# Frequency count, version 1.1

# Input: dictionary of six letter words
# Process: determine the frequency of each letter across the entire dictionary
# Output: each letter A-Z and their total number of appearances in all words
#  This version uses a "list comprehension"

from string import lowercase

def read_words(fname):
#    infile = open(fname)
#    temp = infile.read()
#    infile.close()
#    return temp.split('\n')[:-1]
	infile=open(fname)
	templist=[]
	word=infile.readline()
	while word:
		templist.append(word[0:len(word)-1]) # strip off the end of line '\n' from the end of word
		word=infile.readline()
	return templist

def main():
	wlist = read_words("wordsShort.txt")
#    ht = dict(zip(lowercase, [0]*26)) # hash table
	lowercase = "abcdefghijklmnopqrstuvwxyz"
#	ht=dict(zip(lowercase,[0]*26)) # hash table
	ht={} #hash table
	for i in range(26):
		ht[lowercase[i]] = 0;
 	for w in wlist:
 		for ch in w:
        		ht[ch] += 1
	print "ht: %s" % ht
	pairs=[]
	#pairs = [ (ht[ch], ch) for ch in lowercase[0:26] ] # list comprehension
	for ch in lowercase:
		pairs.append((ht[ch], ch))   # append the tuple
	print "pairs: %s" % pairs
	pairs.sort()  # sorts by the frequency (first in pair).  If frequencies
                      # are tied, then sorts by letter
	pairs.reverse()   # descending 
        
	for (x, y) in pairs:
		print "%s %4d" % (y, x)
              

if __name__=='__main__':
    main()

# Notes
# ------
# 1. Loop over words in dictionary (5K), loop over letters in word (6),
#     increment count for that letter (30K total)
# 2. Loop over letters (26), loop over all words (5K), loop over letters
#     in word (6), count occurrences of current letter (780K total)
#