
Untitled
By: a guest on
May 12th, 2012 | syntax:
None | size: 0.46 KB | hits: 15 | expires: Never
Extracting specific information from text
import nltk
from nltk.text import *
from nltk.corpus import PlaintextCorpusReader
def readfiles():
corpus_root = 'C:prototypeemails'
w = PlaintextCorpusReader(corpus_root, '.*')
t = Text(w.words())
print "--- to ----"
print t.concordance("to")
print "--- from ----"
print t.concordance("from")
cityState = dataAfterTo.split(",")
city = cityState[0]
state = cityState[1].split()[0]