update Part_A.py and Part_B.py

Part_A.py

@@ -69,13 +69,21 @@ def main():
     # Evaluate the performance of the trained classifiers
     for classifier_name, classifier in classifiers:
         print(f"Training {classifier_name}...")
+
+        # Predict the labels for the training data 
         train_predicted_labels = classifier.predict(train_features_scaled)
+
+        # Compare predicted labels to actual labels
         train_accuracy = accuracy_score(train_labels, train_predicted_labels)
         print(f"Training Accuracy:", train_accuracy)
+
+        # Perform cross validation to obtain a more accurate accuracy score
         cv_accuracy = cross_validation(classifier, train_features_scaled, train_labels, "accuracy")
         print(f"Cross-Validated Accuracy: {cv_accuracy}")
         cv_f1 = cross_validation(classifier, train_features_scaled, train_labels, "f1")
         print(f"Cross-Validated F1-Score: {cv_f1}")
+
+        # Average both accuracy and f1 score together to find an average cross validation score
         cv_average = ((cv_accuracy + cv_f1) / 2)
         print(f"Average Score: {cv_average} \n")
 

Part_B.py

@@ -6,7 +6,6 @@ from skopt.space import Real, Categorical, Integer
 from sklearn.model_selection import cross_val_score
 from sklearn.utils import shuffle
 from sklearn.preprocessing import StandardScaler
-from sklearn.decomposition import PCA
 from sklearn.metrics import accuracy_score, f1_score
 from sklearn.linear_model import LogisticRegression
 from sklearn.neural_network import MLPClassifier
@@ -15,72 +14,103 @@ 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):
-    scores = cross_val_score(classifier, features, labels, cv = 5, scoring = scoring_metrics, n_jobs = -1)
+    # 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_name = ""
     best_classifier_average = 0
+
+    # Read the training data
     train_data = pd.read_csv("TrainingDataMulti.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)
 
-    """
-
+    # The following commented out code was used to find optimal hyperparameters
+    '''
+    # Define the hyperparameters for the Bayes search
     parameters = {
         "solver" : ["lbfgs", "sgd", "adam"],
         "activation" : ["relu", "logistic", "tanh"],
         "learning_rate" : ["constant", "invscaling", "adaptive"]
     }
 
-    search = BayesSearchCV(MLPClassifier(max_iter = 10000, solver = "newton-cg"), parameters, n_iter = 50, n_jobs = -1, cv = 5, scoring = "accuracy").fit(train_features_scaled, train_labels)
+    # 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_}")
+    '''
     
-    """
-
-    classifiers = [#LogisticRegression(max_iter = 10000, solver = "newton-cg", C = 9.088000000000001).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),
-                   #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)
+    # Train the classifiers
+    classifiers = [
+        #("Logistical Regression" , LogisticRegression(max_iter = 10000, solver = "newton-cg", C = 9.088000000000001).fit(train_features_scaled, train_labels)),
+        ("Multi-layer Perceptron" , MLPClassifier(max_iter = 10000, solver = "adam", activation = "tanh", learning_rate = "adaptive").fit(train_features_scaled, train_labels)),
+        #("C-Support Vector" , SVC(C = 9.59, kernel = "linear").fit(train_features_scaled, train_labels))
     ]
 
-    #Heya
+    # Evaluate the performance of the trained classifiers
+    for classifier_name, classifier in classifiers:
+        print(f"Training {classifier_name}...")
 
-    for classifier in classifiers:
+        # Predict the labels for the training data 
         train_predicted_labels = classifier.predict(train_features_scaled)
+
+        # Compare predicted labels to actual labels
         train_accuracy = accuracy_score(train_labels, train_predicted_labels)
         print(f"Training Accuracy:", train_accuracy)
+
+        # Perform cross validation to obtain a more accurate accuracy score
         cv_accuracy = cross_validation(classifier, train_features_scaled, train_labels, "accuracy")
         print(f"Cross-Validated Accuracy: {cv_accuracy}")
         cv_f1 = cross_validation(classifier, train_features_scaled, train_labels, "f1_weighted")
         print(f"Cross-Validated F1-Score: {cv_f1}")
+
+        # Average both accuracy and f1 score together to find an average cross validation score
         cv_average = ((cv_accuracy + cv_f1) / 2)
-        print(f"Average Score: {cv_average}")
+        print(f"Average Score: {cv_average} \n")
 
+        # Update the best classifier if the current classifier has a better average score
         if (best_classifier_average < cv_average):
+            best_classifier_name = classifier_name
             best_classifier = classifier
             best_classifier_average = cv_average
 
+        # Update the best classifier if the current classifier has a better average score
+        if (best_classifier_average < cv_average):
+            best_classifier_name = classifier_name
+            best_classifier = classifier
+            best_classifier_average = cv_average
 
+    print(f"The best classifier is {best_classifier_name}.\n")
+
+    # Read the training data
     test_features = pd.read_csv("TestingDataMulti.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("TestingResultsMulti1.csv", header = False, index = False)
-
+    test_results.to_csv("TestingResultsMulti.csv", header = False, index = False)
 
+    print("Test data was trained and new labels have been predicted.")
 
 if __name__ == "__main__":
     main()
\ No newline at end of file