gistfile1.py

import re, string, sys, nltk
from nltk.stem.wordnet import WordNetLemmatizer

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("C:\Users\graingec\spillovers\data\patents_abstracts.csv","rb") as f:
    with open("C:\Users\graingec\spillovers\\abstracts\\abstracts.txt","w") as f2:
    	with open("C:\Users\graingec\spillovers\\abstracts\\patentids.txt","w") as f3:
	        f2.truncate()
	        f3.truncate()
	        for line in f:
	            y = line.split(',',1)
	            if len(y)==2:
	                c = y[1].replace(',','')
	                a = clean(c)
	                f2.write(a + '\n')
	                f3.write(y[0] + '\n')