.416).fit(train_features_scaled, train_labels),
         MLPClassifier(max_iter = 10000, solver = "adam", activation = "tanh", learning_rate = "constant").fit(train_features_scaled, train_labels)
-                   #SVC(C = 7.989999999999979, kernel = "linear").fit(train_features_scaled, train_labels),
+        SVC(C = 7.989999999999979, kernel = "linear").fit(train_features_scaled, train_labels),
         #RandomForestClassifier(n_estimators = 418, max_depth = 5).fit(train_features_scaled, train_labels),
         #DecisionTreeClassifier(max_features = "sqrt", criterion = "gini", max_depth = 19).fit(train_features_scaled, train_labels),
         #KNeighborsClassifier(n_neighbors = 4, n_jobs = -1, leaf_size = 68, metric = "manhattan", weights = "distance", algorithm = "kd_tree").fit(train_features_scaled, train_labels)
     ]
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      
-
+    # Evaluate the performance of the trained classifiers
     for classifier in classifiers:
         train_predicted_labels = classifier.predict(train_features_scaled)
         train_accuracy = accuracy_score(train_labels, train_predicted_labels)
@@ -66,21 +74,24 @@ def main():
         cv_average = ((cv_accuracy + cv_f1) / 2)
         print(f"Average Score: {cv_average}")
 
+        # Update the best classifier if the current classifier has a better average score
         if (best_classifier_average < cv_average):
             best_classifier = classifier
             best_classifier_average = cv_average
 
-
+    # Read the training data
     test_features = pd.read_csv("TestingDataBinary.csv", header = None)
+
+    # Scale the test features
     test_features_scaled = scaler.transform(test_features)
 
+    # Predict the labels for the test data
     test_predicted_labels = best_classifier.predict(test_features_scaled)
 
+    # Save the test results
     test_results = test_features.copy()
     test_results["Predicted Labels"] = test_predicted_labels
     test_results.to_csv("TestingResultsBinary.csv", header = False, index = False)
 
-    """
-
 if __name__ == "__main__":
     main()
\ No newline at end of file

Part_B.py

@@ -53,6 +53,7 @@ def main():
                    #KNeighborsClassifier(n_neighbors = 4, n_jobs = -1, leaf_size = 68, metric = "manhattan", weights = "distance", algorithm = "kd_tree").fit(train_features_scaled, train_labels)
                    ]
                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                      
+    #Heya
 
     for classifier in classifiers:
         train_predicted_labels = classifier.predict(train_features_scaled)