Created
November 14, 2016 14:04
-
-
Save alexeytal/a61c0bc04604cbb56365fe615a89f249 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import argparse | |
from operator import itemgetter | |
import sys | |
parser=argparse.ArgumentParser() | |
parser.add_argument('file', help='name of the file', type=str) | |
parser.add_argument('-n', help='number of words',type = int) | |
parser.add_argument('-s', help='short words',action = 'store_true') | |
options=parser.parse_args() | |
f = open(options.file, 'r') | |
dict = {} | |
text = f.read() | |
text = text.replace(',',' ') | |
text = text.replace('.', ' ') | |
text = text.split() | |
for i in range(len(text)): | |
dict[text[i]] = dict.get(text[i],0) + 1 | |
a=sorted(dict.items(), key=lambda x:x[1], reverse=True) | |
#a=sorted(dict.items(), key=itemgetter(1), reverse=True) | |
if options.s: | |
a = [(x,y) for x,y in a if len(x)>2] | |
a = a[:options.n] | |
else: | |
a = a[:options.n] | |
for k,v in a: | |
if options.s: | |
if len(k) > 2: | |
print k, v, "%.4f" % (float(v) / len(text)) | |
else: | |
print k, v, float(v) / len(text) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment