fclesio

def get_topics(df, n_components, number_words):
    
    # Convert to list
    data = df.lyric.values.tolist()

    # Remove special characters
    data = [re.sub('\S*@\S*\s?', '', sent) for sent in data]

    # Remove new line characters
    data = [re.sub('\s+', ' ', sent) for sent in data]

fclesio

lda_model_angra, data_vectorized_angra, \
data_angra, lda_output_angra, vectorizer_angra = \
    get_topics(df_raw_lyrics_angra, n_components=7, number_words=10)

fclesio

lda_model_sepultura, data_vectorized_sepultura, \
data_sepultura, lda_output_sepultura, vectorizer_sepultura = \
    get_topics(df_raw_lyrics_sepultura, n_components=7,number_words=10)

fclesio

def get_topic_distribution(df_document_topic):
    df_topic_distribution = df_document_topic['dominant_topic'].value_counts().reset_index(name="Num Documents")
    df_topic_distribution.columns = ['Topic Num', 'Num Documents']
    total_docs = df_topic_distribution['Num Documents'].sum()
    df_topic_distribution['perc_per_topic'] = np.round(((df_topic_distribution['Num Documents'] /total_docs) * 100), 2)

    return df_topic_distribution

fclesio

get_topic_distribution(df_topic_per_document_angra)

fclesio

get_topic_distribution(df_topic_per_document_sepultura)

fclesio

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

fclesio

get_word_topics(vectorizer_angra, lda_model_angra)

fclesio

get_word_topics(vectorizer_sepultura, lda_model_sepultura)

fclesio

def get_lda_plot(lda_model, data_vectorized, vectorizer):
    pyLDAvis.enable_notebook()
    panel = pyLDAvis.sklearn.prepare(lda_model, data_vectorized, vectorizer, mds='tsne')
    return panel