visualizing_wordcloud.py

# 1. Wordcloud of Top N words in each topic
from matplotlib import pyplot as plt
from wordcloud import WordCloud, STOPWORDS
import matplotlib.colors as mcolors
from nltk.corpus import stopwords

def visualize_wordcloud(model):
    cols = [color for _, color in mcolors.TABLEAU_COLORS.items()]  # more colors: 'mcolors.XKCD_COLORS'

    stop_words = stopwords.words('english')
    
    cloud = WordCloud(stopwords=stop_words,
                    background_color='black',
                    width=2000,
                    height=1500,
                    max_words=10,
                    colormap='tab10',
                    color_func=lambda *args, **kwargs: cols[i],
                    prefer_horizontal=1.0)
    
    

    topics = model.show_topics(formatted=False)

    fig, axes = plt.subplots(2, 5, figsize=(7,7), sharex=True, sharey=True)

    for i, ax in enumerate(axes.flatten()):
        fig.add_subplot(ax)
        topic_words = dict(topics[i][1])
        cloud.generate_from_frequencies(topic_words, max_font_size=200)
        plt.gca().imshow(cloud)
        plt.gca().set_title('Topic ' + str(i+1), fontdict=dict(size=13))
        plt.gca().axis('off')


    plt.subplots_adjust(wspace=0, hspace=0)
    plt.axis('off')
    plt.margins(x=0, y=0)
    plt.tight_layout()
    plt.show()

if __name__ == '__main__':
    visualize_wordcloud()