from sklearn.linear_model import LogisticRegression

lr_clf = LogisticRegression(max_iter=1000)
lr_clf.fit(X_train, y_train)

y_pred_lr = lr_clf.predict(X_test)
print("Logistic Regression accuracy:", accuracy_score(y_test, y_pred_lr))

# Compare predictions side by side
for i in range(len(X_test)):
    text = texts[idx_test[i]]
    label = y_test[i]
    nb_prediction = y_pred[i]
    lr_prediction = y_pred_lr[i]
    print(f"MSG: '{text}' | TRUE: {label} | NB: {nb_prediction} | LR: {lr_prediction}")