trump_tweet_wordcloud.py

import re

import pandas as pd
from pandas import DataFrame

import random
import sys
from os import path
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
from wordcloud import WordCloud, STOPWORDS

def wordcloud():
    X = pd.read_csv('data/result_1.csv')
    texts = X['text'].values[-3000:]
    join = '\n'.join(texts).lower()
    join = re.sub('[^a-z0-9#]', ' ', join).replace('\s+',' ')
    d = path.dirname(__file__)
    text = join
    mask = np.array(Image.open(path.join(d, "../data/mask.png")))

    stopwords = set(STOPWORDS)
    stopwords.add('https')
    stopwords.add('http')
    stopwords.add('realdonaldtrump')
    stopwords.add('co')

    cmap = plt.cm.get_cmap('Dark2')
    wc = WordCloud(background_color="white", max_words=250, mask=mask,
                   stopwords=stopwords, colormap=cmap)
    
    # generate word cloud
    wc.generate(text)

    # store to file
    wc.to_file(path.join(d, "wordcloud.png"))

    # show
    plt.imshow(wc, interpolation='bilinear')
    plt.axis("off")
    plt.figure()
    plt.imshow(mask, cmap=cmap, interpolation='bilinear')
    plt.axis("off")
    plt.show()

if __name__ == '__main__':
    wordcloud()