def word_counts(self):
'''Dictionary of word frequencies in this text.
'''
counts = defaultdict(int)
stripped_words = [lowerstrip(word) for word in self.words]
for word in stripped_words:
counts[word] += 1
return counts
def contains_extractor(document):
'''A basic document feature extractor that returns a dict of words that
the document contains.
'''
tokenizer = WordTokenizer()
if isinstance(document, basestring):
tokens = set([w.lower()
for w in tokenizer.itokenize(document, include_punc=False)])
else:
tokens = set((lowerstrip(w, all=False) for w in document))
features = dict((u'contains({0})'.format(w), True) for w in tokens)
return features
def __init__(self, text, tokenizer=None,
pos_tagger=None, np_extractor=None, analyzer=None,
parser=None, classifier=None, clean_html=False):
if not isinstance(text, basestring):
raise TypeError('The `text` argument passed to `__init__(text)` '
'must be a string, not {0}'.format(type(text)))
if clean_html:
raise NotImplementedError("clean_html has been deprecated. "
"To remove HTML markup, use BeautifulSoup's "
"get_text() function")
self.raw = self.string = text
self.stripped = lowerstrip(self.raw, all=True)
_initialize_models(self, tokenizer, pos_tagger, np_extractor, analyzer,
parser, classifier)
def basic_extractor(document, train_set):
'''A basic document feature extractor that returns a dict indicating
what words in ``train_set`` are contained in ``document``.
:param document: The text to extract features from. Can be a string or an iterable.
:param train_set: Training data set, a list of tuples of the form
``(words, label)``.
'''
tokenizer = WordTokenizer()
word_features = _get_words_from_dataset(train_set)
if isinstance(document, basestring):
tokens = set([w.lower()
for w in tokenizer.itokenize(document, include_punc=False)])
else:
tokens = set((lowerstrip(w, all=False) for w in document))
features = dict([(u'contains({0})'.format(word), (word in tokens))
for word in word_features])
return features
def test_lowerstrip(self):
assert_equal(lowerstrip(self.text),
'this has punctuation')
def test_lowerstrip(self):
assert_equal(lowerstrip(self.text), 'this. has. punctuation')
