Quick python script to find the histogram of words used in the a text file.

wordHistogram.py

#!/usr/bin/python

import sys
import json
from collections import OrderedDict
from operator import itemgetter

def getWordMap(filename):
    wordMap = dict()
    totalWords = 0
    with open(filename, 'r') as f:
        for line in f:
            for w in line.split():
                word = ''.join(e for e in w.lower() if e.isalnum())
                totalWords += 1
                if word in wordMap:
                    wordMap[word] += 1
                else:
                    wordMap[word] = 1
    return (totalWords, wordMap)

if __name__ == "__main__":
    if len(sys.argv) < 3:
        print "python wordFun.py textFile.txt out.yml"
    else:
        total, wordMap = getWordMap(sys.argv[1])
        wm = OrderedDict(sorted(wordMap.items(), key=itemgetter(1), reverse=True))

        print 'Total word count = {}'.format(total)
        print 'Total word dictionary = {}'.format(len(wm))

        with open(sys.argv[2], 'w') as f:
            json.dump({'Total word count':total, 'Total words used': len(wm), 'Word and count': wm}, f, indent=4)