word-topics.py

def get_word_topics(vectorizer, lda_model):

    # Show top n keywords for each topic
    def show_topics(vectorizer=vectorizer, lda_model=lda_model, n_words=20):
        keywords = np.array(vectorizer.get_feature_names())
        topic_keywords = []
        for topic_weights in lda_model.components_:
            top_keyword_locs = (-topic_weights).argsort()[:n_words]
            topic_keywords.append(keywords.take(top_keyword_locs))
        return topic_keywords

    topic_keywords = show_topics(vectorizer=vectorizer, lda_model=lda_model, n_words=10)        

    # Topic - Keywords Dataframe
    df_topic_keywords = pd.DataFrame(topic_keywords)
    df_topic_keywords.columns = ['Word '+ str(i) for i in range(df_topic_keywords.shape[1])]
    df_topic_keywords.index = ['Topic '+ str(i) for i in range(df_topic_keywords.shape[0])]

    return df_topic_keywords