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([strip_punc(w, all=False)
for w in tokenizer.itokenize(document, include_punc=False)])
else:
tokens = set((strip_punc(w, all=False) for w in document))
features = dict((u'contains({0})'.format(w), True) for w in tokens)
return features
def tokenize(self, text, include_punc=True):
'''Return a list of word tokens.
:param text: string of text.
:param include_punc: (optional) whether to include punctuation as separate tokens. Default to True.
'''
tokens = nltk.tokenize.word_tokenize(text)
if include_punc:
return tokens
else:
# Return each word token
# Strips punctuation unless the word comes from a contraction
# e.g. "Let's" => ["Let", "'s"]
# e.g. "Can't" => ["Ca", "n't"]
# e.g. "home." => ['home']
return [word if word.startswith("'") else strip_punc(word, all=False)
for word in tokens if strip_punc(word, all=False)]
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([strip_punc(w, all=False)
for w in tokenizer.itokenize(document, include_punc=False)])
else:
tokens = set(strip_punc(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_strip_punc(self):
assert_equal(strip_punc(self.text),
'this Has Punctuation ')
def noun_phrases():
text = get_text(request)
noun_phrases = set(TextBlob(text).noun_phrases)
# Strip punctuation from ends of noun phrases and exclude long phrases
stripped = [strip_punc(np) for np in noun_phrases if len(np.split()) <= 5]
return jsonify({"result": stripped})
def test_strip_punc_all(self):
assert_equal(strip_punc(self.text, all=True), 'this Has Punctuation')
def test_strip_punc(self):
assert_equal(strip_punc(self.text), 'this. Has. Punctuation')
def noun_phrases():
text = get_text(request)
noun_phrases = set(TextBlob(text).noun_phrases)
# Strip punctuation from ends of noun phrases and exclude long phrases
stripped = [strip_punc(np) for np in noun_phrases if len(np.split()) <= 5]
return jsonify({"result": stripped})
