w_cloud.py

from wordcloud import WordCloud, STOPWORDS
import matplotlib.pyplot as plt
import pandas as pd

#CHANGE AS NEEDED
df = pd.read_csv(
    "data/computed/cluster/april-21/1-gram-8-clusters.csv", encoding="latin-1")
export_path = 'reports/wordclouds/april-21/'
cluster_no = 8


stopwords = set(STOPWORDS) #need for wordcloud

for i in range(0, cluster_no):
    both = df[df['cluster'] == i]
    both['text'] = both['text'].apply(lambda x: str(x))
    print('printing both wordcloud for cluster no. {}'.format(i))
    wordcloud = WordCloud(width=800, height=800,
                          background_color='white',
                          stopwords=stopwords,
                          min_font_size=10).generate(" ".join(both.text))
    wordcloud.to_file(export_path + 'cluster_{}_both.png'.format(i))

    """yes = df[(df['Y/N'] == 1) & (df['cluster'] == i)]
    #print(yes.head())
    print('printing yes wordcloud for cluster no. {}'.format(i))
    wordcloud = WordCloud(width=800, height=800, 
                        background_color='white', 
                        stopwords=stopwords, 
                        min_font_size=10).generate(" ".join(yes.text))
    wordcloud.to_file(export_path + 'cluster_{}_yes.png'.format(i))

    no = df[(df['Y/N'] == 0) & (df['cluster'] == i)]
    #print(no.head())
    print('printing no wordcloud for cluster no. {}'.format(i))
    wordcloud = WordCloud(width=800, height=800,
                          background_color='white',
                          stopwords=stopwords,
                          min_font_size=10).generate(" ".join(no.text))
    wordcloud.to_file(
        export_path + 'cluster_{}_no.png'.format(i))"""

#if want to display
# plt.figure(figsize=(8, 8), facecolor=None)
# plt.imshow(wordcloud)
# plt.axis("off")
# plt.tight_layout(pad=0)
# plt.show()