Plot grayscale wordclouds with ease.

plot-grayscale-wordclouds.py

# Import pymongo, pandas and matplotlib
import tqdm, re, pandas as pd, random
import matplotlib.pyplot as plt

# Import wordcloud library
from wordcloud import WordCloud, STOPWORDS
stopwords= set(STOPWORDS)

# Define the colors for grayscale
def grey_color_func(word, font_size, position, orientation, random_state=None, **kwargs):
   return "hsl(0, 0%%, %d%%)" % random.randint(15, 45)

# Preprocess the data (remove hashtag, links and mentions from the text)
def preprocess(data):
    comment_words= ''
    for i in tqdm.tqdm(data):
        if isinstance(i, str):
            tokens= re.sub("(@[A-Za-z0-9]+)|([^0-9A-Za-z \t])|(\w+:\/\/\S+)", " ", i).split()
            for i in range(len(tokens)):
                tokens[i]= tokens[i].lower() 
            comment_words+= " ".join(tokens) + " "
    return comment_words
    
# Plotting the wordcloud
def plotWordCloud(data):

    # Configuring the WordCloud api
    wordcloud= WordCloud(
        collocations= False, # To remove duplicate entries
        width= 1000, 
        height= 1000,
        background_color= '#ffffff',
        stopwords= stopwords, 
        min_font_size= 10
    ).generate(preprocess(data))
    wordcloud.recolor(color_func= grey_color_func)
    
    # plot the WordCloud
    plt.figure(figsize= (8, 8), facecolor= None)
    plt.imshow(wordcloud) 
    plt.axis("off") 
    plt.tight_layout(pad= 0)
    plt.show()