import pandas as pd
from sklearn.feature_extraction.text import CountVectorizer, TfidfTransformer

chunks = pd.read_csv("data.csv.bz2",
                     chunksize=1000000,
                     nrows=120000000,
                    )

print(type(chunks))  # <class 'pandas.io.parsers.TextFileReader'>

count_vectorizer = CountVectorizer()
X_train_counts = count_vectorizer.fit_transform(data_train.comment)

tfidf_transformer = TfidfTransformer()
X_train_tfidf = tfidf_transformer.fit_transform(X_train_counts)