Update app.py

app.py

@@ -40,7 +40,9 @@ def preprocess_and_train(df):
     ros = RandomOverSampler(random_state=42)
     X_resampled, y_resampled = ros.fit_resample(text_embeddings, labels)
 
-    X_train, X_test, y_train, y_test = train_test_split(X_resampled, y_resampled, test_size=0.2, random_state=42)
+    '''X_train, X_test, y_train, y_test = train_test_split(X_resampled, y_resampled, test_size=0.2, random_state=42)'''
+    X_train, X_test, y_train, y_test = train_test_split(X_resampled, y_resampled, test_size=0.2, random_state=42, stratify=y_resampled)
+
 
     clf = LogisticRegression(max_iter=1000)
     clf.fit(X_train, y_train)