Python: cari-stopwords-freq.py
Revision as of 08:08, 2 February 2017 by Onnowpurbo (talk | contribs) (Created page with " import os,nltk,os.path,re,string import argparse from nltk.stem.porter import PorterStemmer from collections import Counter import re ps=PorterStemmer() def hanya_...")
import os,nltk,os.path,re,string import argparse from nltk.stem.porter import PorterStemmer from collections import Counter import re ps=PorterStemmer() def hanya_huruf( input ): r=re.match('^[a-zA-Z]+$', input) if r==None: return False else: return True def parse_args(): parser = argparse.ArgumentParser() parser.add_argument('-i', '--infile', default=, help='input filename') return parser.parse_args() args = parse_args() infile = args.infile words = re.findall(r'\w+', open(infile).read().lower()) wordfreqs = Counter(words) for word, count in wordfreqs.items(): if count < 200: print word