Wordcloud visualization of clusters

wordcloud.py

%%time
clusters = dbscan.fit(doc2vec_list)

cl_labels = clusters.labels_.tolist()

def wordcloud_cluster_byIds(cluId):
    texts = []
    for i in range(0, len(cl_labels)):
        if cl_labels[i] == cluId:
            for word in word_tokenize(dialogs_concatted.iloc[i].TEXT):
                texts.append(word)
    
    wordcloud = WordCloud(max_font_size=40, relative_scaling=.8).generate(' '.join(texts))
    plt.figure(figsize=(10,10))
    plt.imshow(wordcloud)
    plt.axis("off")
    plt.title('Cluster #{}'.format(cluId))
    plt.savefig(str(cluId)+".png")
    
for cluId in tqdm_notebook(set(cl_labels)):
    wordcloud_cluster_byIds(cluId)