def test_word_analyzer_unigrams_and_bigrams():
wa = WordNGramAnalyzer(min_n=1, max_n=2, stop_words=None)
text = u"J'ai mang\xe9 du kangourou ce midi, c'\xe9tait pas tr\xeas bon."
expected = [
u"ai",
u"mange",
u"du",
u"kangourou",
u"ce",
u"midi",
u"etait",
u"pas",
u"tres",
u"bon",
u"ai mange",
u"mange du",
u"du kangourou",
u"kangourou ce",
u"ce midi",
u"midi etait",
u"etait pas",
u"pas tres",
u"tres bon",
]
assert_equal(wa.analyze(text), expected)
def test_word_analyzer_unigrams_and_bigrams():
wa = WordNGramAnalyzer(min_n=1, max_n=2, stop_words=None)
text = u"J'ai mang\xe9 du kangourou ce midi, c'\xe9tait pas tr\xeas bon."
expected = [u'ai', u'mange', u'du', u'kangourou', u'ce', u'midi', u'etait',
u'pas', u'tres', u'bon', u'ai mange', u'mange du',
u'du kangourou', u'kangourou ce', u'ce midi', u'midi etait',
u'etait pas', u'pas tres', u'tres bon']
assert_equal(wa.analyze(text), expected)
def test_word_analyzer_unigrams_and_bigrams():
wa = WordNGramAnalyzer(min_n=1, max_n=2, stop_words=None)
text = u"J'ai mang\xe9 du kangourou ce midi, c'\xe9tait pas tr\xeas bon."
expected = [u'ai', u'mange', u'du', u'kangourou', u'ce', u'midi', u'etait',
u'pas', u'tres', u'bon', u'ai mange', u'mange du',
u'du kangourou', u'kangourou ce', u'ce midi', u'midi etait',
u'etait pas', u'pas tres', u'tres bon']
assert_equal(wa.analyze(text), expected)
def test_word_analyzer_unigrams():
wa = WordNGramAnalyzer(min_n=1, max_n=1, stop_words=None)
text = u"J'ai mang\xe9 du kangourou ce midi, c'\xe9tait pas tr\xeas bon."
expected = [u"ai", u"mange", u"du", u"kangourou", u"ce", u"midi", u"etait", u"pas", u"tres", u"bon"]
assert_equal(wa.analyze(text), expected)
text = "This is a test, really.\n\n I met Harry yesterday."
expected = [u"this", u"is", u"test", u"really", u"met", u"harry", u"yesterday"]
assert_equal(wa.analyze(text), expected)
text = StringIO("This is a test with a file-like object!")
expected = [u"this", u"is", u"test", u"with", u"file", u"like", u"object"]
assert_equal(wa.analyze(text), expected)
def test_word_analyzer_unigrams():
wa = WordNGramAnalyzer(min_n=1, max_n=1, stop_words=None)
text = u"J'ai mang\xe9 du kangourou ce midi, c'\xe9tait pas tr\xeas bon."
expected = [u'ai', u'mange', u'du', u'kangourou', u'ce', u'midi',
u'etait', u'pas', u'tres', u'bon']
assert_equal(wa.analyze(text), expected)
text = "This is a test, really.\n\n I met Harry yesterday."
expected = [u'this', u'is', u'test', u'really', u'met', u'harry',
u'yesterday']
assert_equal(wa.analyze(text), expected)
text = StringIO("This is a test with a file-like object!")
expected = [u'this', u'is', u'test', u'with', u'file', u'like',
u'object']
assert_equal(wa.analyze(text), expected)
def test_word_analyzer_unigrams():
wa = WordNGramAnalyzer(min_n=1, max_n=1, stop_words=None)
text = u"J'ai mang\xe9 du kangourou ce midi, c'\xe9tait pas tr\xeas bon."
expected = [u'ai', u'mange', u'du', u'kangourou', u'ce', u'midi',
u'etait', u'pas', u'tres', u'bon']
assert_equal(wa.analyze(text), expected)
text = "This is a test, really.\n\n I met Harry yesterday."
expected = [u'this', u'is', u'test', u'really', u'met', u'harry',
u'yesterday']
assert_equal(wa.analyze(text), expected)
text = StringIO("This is a test with a file-like object!")
expected = [u'this', u'is', u'test', u'with', u'file', u'like',
u'object']
assert_equal(wa.analyze(text), expected)
def test_unicode_decode_error():
# decode_error default to strict, so this should fail
# First, encode (as bytes) a unicode string.
text = u"J'ai mang\xe9 du kangourou ce midi, c'\xe9tait pas tr\xeas bon."
text_bytes = text.encode('utf-8')
# Then let the Analyzer try to decode it as ascii. It should fail,
# because we have given it an incorrect charset.
wa = WordNGramAnalyzer(min_n=1, max_n=2, stop_words=None, charset='ascii')
assert_raises(UnicodeDecodeError, wa.analyze, text_bytes)
ca = CharNGramAnalyzer(min_n=1, max_n=2, charset='ascii')
assert_raises(UnicodeDecodeError, ca.analyze, text_bytes)
# 'svc': [{'probability': True}],
}
# split a training set and a test set
iter = ShuffleSplit(num_posts, n_iterations=1, test_fraction=0.15, indices=False)
for (iter_no, (train_index, test_index)) in enumerate(iter):
print 'Iteration no. %d' %(iter_no + 1)
y_train = np.array([ x for (x, y) in zip(all_data['target'], train_index) if y ])
y_test = np.array([ x for (x, y) in zip(all_data['target'], test_index) if y ])
print 'Sampled %d training and %d test posts' %(len(y_train), len(y_test))
print "Extracting features from the training dataset using a sparse vectorizer"
t0 = time()
title_vectorizer = Vectorizer(
analyzer=WordNGramAnalyzer(
charset='utf-8',
stop_words=set(['a', 'an', 'and', 'in', 'is', 'of', 'on', 'the', 'to']),
)
)
title_train = title_vectorizer.fit_transform([ x for (x, y) in zip(all_data['title'], train_index) if y ])
domain_vectorizer = extract.SimpleVectorizer()
domain_train = domain_vectorizer.fit_transform([ x for (x, y) in zip(all_data['domain'], train_index) if y ])
X_train = title_train
print "done in %fs" % (time() - t0)
print "n_samples: %d, n_features: %d" % X_train.shape
print
print "Extracting features from the test dataset using the same vectorizer"
t0 = time()
title_test = title_vectorizer.transform([ x for (x, y) in zip(all_data['title'], test_index) if y ])
domain_test = domain_vectorizer.transform([ x for (x, y) in zip(all_data['domain'], test_index) if y ])
