How to Create Beautiful Word Cloud in Python

DataPlotPlus -

A word cloud is a powerful visualization tool that highlights the most frequent words in text data. Using shaped word clouds, such as a parrot, makes visualizations more engaging and aesthetically appealing.

Why Use a Shaped Word Cloud?

  • Enhances visual appeal by following an image shape
  • Helps in branding and creative presentations
  • Allows for custom color mapping from the original image
  • Useful for text analysis, marketing, and education

When to Use a Word Cloud

  • Provides a quick visual summary of text data
  • Highlights important keywords in large datasets
  • Useful for NLP tasks, sentiment analysis, and reports
  • Creates engaging visualizations for presentations

Steps to Create a Parrot-Shaped Word Cloud

  1. Import required libraries (wordcloud, matplotlib, numpy, PIL)
  2. Load a custom mask image (parrot shape example)
  3. Extract colors from the image using ImageColorGenerator
  4. Process text (remove stopwords, clean words)
  5. Generate a WordCloud using the mask and color mapping
  6. Display the final word cloud

More examples and inspiration: WordCloud Examples

Example: Parrot-Shaped Word Cloud

import os
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
from scipy.ndimage import gaussian_gradient_magnitude
from wordcloud import WordCloud, ImageColorGenerator

d = os.path.dirname(__file__) if "__file__" in locals() else os.getcwd()

text = open(os.path.join(d, '/home/user/wiki_rainbow.txt'), encoding="utf-8").read()
parrot_color = np.array(Image.open(os.path.join(d, "/home/user/parrot-by-jose-mari-gimenez2.jpg")))
parrot_color = parrot_color[::3, ::3]
parrot_mask = parrot_color.copy()
parrot_mask[parrot_mask.sum(axis=2) == 0] = 255

edges = np.mean([gaussian_gradient_magnitude(parrot_color[:, :, i] / 255., 2) for i in range(3)], axis=0)
parrot_mask[edges > .08] = 255

wc = WordCloud(max_words=2000, mask=parrot_mask, max_font_size=40, random_state=42, relative_scaling=0)

wc.generate(text)
plt.imshow(wc)

image_colors = ImageColorGenerator(parrot_color)
wc.recolor(color_func=image_colors)
plt.figure(figsize=(10, 10))
plt.imshow(wc, interpolation="bilinear")
wc.to_file("parrot_new.png")

Original source code and explanations can be found here: word_cloud examples parrot.py

You need to download to run the code above:

Output

A parrot-shaped word cloud where words are colored based on the original parrot image:

Full size result:

Customizations

You can enhance your word cloud with:

  • Change the shape:
    wordcloud = WordCloud(mask=custom_mask, contour_color='black', contour_width=2)
  • Custom fonts:
    WordCloud(font_path='path/to/font.ttf')
  • Increase max words & adjust size:
    WordCloud(max_words=200, width=1000, height=500, contour_width=2)
  • Use different color maps:
    WordCloud(colormap='plasma')  # Try 'cool', 'magma', 'inferno', etc.

Resources

Shaped word clouds create stunning visualizations for presentations, reports, and branding.