Update app.py

app.py

@@ -20,8 +20,10 @@ def clean_text(text):
 
 texts_cleaned = [clean_text(t) for t in texts]
 
-# 3. Train/test split
-X_train, X_test, y_train, y_test = train_test_split(texts_cleaned, labels, test_size=0.2, random_state=42)
+# 3. Train/test split (use stratified sampling!)
+X_train, X_test, y_train, y_test = train_test_split(
+    texts_cleaned, labels, test_size=0.2, random_state=42, stratify=labels
+)
 
 # 4. Build model: TF-IDF + Logistic Regression
 model = make_pipeline(