news_content = df[df.category=='reliable'].news_content.tolist()

tf_vectorizer = CountVectorizer(strip_accents = 'unicode',
                                stop_words = 'english',
                                lowercase = True,
                                token_pattern = r'\b[a-zA-Z]{3,}\b',
                                max_df = 0.5, 
                                min_df = 10)

tfidf_vectorizer = TfidfVectorizer(**tf_vectorizer.get_params())
dtm_tfidf = tfidf_vectorizer.fit_transform(news_content)
lda_tfidf = LatentDirichletAllocation(n_topics=20, random_state=0)
lda_tfidf.fit(dtm_tfidf)

vis_data = pyLDAvis.sklearn.prepare(lda_tfidf, dtm_tfidf, tf_vectorizer)
pyLDAvis.display(vis_data)