Last active
April 8, 2022 07:37
-
-
Save timgianitsos/aa60a850012b0b64a45aecf2f316609f to your computer and use it in GitHub Desktop.
Input a file to see how closely word frequencies correspond to the Zipf distribution
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from collections import Counter | |
from string import punctuation | |
from os.path import split | |
import sys | |
__author__ = 'Tim Gianitsos' | |
def main(filename=None, num_display=30): | |
c = Counter(s for t in open(filename).read().split() if (s:=t.lower().replace(fr'“‘”’{punctuation}', '')).isalpha()) | |
mc = c.most_common() | |
num_display = min(int(num_display), len(mc)) | |
mc = mc[:num_display] | |
first_freq = mc[0][1] | |
title = f'Frequencies of top {num_display} words as a ratio of most frequent word' | |
print(title) | |
print('\n'.join(f'{t[0]:13s} {t[1] / first_freq * 100:.2f}%' for t in mc)) | |
try: | |
import matplotlib.pyplot as plt | |
plt.style.use('seaborn') | |
plt.gca().set_xticks(range(1, len(mc) + 1)) | |
plt.gca().set_xticklabels([t[0] for t in mc], rotation=60) | |
plt.plot(range(1, num_display + 1), [1 / i for i in range(1, num_display + 1)], label='Unnormalized Zipf distribution') | |
plt.plot(range(1, num_display + 1), [t[1] / first_freq for t in mc], label=split(filename)[1]) | |
plt.legend() | |
plt.title(title) | |
plt.show() | |
except ModuleNotFoundError as err: | |
pass | |
if __name__ == '__main__': | |
if len(sys.argv) <= 1: | |
print(f'usage: python3.8 {__file__} name_of_text.txt', file=sys.stderr) | |
else: | |
main(*sys.argv[1:]) | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment