import pandas as pd
df = pd.read_csv("hf://datasets/CIS5190abcd/headlines_train/train_cleaned_headlines.csv")

from sklearn.model_selection import train_test_split
X = df['title']
y = df['labels']
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
from sklearn.feature_extraction.text import TfidfVectorizer
tfidf = TfidfVectorizer(max_features=5000, ngram_range=(1, 2), stop_words='english')
X_train_tfidf = tfidf.fit_transform(X_train)
X_test_tfidf = tfidf.transform(X_test)