Created
June 5, 2014 13:26
-
-
Save cigrainger/d3b24e002bb140d45c8c 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 re, string, sys, nltk | |
from nltk.stem.wordnet import WordNetLemmatizer | |
from nltk.corpus import wordnet | |
import logging | |
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', | |
level=logging.INFO) | |
lmtzr = WordNetLemmatizer() | |
pattern=re.compile(r'[^a-zA-Z ]') | |
def get_wordnet_pos(treebank_tag): | |
if treebank_tag.startswith('J'): | |
return wordnet.ADJ | |
elif treebank_tag.startswith('V'): | |
return wordnet.VERB | |
elif treebank_tag.startswith('R'): | |
return wordnet.ADV | |
else: | |
return wordnet.NOUN | |
def clean(x): | |
x = x.replace('<image>','') | |
x = pattern.sub('',x.lower()) | |
x = x.replace('\r','') | |
x = x.replace('\n','') | |
x = nltk.word_tokenize(x) | |
tag = nltk.pos_tag(x) | |
pos = [] | |
for i in range(len(tag)): | |
pos.append(get_wordnet_pos(tag[i][1])) | |
y = [] | |
for i in range(len(x)): | |
y.append(lmtzr.lemmatize(x[i],pos[i])) | |
x = ' '.join(y) | |
return(x) | |
with open("abstracts.txt","rb") as f: | |
with open("abstractsfinal.txt","w") as f2: | |
f2.truncate() | |
i = 0 | |
for line in f: | |
y = line.split(',',1) | |
if len(y)==2: | |
c = y[1].replace(',','') | |
a = clean(c) | |
f2.write(a + '\n') | |
i = i+1 | |
print i |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment