

In [3]:

    
# Author: Olivier Grisel <olivier.grisel@ensta.org>
#         Lars Buitinck
#         Chyi-Kwei Yau <chyikwei.yau@gmail.com>
# License: BSD 3 clause

from __future__ import print_function
from time import time

from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
from sklearn.decomposition import NMF, LatentDirichletAllocation
from sklearn.datasets import fetch_20newsgroups

n_samples = 2000
n_features = 1000
n_topics = 10
n_top_words = 20


def print_top_words(model, feature_names, n_top_words):
    for topic_idx, topic in enumerate(model.components_):
        print("Topic #%d:" % topic_idx)
        print(" ".join([feature_names[i]
                        for i in topic.argsort()[:-n_top_words - 1:-1]]))
    print()


# Load the 20 newsgroups dataset and vectorize it. We use a few heuristics
# to filter out useless terms early on: the posts are stripped of headers,
# footers and quoted replies, and common English words, words occurring in
# only one document or in at least 95% of the documents are removed.

print("Loading dataset...")
t0 = time()
dataset = fetch_20newsgroups(shuffle=True, random_state=1,
                             remove=('headers', 'footers', 'quotes'))
data_samples = dataset.data[:n_samples]
print("done in %0.3fs." % (time() - t0))

# Use tf-idf features for NMF.
print("Extracting tf-idf features for NMF...")
tfidf_vectorizer = TfidfVectorizer(max_df=0.95, min_df=2,
                                   max_features=n_features,
                                   stop_words='english')
t0 = time()
tfidf = tfidf_vectorizer.fit_transform(data_samples)
print("done in %0.3fs." % (time() - t0))

# Use tf (raw term count) features for LDA.
print("Extracting tf features for LDA...")
tf_vectorizer = CountVectorizer(max_df=0.95, min_df=2,
                                max_features=n_features,
                                stop_words='english')
t0 = time()
tf = tf_vectorizer.fit_transform(data_samples)
print("done in %0.3fs." % (time() - t0))

# Fit the NMF model
print("Fitting the NMF model with tf-idf features, "
      "n_samples=%d and n_features=%d..."
      % (n_samples, n_features))
t0 = time()
nmf = NMF(n_components=n_topics, random_state=1,
          alpha=.1, l1_ratio=.5).fit(tfidf)
print("done in %0.3fs." % (time() - t0))

print("\nTopics in NMF model:")
tfidf_feature_names = tfidf_vectorizer.get_feature_names()
print_top_words(nmf, tfidf_feature_names, n_top_words)

print("Fitting LDA models with tf features, "
      "n_samples=%d and n_features=%d..."
      % (n_samples, n_features))
lda = LatentDirichletAllocation(n_topics=n_topics, max_iter=5,
                                learning_method='online',
                                learning_offset=50.,
                                random_state=0)
t0 = time()
lda.fit(tf)
print("done in %0.3fs." % (time() - t0))

print("\nTopics in LDA model:")
tf_feature_names = tf_vectorizer.get_feature_names()
print_top_words(lda, tf_feature_names, n_top_words)









    



Loading dataset...
done in 1.861s.
Extracting tf-idf features for NMF...






    



/home/shouldsee/.local/lib/python2.7/site-packages/sklearn/feature_extraction/text.py:1089: FutureWarning: Conversion of the second argument of issubdtype from `float` to `np.floating` is deprecated. In future, it will be treated as `np.float64 == np.dtype(float).type`.
  if hasattr(X, 'dtype') and np.issubdtype(X.dtype, np.float):






    



done in 0.547s.
Extracting tf features for LDA...
done in 0.464s.
Fitting the NMF model with tf-idf features, n_samples=2000 and n_features=1000...
done in 0.617s.

Topics in NMF model:
Topic #0:
just people don think like know time good make way really say right ve want did ll new use years
Topic #1:
windows use dos using window program os drivers application help software pc running ms screen files version card code work
Topic #2:
god jesus bible faith christian christ christians does heaven sin believe lord life church mary atheism belief human love religion
Topic #3:
thanks know does mail advance hi info interested email anybody looking card help like appreciated information send list video need
Topic #4:
car cars tires miles 00 new engine insurance price condition oil power speed good 000 brake year models used bought
Topic #5:
edu soon com send university internet mit ftp mail cc pub article information hope program mac email home contact blood
Topic #6:
file problem files format win sound ftp pub read save site help image available create copy running memory self version
Topic #7:
game team games year win play season players nhl runs goal hockey toronto division flyers player defense leafs bad teams
Topic #8:
drive drives hard disk floppy software card mac computer power scsi controller apple mb 00 pc rom sale problem internal
Topic #9:
key chip clipper keys encryption government public use secure enforcement phone nsa communications law encrypted security clinton used legal standard

Fitting LDA models with tf features, n_samples=2000 and n_features=1000...






    



/home/shouldsee/.local/lib/python2.7/site-packages/sklearn/decomposition/online_lda.py:294: DeprecationWarning: n_topics has been renamed to n_components in version 0.19 and will be removed in 0.21
  DeprecationWarning)






    



done in 4.924s.

Topics in LDA model:
Topic #0:
edu com mail send graphics ftp pub available contact university list faq ca information cs 1993 program sun uk mit
Topic #1:
don like just know think ve way use right good going make sure ll point got need really time doesn
Topic #2:
christian think atheism faith pittsburgh new bible radio games alt lot just religion like book read play time subject believe
Topic #3:
drive disk windows thanks use card drives hard version pc software file using scsi help does new dos controller 16
Topic #4:
hiv health aids disease april medical care research 1993 light information study national service test led 10 page new drug
Topic #5:
god people does just good don jesus say israel way life know true fact time law want believe make think
Topic #6:
55 10 11 18 15 team game 19 period play 23 12 13 flyers 20 25 22 17 24 16
Topic #7:
car year just cars new engine like bike good oil insurance better tires 000 thing speed model brake driving performance
Topic #8:
people said did just didn know time like went think children came come don took years say dead told started
Topic #9:
key space law government public use encryption earth section security moon probe enforcement keys states lunar military crime surface technology