preprocess.py

from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer

no_features = 1000

# NMF is able to use tf-idf
tfidf_vectorizer = TfidfVectorizer(max_df=0.95, min_df=2, max_features=no_features, stop_words='english')
tfidf = tfidf_vectorizer.fit_transform(documents)
tfidf_feature_names = tfidf_vectorizer.get_feature_names()

# LDA can only use raw term counts for LDA because it is a probabilistic graphical model
tf_vectorizer = CountVectorizer(max_df=0.95, min_df=2, max_features=no_features, stop_words='english')
tf = tf_vectorizer.fit_transform(documents)
tf_feature_names = tf_vectorizer.get_feature_names()