# model training
model = FASTopic(8, ngram_preprocessing, num_top_words=10000)

# fit model to documents
topic_top_words, doc_topic_dist = model.fit_transform(docs)

# retrieve 20 bigrams for each topic
import pandas as pd

max_bigrams = 20

# Retrieve the bigrams for each topic and select only the word columns
topic_0 = pd.DataFrame(model.get_topic(0, max_bigrams), columns=["Topic_0_word", "Topic_0_prob"])[["Topic_0_word"]]
topic_1 = pd.DataFrame(model.get_topic(1, max_bigrams), columns=["Topic_1_word", "Topic_1_prob"])[["Topic_1_word"]]
topic_2 = pd.DataFrame(model.get_topic(2, max_bigrams), columns=["Topic_2_word", "Topic_2_prob"])[["Topic_2_word"]]
topic_3 = pd.DataFrame(model.get_topic(3, max_bigrams), columns=["Topic_3_word", "Topic_3_prob"])[["Topic_3_word"]]
topic_4 = pd.DataFrame(model.get_topic(4, max_bigrams), columns=["Topic_4_word", "Topic_4_prob"])[["Topic_4_word"]]
topic_5 = pd.DataFrame(model.get_topic(5, max_bigrams), columns=["Topic_5_word", "Topic_5_prob"])[["Topic_5_word"]]
topic_6 = pd.DataFrame(model.get_topic(6, max_bigrams), columns=["Topic_6_word", "Topic_6_prob"])[["Topic_6_word"]]
topic_7 = pd.DataFrame(model.get_topic(7, max_bigrams), columns=["Topic_7_word", "Topic_7_prob"])[["Topic_7_word"]]

# concatenate the dataframes
topics_df = pd.concat([topic_0,topic_1, topic_2, topic_3, topic_4,topic_5,topic_6,topic_7], axis=1)

# remove underscores from bigrams
topics_df = topics_df.applymap(lambda x: x.replace('_', ' ') if isinstance(x, str) else x)