Find the leakage risks in this generated feature pipeline.
Python
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.model_selection import train_test_split
def prepare(rows):
texts = [row["text"] for row in rows]
labels = [row["label"] for row in rows]
features = TfidfVectorizer().fit_transform(texts)
return train_test_split(
features, labels, test_size=0.2, random_state=42
)