Letter frequency in python

Question

I need to make a program that prints out the frequency of letters in a text file and compares that frequency with that of another in python.

So far I am able to prin

Answer 1

I think this is a really straight forward way to do it:

while True:
    speech = raw_input("Enter file name:")

    wholeFile = open(speech, 'r+').read()
    lowlet = wholeFile.lower()

    alphas = 'abcdefghijklmnopqrstuvwxyz'

    # lets set default values first
    occurrences = {letter : 0 for letter in alphas }
    # occurrences = dict(zip(alphas, [0]*len(alphas))) # for python<=2.6

    # total number of valid letters
    total = 0

    # iter everything in the text
    for letter in lowlet:
        # if it is a valid letter then it is in occurrences
        if letter in occurrences:
            # update counts
            total += 1
            occurrences[letter] += 1

    # now print the results:
    for letter, count in occurrences.iteritems():
        print letter, (1.0*count/total)

As you notices you need the total number of valid letters in the text before you can calculate the frequency. Either you filter the text before processing it, or you combine the filtering with the processing, which is what I do here.

Answer 2

You could use the translator recipe to drop all characters not in alpha. Since doing so makes letters contain nothing but characters from alpha, n is now the correct denominator.

You could then use a collections.defaultdict(int) to count the occurrences of the letters:

import collections
import string

def translator(frm='', to='', delete='', keep=None):
    # Python Cookbook Recipe 1.9
    # Chris Perkins, Raymond Hettinger
    if len(to) == 1: to = to * len(frm)
    trans = string.maketrans(frm, to)
    if keep is not None:
        allchars = string.maketrans('', '')
        # delete is expanded to delete everything except
        # what is mentioned in set(keep)-set(delete)
        delete = allchars.translate(allchars, keep.translate(allchars, delete))
    def translate(s):
        return s.translate(trans, delete)
    return translate

alpha = 'abcdefghijklmnopqrstuvwxyz'
keep_alpha=translator(keep=alpha)

while True:
    speech = raw_input("Enter file name:")
    wholeFile = open(speech, 'r+').read()
    lowlet = wholeFile.lower()
    letters = keep_alpha(lowlet)
    n = len(letters)
    occurrences = collections.defaultdict(int)    
    for x in letters:
        occurrences[x]+=1
    for x in occurrences:
        print x, occurrences[x], occurrences[x]/float(n)

Answer 3

import collections
import re
from __future__ import division

file1 = re.subn(r"\W", "", open("file1.txt", "r").read())[0].lower()
counter1 = collections.Counter(file1)
for k, v in counter1.iteritems():
   counter1[k] = v / len(file1)

file2 = re.subn(r"\W", "", open("file2.txt", "r").read())[0].lower()
counter2 = collections.Counter(file2)
for k, v in counter2.iteritems():
   counter2[k] = v / len(file2)

Note: requires Python 2.7.