Finding top 3 dominant topics for LDA topic model

Question

I am creating a datatable via this LDA modeling tutorial, (https://www.machinelearningplus.com/nlp/topic-modeling-visualization-how-to-present-results-lda-models/) and instead of just finding the single most dominant topic, I want to expand to find the top 3 most dominant topics, along with each of their percent contributions and topic keywords.

To do that, is it best to create 2 additional functions to create 3 separate dataframes, and append each of the results? Or is there a simpler way to modify the format_topics_sentence function to pull the top 3 topics from the enumerated bag of words corpus?

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']

# Add original text to the end of the output
contents = pd.Series(texts)
sent_topics_df = pd.concat([sent_topics_df, contents], axis=1)
return(sent_topics_df)

df_topic_sents_keywords = format_topics_sentences(ldamodel=lda_model, corpus=corpus, texts=data_ready)

# Format
df_dominant_topic = df_topic_sents_keywords.reset_index()
df_dominant_topic.columns = ['Document_No', 'Dominant_Topic', 'Topic_Perc_Contrib', 'Keywords', 'Text']
df_dominant_topic.head(10)

table ouput

Yedhu Krishna Yedhu Krishna · Accepted Answer · 2020-10-14T11:11:27

I had a similar requirement in a recent project, hopefully this helps you out, you will need to add topic keywords to below code:

topics_df1 = pd.DataFrame()
topics_df2 = pd.DataFrame()
topics_df3 = pd.DataFrame()

for i, row_list in enumerate(lda_model[corpus]):
    row = row_list[0] if lda_model.per_word_topics else row_list            
    row = sorted(row, key=lambda x: (x[1]), reverse=True)
    for j, (topic_num, prop_topic) in enumerate(row):
        if len(row) >= 3:        
            if j ==0:
                topics_df1 = topics_df1.append(pd.Series([int(topic_num), prop_topic]), ignore_index=True)
            elif j ==1:
                topics_df2 = topics_df2.append(pd.Series([int(topic_num), prop_topic]), ignore_index=True)
            elif j ==2:
                topics_df3 = topics_df3.append(pd.Series([int(topic_num), prop_topic]), ignore_index=True)
            else:
                break
        elif len(row) == 2:
            if j ==0:
                topics_df1 = topics_df1.append(pd.Series([int(topic_num), prop_topic]), ignore_index=True)
            elif j ==1:
                topics_df2 = topics_df2.append(pd.Series([int(topic_num), prop_topic]), ignore_index=True)
                topics_df3 = topics_df3.append(pd.Series(['-', '-']), ignore_index=True)
        elif len(row) == 1:
                topics_df1 = topics_df1.append(pd.Series([int(topic_num), prop_topic]), ignore_index=True)
                topics_df2 = topics_df2.append(pd.Series(['-', '-']), ignore_index=True)  
                topics_df3 = topics_df3.append(pd.Series(['-', '-']), ignore_index=True)        
                
            
topics_df1.rename(columns={0:'1st Topic', 1:'1st Topic Contribution'}, inplace=True)
topics_df2.rename(columns={0:'2nd Topic', 1:'2nd Topic Contribution'}, inplace=True)
topics_df3.rename(columns={0:'3rd Topic', 1:'3rd Topic Contribution'}, inplace=True)

topics_comb = pd.concat([topics_df1, topics_df2, topics_df3],  axis=1, sort=False)

#Join topics dataframe to original data
new_df = pd.concat([data_ready, topics_comb], axis=1, sort=False)

Finding top 3 dominant topics for LDA topic model

1 Answers