minor fixes. update helper, autoencoder and main.py

autoencoder.py

@@ -51,8 +51,8 @@ def __init__(self, num_features, verbose=True, mse_threshold = 0.5, archi="U15,D
 
 
     def accuracy(self, y_true, y_pred):
-        mse = K.mean(K.square((y_true - y_pred)), axis = 1)
-        temp = K.ones(K.shape(mse))
+        mse = K.mean(K.square((y_true - y_pred)), axis=1)
+        temp = K.ones_like(mse) # Resolve out-of-scope error
         return K.mean(K.equal(temp, K.cast(mse < self.mse_threshold, temp.dtype)))
 
     def loss(self, y_true,y_pred):

helper.py

@@ -20,7 +20,7 @@ def dataframe_drop_correlated_columns(df, threshold=0.95, verbose=False):
     corr_matrix = df.corr().abs()
 
     # Select upper triangle of correlation matrix
-    upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(np.bool))
+    upper = corr_matrix.where(np.triu(np.ones(corr_matrix.shape), k=1).astype(bool)) # Depracated np.bool, change to bool
 
     # Find index of feature columns with correlation greater than 0.95
     to_drop = [column for column in upper.columns if any(upper[column] > threshold)]

main.py

@@ -42,7 +42,10 @@ def evaluate(model, valid_X, attack_path, output_file):
 label_encoder_1 = preprocessing.LabelEncoder()
 label_encoder_2 = preprocessing.LabelEncoder()
 label_encoder_3 = preprocessing.LabelEncoder()
-one_hot_encoder = preprocessing.OneHotEncoder(categorical_features = [1,2,3])
+# one_hot_encoder = preprocessing.OneHotEncoder(categorical_features = [1,2,3])
+
+
+
 
 def read_kdd_dataset(path):
     global label_encoder_1, label_encoder_2, label_encoder_3, one_hot_encoder
@@ -59,7 +62,11 @@ def read_kdd_dataset(path):
         dataset[:, 1] = label_encoder_1.fit_transform(dataset[:, 1])
         dataset[:, 2] = label_encoder_2.fit_transform(dataset[:, 2])        
         dataset[:, 3] = label_encoder_3.fit_transform(dataset[:, 3])
-        dataset_features = one_hot_encoder.fit_transform(dataset[:, :-2]).toarray() 
+        # dataset_features = one_hot_encoder.fit_transform(dataset[:, :-2]).toarray() 
+        categorical_cols = [1, 2, 3]  # Specify the categorical columns here
+        # Ensure categorical columns are properly encoded using OneHotEncoder
+        one_hot_encoder = preprocessing.OneHotEncoder(categories='auto', sparse=False, handle_unknown='ignore')
+        one_hot_encoded_cols = one_hot_encoder.fit_transform(dataset[:, categorical_cols])
     else:
         dataset[:, 1] = label_encoder_1.transform(dataset[:, 1])
         dataset[:, 2] = label_encoder_2.transform(dataset[:, 2])