histogram.py

"""Creates a histogram of the word lengths from the text file"""

import sys

def read_text():
	inputF = open(sys.argv[1], 'r')
	return inputF

openF = read_text()
text = openF.read()
		
for punc in "&,?-;:.'":
	text = text.replace(punc, "")
	
words = text.lower().split()
lngth_of_words = []
for word in words:
	lngth_of_words.append(len(word))
	max_l = max(lngth_of_words)
	freqs = [0 for i in range(max_l + 1)]
	for length in lngth_of_words:
		freqs[length] += 1
print("Length   Count")
for i, count in enumerate(freqs):
	if i != 0:
		print("{:>4} {:>8}".format(i, count))
		
freq = dict([(i, count) for i, count in enumerate(freqs)])

yL = round(max(freqs) + 100, -2)	
for y in range(yL, 9, -20):
	if y % 100 ==0:
		print("{:>8}-| ".format(y), end ='')
	else:
		print("{:>8} | ".format(''), end ='')
	for x in range(1, max_l +2):
		if freq.get(x,0) >= y:
			column = "***"
		else:
			column = "   "
		print(column, end="")
	print()
print('        -+-+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+-')
print('         | 1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16')