RWETMidterm_Frequency Analysis

gistfile1.txt

from __future__ import division
from random import shuffle
import sys
import string # to find punctuation 
import re
import pprint
import random


#load source text
##text_file = open("american_psycho.txt", "w")

punctuation_set = set(string.punctuation)



counts = {}
all_numbers = list()
unique_words = list()
##for c in string.punctuation:

for line in sys.stdin:
	line = line.strip()
	
	for punctuation in punctuation_set:
		line = line.replace(punctuation, '')
	line = line.replace("'", "")
	line = line.replace('\"','')
	line = line.replace("\n", "")
	line = line.replace("\r", "")
	line = line.replace("\t", "")
	line = line.replace('"','') 
	
	words = line.split() # split line by words

	

	for item in words:   # for every word
		if item in counts:  #is the item in the dictionary?
			counts[item] += 1
		else:
			counts[item] = 1
	


for key in counts.keys():
	if counts[key] == 1:
		unique_words.append(key.upper())

uniqueWord = random.sample(unique_words, 1)

# for key in counts.keys():
# 	if counts[key] == max()



######print singular numbers as a giant list
singleList = list()
all_numbers = counts.values()
all_numbers.sort()

most_word =  list()


######put the most common word in an array called most_word
for key in counts.keys():
	if counts[key] == max(all_numbers):
		most_word.append(key)


##print most_word

totalWords = sum(all_numbers)

nums = all_numbers

#######append all the 1's/unique words to singleList
for item in nums:
	if item == 1:
		singleList.append(item)

oneWords = len(singleList)
######or uniqueWords = sum(singleList)
##print oneWords
##print totalWords
ratioUnique = float(oneWords/totalWords)
print ratioUnique 
#######create a list with 6000 background values of 1
backgroundList = list()
backgroundNum = 1000 * ratioUnique
backgroundNum2 = 1000 * (1 - ratioUnique)

backgroundList = most_word * int(backgroundNum2/2) + ['+'] * int(backgroundNum) + most_word * int(backgroundNum2/2)



backgroundList.insert(int(backgroundNum/2 + backgroundNum2/2), uniqueWord)
####shuffle(backgroundList)

int(len(backgroundList)/4) 

print s.join(map(str, backgroundList)).center(50)

#______________________________________________________