Difference between revisions of "Python: cari-stopwords-freq.py"
Jump to navigation
Jump to search
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_...") |
Onnowpurbo (talk | contribs) |
||
Line 5: | Line 5: | ||
import re | import re | ||
− | ps=PorterStemmer() | + | ps=PorterStemmer() |
def hanya_huruf( input ): | def hanya_huruf( input ): | ||
Line 25: | Line 25: | ||
wordfreqs = Counter(words) | wordfreqs = Counter(words) | ||
for word, count in wordfreqs.items(): | for word, count in wordfreqs.items(): | ||
− | if count < | + | if hanya_huruf(word) and len(word)>1 and word!='Iing' and count<10 : |
− | + | 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 |
Latest revision as of 10:09, 5 February 2017
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 hanya_huruf(word) and len(word)>1 and word!='Iing' and count<10 : 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