How can I get the topic scores attributed to a document on gensim LSI?

Question

I am a newbie in python and ML. I found a nice script (https://www.machinelearningplus.com/nlp/topic-modeling-visualization-how-to-present-results-lda-models/) on how to get attributed topics to each document for LDA and I changed it to be able to use it with LSI as well. The original code is:

def format_topics_sentences(ldamodel=None, corpus=corpus, texts=data):
    # Init output
    sent_topics_df = pd.DataFrame()
    # Get main topic in each document
    for i, row_list in enumerate(ldamodel[corpus]):
        row = row_list[0] if ldamodel.per_word_topics else row_list            
        # print(row)
        row = sorted(row, key=lambda x: (x[1]), reverse=True)
        # Get the Dominant topic, Perc Contribution and Keywords for each document
        for j, (topic_num, prop_topic) in enumerate(row):
            if j == 0:  # => dominant topic
                wp = ldamodel.show_topic(topic_num)
                topic_keywords = ", ".join([word for word, prop in wp])
                sent_topics_df = sent_topics_df.append(pd.Series([int(topic_num), round(prop_topic,4), topic_keywords]), ignore_index=True)
            else:
                break
    sent_topics_df.columns = ['Dominant_Topic', 'Perc_Contribution', 'Topic_Keywords']

In order to use it for LSI, I changed it to:

def format_topics_sentences_lsi(LsiModel=None, corpus=corpus, texts=data):
    """
    Extract all the information needed such as most predominant topic assigned to document and percentage of contribution
    LsiModel= model to be used
    corpus = corpus to be used
    texts = original text to be classify (for topic assignment)
    """
    # Init output
    sent_topics_df = pd.DataFrame()

    # Get main topic in each document
    for i, row in enumerate(LsiModel[corpus]):
        row = sorted(row, key=lambda x: (x[1]), reverse=True)
        # Get the Dominant topic, Perc Contribution and Keywords for each document
        for j, (topic_num, prop_topic) in enumerate(row):
            if j == 0:  # => dominant topic
                wp = LsiModel.show_topic(topic_num)
                topic_keywords = ", ".join([word for word, prop in wp])
                sent_topics_df = sent_topics_df.append(pd.Series([int(topic_num), round(prop_topic,4), topic_keywords]), ignore_index=True)
            else:
                break
    sent_topics_df.columns = ['Dominant_Topic', 'Perc_Contribution', 'Topic_Keywords']

Is this the correct way?
As LSI is not based on probabilities the "Perc_Contrib" is above 100%. How should I interpret this number?
Apart from the script above, since LSI does not have get_document_topics, which function can I use to see the topic with the highest score?

How can I get the topic scores attributed to a document on gensim LSI?

0 Answers0