Update my_pages/multiverse.py

my_pages/multiverse.py

@@ -12,6 +12,7 @@ from sklearn.preprocessing import MinMaxScaler, StandardScaler
 from sklearn.neural_network import MLPClassifier
 from sklearn.linear_model import SGDClassifier
 from sklearn.ensemble import RandomForestClassifier
+from sklearn.preprocessing import LabelEncoder
 
 choices_list = [
     {"label": "Data Scaling", "options": [
@@ -216,41 +217,35 @@ def render():
     ##########################
 
 
-    def split_and_scale(features_raw, features, label, group, test_split=0.2, preprocess_scale=True):
-        X_raw_train, X_raw_test, X_train, X_test, y_train, y_test, group_train, group_test = train_test_split(
-            features_raw, features, label, group, test_size=test_split, random_state=0)
+    def split_and_scale(features, label, test_split=0.2, preprocess_scale=True):
+        X_train, X_test, y_train, y_test = train_test_split(features, label, test_size=test_split, random_state=0)
     
         if preprocess_scale:
             scaler = MinMaxScaler()
             scaler.fit(X_train)
             X_train, X_test = scaler.transform(X_train), scaler.transform(X_test)
     
-        return X_raw_train, X_raw_test, X_train, X_test, y_train, y_test, group_train, group_test
+        return X_train, X_test, y_train, y_test
     
     def get_stackoverflow_dataset(test_split=0.2, preprocess_scale=True):
-        raw_data = pd.read_csv('stackoverflow_full.csv')
-        raw_data = raw_data[raw_data['Country']=='Canada']
-    
-        features = raw_data[['Age', 'EdLevel', 'Employment', 'Gender', 'MainBranch', 'YearsCode', 'YearsCodePro', 'PreviousSalary', 'ComputerSkills']]
-        features_raw = features.copy()
-        
-        categorical_cols = ['Age', 'EdLevel', 'Employment', 'Gender', 'MainBranch']
-        if len(categorical_cols) > 0:
-            features = pd.get_dummies(features, columns=categorical_cols)
+        data = pd.read_csv('loan_approval_dataset.csv')
+
+        features = data.drop(columns=["loan_id", " loan_status"])
+        features = pd.get_dummies(features, columns=[" education", " self_employed"], drop_first=True).values
         
-        label = np.array(raw_data['Employed'].astype(int))
-        group = features['Gender_Man'].astype('category').cat.codes
+        le = LabelEncoder()
+        label = le.fit_transform(data[" loan_status"])
     
-        features, label, group = np.array(features), np.array(label), np.array(group)
+        features, label = np.array(features), np.array(label)
     
-        return split_and_scale(features_raw, features, label, group, test_split, preprocess_scale)
+        return split_and_scale(features, label, test_split, preprocess_scale)
     
     
     ### Main Code Starts Here
     scaler, arch, iterations, seed = selected_path[0], selected_path[1], int(selected_path[2]), int(selected_path[3])
     random_seed = seed
         
-    X_raw_train, X_raw_test, X_train, X_test, y_train, y_test, group_train, group_test = get_stackoverflow_dataset()
+    X_train, X_test, y_train, y_test = get_stackoverflow_dataset()
     
     placeholder = st.empty()
     modelclass_dict = {'Neural Network (Small)': MLPClassifier([10], random_state=random_seed, max_iter=iterations),