herrfz

# Reuters-21578 dataset downloader and parser
#
# Author:  Eustache Diemert <[email protected]> 
# http://scikit-learn.org/stable/auto_examples/applications/plot_out_of_core_classification.html
#
# Modified by @herrfz, get pandas DataFrame from the orig SGML
# License: BSD 3 clause

from __future__ import print_function

miguelmalvarez

from nltk import word_tokenize
from nltk.corpus import reuters 
from sklearn.feature_extraction.text import TfidfVectorizer
from nltk.stem.porter import PorterStemmer
import re
from nltk.corpus import stopwords

cachedStopWords = stopwords.words("english")

def tokenize(text):

bbengfort

import os
import time
import string
import pickle

from operator import itemgetter

from nltk.corpus import stopwords as sw
from nltk.corpus import wordnet as wn
from nltk import wordpunct_tokenize