cures-nprm-cloud.png

cures-nprm-cloud.py

#!/usr/bin/env python
"""
Cures NPRM word cloud
================

Creates a simple word cloud out of the ONC Cures Act NPRM. For entertainment purposes only.
Uses https://github.com/amueller/word_cloud to create the cloud.

Based on Masked Word cloud Example
http://amueller.github.io/word_cloud/auto_examples/masked.html

1. Download rule: wget https://www.healthit.gov/sites/default/files/nprm/ONCCuresActNPRM.pdf
2. Get text without footer: pdftotext -y 80 -H 600 -W 1000 -nopgbrk ONCCuresActNPRM.pdf nprm-content.txt
3. Download stencil: wget https://gist.githubusercontent.com/arscan/ed4fac87cad217cb1a3272fbdb0cc70d/raw/f4311e587967f2466c9592ff0c52cc752bd67ad9/cures-nprm-stencil.png
4. Install wordcloud: pip install wordcloud
5. Run this script: ./cures-nprm-cloud.py

"""

from os import path
from PIL import Image
import numpy as np
import os
import random

from wordcloud import WordCloud, STOPWORDS

def grey_color_func(word, font_size, position, orientation, random_state=None,
                            **kwargs):
        return "rgb(%d, %d, %d)" % (random.randint(245,255), random.randint(0, 155), random.randint(0,40))

# get data directory (using getcwd() is needed to support running example in generated IPython notebook)
d = path.dirname(__file__) if "__file__" in locals() else os.getcwd()

# Read the whole text.
text = open(path.join(d, 'nprm-content.txt')).read()

# read the mask image
# taken from
alice_mask = np.array(Image.open(path.join(d, "cures-nprm-stencil.png")))

stopwords = set(STOPWORDS)
stopwords.add("said")

wc = WordCloud(background_color="white", max_words=2000, mask=alice_mask,
               stopwords=stopwords, contour_width=3, contour_color='rgb(255,255,255)').generate(text)

wc.recolor(color_func=grey_color_func, random_state=3)

wc.to_file(path.join(d, "cures-nprm-cloud.png"))

cures-nprm-stencil.png