TF-IDF, pairwise similarity matrix, and pandas dataframe

tfidf.py

import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer

documents = [open(f).read() for f in texts]
tfidf = TfidfVectorizer(stop_words=my_stop_words).fit_transform(documents)
pairwise_similarity = tfidf * tfidf.T
pairwise_similarity_matrix = pairwise_similarity.todense()
psm_df = pd.DataFrame(pairwise_similarity_matrix, index = titles, columns = titles).round(3)
psm_df