tfidf.py

from sklearn.feature_extraction.text import TfidfVectorizer

# Using Abhishek Thakur's arguments for TF-IDF
tfv = TfidfVectorizer(min_df=3,  max_features=None, 
            strip_accents='unicode', analyzer='word',token_pattern=r'\w{1,}',
            ngram_range=(1, 3), use_idf=1,smooth_idf=1,sublinear_tf=1,
            stop_words = 'english')

# Filling NaNs with empty string
movies_clean['overview'] = movies_clean['overview'].fillna('')

# Fitting the TF-IDF on the 'overview' text
tfv_matrix = tfv.fit_transform(movies_clean['overview'])

tfv_matrix.shape