Onnowpurbo at 03:07, 5 February 2017

2017-02-05T03:07:58Z

← Older revision		Revision as of 03:07, 5 February 2017
Line 21:		Line 21:
	args = parse_args()		args = parse_args()
	infile = args.infile		infile = args.infile

			words = re.findall(r'\w+', open(infile).read().lower())
			wordcommon = Counter(words).most_common(400)

	~~words~~ = ~~re.findall(r~~'~~\w+~~'~~, open~~(~~infile)~~.~~read(~~).lower())		for word, val in wordcommon:
	~~wordcommon = Counter~~(~~words~~).~~most_common~~(~~300~~)		if hanya_huruf(word) and len(word)>1 and word!='Iing' :
	print ~~wordcommon~~		word = word.strip(string.punctuation).lower()
			if word not in nltk.corpus.stopwords.words('english'):
			if word not in nltk.corpus.stopwords.words('indonesia'):
			print word

			~

Onnowpurbo: 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_h..."

2017-02-02T01:09:47Z

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_h..."

New page

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())
wordcommon = Counter(words).most_common(300)
print wordcommon

Python: cari-stopwords-common.py - Revision history

Onnowpurbo at 03:07, 5 February 2017

Onnowpurbo: 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_h..."