format='%(asctime)s %(levelname)s %(message)s')
################################################################################
# Load some categories from the training set
categories = [
'alt.atheism',
'talk.religion.misc',
]
# Uncomment the following to do the analysis on all the categories
#categories = None
print "Loading 20 newsgroups dataset for categories:"
print categories
data = load_20newsgroups(subset='train', categories=categories)
print "%d documents" % len(data.filenames)
print "%d categories" % len(data.target_names)
print
################################################################################
# define a pipeline combining a text feature extractor with a simple
# classifier
pipeline = Pipeline([
('vect', CountVectorizer()),
('tfidf', TfidfTransformer()),
('clf', SGDClassifier()),
])
parameters = {
# uncommenting more parameters will give better exploring power but will
################################################################################
# Load some categories from the training set
categories = [
'alt.atheism',
'talk.religion.misc',
'comp.graphics',
'sci.space',
]
# Uncomment the following to do the analysis on all the categories
#categories = None
print "Loading 20 newsgroups dataset for categories:"
print categories
data_train = load_20newsgroups(subset='train', categories=categories,
shuffle=True, rng=42)
data_test = load_20newsgroups(subset='test', categories=categories,
shuffle=True, rng=42)
print "%d documents (training set)" % len(data_train.filenames)
print "%d documents (testing set)" % len(data_test.filenames)
print "%d categories" % len(data_train.target_names)
print
# split a training set and a test set
filenames_train, filenames_test = data_train.filenames, data_test.filenames
y_train, y_test = data_train.target, data_test.target
print "Extracting features from the training dataset using a sparse vectorizer"
t0 = time()
logging.basicConfig(level=logging.INFO,
format='%(asctime)s %(levelname)s %(message)s')
################################################################################
# Load some categories from the training set
categories = [
'alt.atheism',
'talk.religion.misc',
]
# Uncomment the following to do the analysis on all the categories
#categories = None
print "Loading 20 newsgroups dataset for categories:"
print categories
data = load_20newsgroups(subset='train', categories=categories)
print "%d documents" % len(data.filenames)
print "%d categories" % len(data.target_names)
print
################################################################################
# define a pipeline combining a text feature extractor with a simple
# classifier
pipeline = Pipeline([
('vect', CountVectorizer()),
('tfidf', TfidfTransformer()),
('clf', SGDClassifier()),
])
parameters = {
# uncommenting more parameters will give better exploring power but will
################################################################################
# Load some categories from the training set
categories = [
'alt.atheism',
'talk.religion.misc',
'comp.graphics',
'sci.space',
]
# Uncomment the following to do the analysis on all the categories
#categories = None
print "Loading 20 newsgroups dataset for categories:"
print categories
data_train = load_20newsgroups(subset='train',
categories=categories,
shuffle=True,
rng=42)
data_test = load_20newsgroups(subset='test',
categories=categories,
shuffle=True,
rng=42)
print "%d documents (training set)" % len(data_train.filenames)
print "%d documents (testing set)" % len(data_test.filenames)
print "%d categories" % len(data_train.target_names)
print
# split a training set and a test set
filenames_train, filenames_test = data_train.filenames, data_test.filenames
y_train, y_test = data_train.target, data_test.target
