Python program that finds most frequent word in a .txt file, Must print word and its count

Question

As of right now, I have a function to replace the countChars function,

def countWords(lines):
  wordDict = {}
  for line in lines:
    wordList = lines.split()
    for word in wordList:
      if word in wordDict: wordDict[word] += 1
      else: wordDict[word] = 1
  return wordDict

but when I run the program it spits out this abomination (this is just an example, there's about two pages of words with a huge number count next to it)

before 1478
battle-field 1478
as 1478
any 1478
altogether 1478
all 1478
ago 1478
advanced. 1478
add 1478
above 1478

While obviously this means that the code is sound enough to run, I'm not getting what I want out of it. It needs to print how many times each word is in the file (gb.txt, which is the Gettysburg address) Obviously each word that is in the file isn't in there exactly 1478 times..

I'm pretty new at programming, so I'm kind of stumped..

from __future__ import division

inputFileName = 'gb.txt'

def readfile(fname):
  f = open(fname, 'r')
  s = f.read()
  f.close()
 return s.lower()

def countChars(t):
  charDict = {}
  for char in t:
    if char in charDict: charDict[char] += 1
    else: charDict[char] = 1
  return charDict

def findMostCommon(charDict):
  mostFreq = ''
  mostFreqCount = 0
  for k in charDict:
    if charDict[k] > mostFreqCount:
      mostFreqCount = charDict[k]
      mostFreq = k
  return mostFreq

def printCounts(charDict):
  for k in charDict:
    #First, handle some chars that don't show up very well when they print
    if k == '\n': print '\\n', charDict[k]  #newline
    elif k == ' ': print 'space', charDict[k]
    elif k == '\t': print '\\t', charDict[k] #tab
    else: print k, charDict[k]  #Normal character - print it with its count

def printAlphabetically(charDict):
  keyList = charDict.keys()
  keyList.sort()
  for k in keyList:
    #First, handle some chars that don't show up very well when they print
    if k == '\n': print '\\n', charDict[k]  #newline
    elif k == ' ': print 'space', charDict[k]
    elif k == '\t': print '\\t', charDict[k] #tab
    else: print k, charDict[k]  #Normal character - print it with its count

def printByFreq(charDict):
  aList = []
  for k in charDict:
    aList.append([charDict[k], k])
  aList.sort()     #Sort into ascending order
  aList.reverse()  #Put in descending order
  for item in aList:
    #First, handle some chars that don't show up very well when they print
    if item[1] == '\n': print '\\n', item[0]  #newline
    elif item[1] == ' ': print 'space', item[0]
    elif item[1] == '\t': print '\\t', item[0] #tab
    else: print item[1], item[0]  #Normal character - print it with its count

def main():
  text = readfile(inputFileName)
  charCounts = countChars(text)
  mostCommon = findMostCommon(charCounts)
  #print mostCommon + ':', charCounts[mostCommon]
  #printCounts(charCounts)
  #printAlphabetically(charCounts)
  printByFreq(charCounts)

main()

Answer 1

If you need to count a number of words in a passage, then it is better to use regex.

Let's start with a simple example:

import re

my_string = "Wow! Is this true? Really!?!? This is crazy!"

words = re.findall(r'\w+', my_string) #This finds words in the document

Result:

>>> words
['Wow', 'Is', 'this', 'true', 'Really', 'This', 'is', 'crazy']

Note that "Is" and "is" are two different words. My guess is that you want the to count them the same, so we can just capitalize all the words, and then count them.

from collections import Counter

cap_words = [word.upper() for word in words] #capitalizes all the words

word_counts = Counter(cap_words) #counts the number each time a word appears

Result:

>>> word_counts
Counter({'THIS': 2, 'IS': 2, 'CRAZY': 1, 'WOW': 1, 'TRUE': 1, 'REALLY': 1})

Are you good up to here?

Now we need to do exactly the same thing we did above just this time we are reading a file.

import re
from collections import Counter

with open('your_file.txt') as f:
    passage = f.read()

words = re.findall(r'\w+', passage)

cap_words = [word.upper() for word in words]

word_counts = Counter(cap_words)