Topic_Modeling.py

def topic_modeling(data):
    ### Tokens
    tokens = []
    for text in data:
        text = word_tokenize(text)
        tokens.append(text)
        
    ### Make Biagrams
    tokens = make_biagram(data=data,tokens=tokens)

    ### Corpora Dictionary
    dictionary = corpora.Dictionary(tokens)
    
    ### Creating Document Term Matrix
    doc_term_matrix = [dictionary.doc2bow(doc) for doc in tokens]

    ### Training The LDA Model
    lda_model =  gensim.models.LdaModel(doc_term_matrix,   ## Document Term Matrix
                                       num_topics = 5,     ## Number of Topics
                                       id2word = dictionary,     ## Word and Frequency Dictionary                                
                                       passes = 10,        ## Number of passes throw the corpus during training (similar to epochs in neural networks)
                                       chunksize=10,       ## Number of documents to be used in each training chunk
                                       update_every=1,     ## Number of documents to be iterated through for each update.
                                       alpha='auto',       ## number of expected topics that expresses
                                       per_word_topics=True,
                                       random_state=42)

    ### Exploring Common Words For Each Topic With Their Relative Words
    for idx, topic in lda_model.print_topics():
        print("Topic: {} \nWords: {}".format(idx, topic ))
        print("\n")

topic_modeling(cleaned_reviews)