Created
April 30, 2019 03:57
-
-
Save lernisto/0eab510e7bfe6c29d555e69006f739e5 to your computer and use it in GitHub Desktop.
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
import re | |
from collections import defaultdict | |
def wordfreq(words): | |
freq = defaultdict(int) | |
for word in words: | |
freq[word] += 1 | |
return freq | |
def report(freq): | |
freq = list(freq.items()) | |
freq.sort(key=lambda x: (-x[1], x[0])) | |
total = 0 | |
for word, count in freq: | |
print(count, word, sep="\t") | |
total += count | |
print(f"total:\t{total}") | |
def readwords(*files): | |
for f in files: | |
if isinstance(f, str): | |
f = open(f) | |
# TODO: replace this simple regex with nltk tokenization | |
for m in re.finditer(r"([-_a-zA-Z0-9]+)", f.read()): | |
yield m.group(0) | |
if __name__ == "__main__": | |
import sys | |
files = [sys.stdin] if len(sys.argv) == 1 else sys.argv[1:] | |
freq = wordfreq(readwords(*files)) | |
report(freq) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment