tfidf.py

pipeline = Pipeline([
    # Use FeatureUnion to combine the features from subject and body
    ('union', FeatureUnion(
        transformer_list=[
            ('review_text', Pipeline([
                ('selector', ItemSelector(key='review_text')),
                ('count_dict', CountVectorizer()),
            ])),
            ('rating', Pipeline([
                ('selector', ItemSelector(key='rating')),
                ('rating_dict', CountVectorizer())
            ])),
            ('verified_purchase', Pipeline([
                ('selector', ItemSelector(key='verified_purchase')),
                ('verified_dict', CountVectorizer())
            ]))
        ]
    )),
    ('classifier', MultinomialNB(alpha=0.2)),
])