def __init__(self, train_set, feature_extractor=basic_extractor, format=None, **kwargs):
self.format_kwargs = kwargs
self.feature_extractor = feature_extractor
if is_filelike(train_set):
self.train_set = self._read_data(train_set, format)
else: # train_set is a list of tuples
self.train_set = train_set
self.train_features = None
def __init__(self, train_set, feature_extractor=basic_extractor, format=None, **kwargs):
self.format_kwargs = kwargs
self.feature_extractor = feature_extractor
if is_filelike(train_set):
self.train_set = self._read_data(train_set, format)
else: # train_set is a list of tuples
self.train_set = train_set
self.train_features = None
def __init__(self, train_set, feature_extractor=basic_extractor, format=None, **kwargs):
self.format_kwargs = kwargs
self.feature_extractor = feature_extractor
if is_filelike(train_set):
self.train_set = self._read_data(train_set, format)
else: # train_set is a list of tuples
self.train_set = train_set
self._word_set = _get_words_from_dataset(self.train_set) # Keep a hidden set of unique words.
self.train_features = None
def __init__(self, train_set, feature_extractor=basic_extractor, format=None, **kwargs):
self.format_kwargs = kwargs
self.feature_extractor = feature_extractor
if is_filelike(train_set):
self.train_set = self._read_data(train_set, format)
else: # train_set is a list of tuples
self.train_set = train_set
self._word_set = _get_words_from_dataset(self.train_set) #Keep a hidden set of unique words.
self.train_features = None
def detect(fp, max_read=1024):
"""Attempt to detect a file's format, trying each of the supported
formats. Return the format class that was detected. If no format is
detected, return ``None``.
"""
if not is_filelike(fp):
return None
for Format in _registry.values():
if Format.detect(fp.read(max_read)):
fp.seek(0)
return Format
fp.seek(0)
return None
def detect(fp, max_read=1024):
"""Attempt to detect a file's format, trying each of the supported
formats. Return the format class that was detected. If no format is
detected, return ``None``.
"""
if not is_filelike(fp):
return None
for Format in _registry.values():
if Format.detect(fp.read(max_read)):
fp.seek(0)
return Format
fp.seek(0)
return None
def accuracy(self, test_set, format=None):
"""Compute the accuracy on a test set.
:param test_set: A list of tuples of the form ``(text, label)``, or a
file pointer.
:param format: If ``test_set`` is a filename, the file format, e.g.
``"csv"`` or ``"json"``. If ``None``, will attempt to detect the
file format.
"""
if is_filelike(test_set):
test_data = self._read_data(test_set, format)
else: # test_set is a list of tuples
test_data = test_set
test_features = [(self.extract_features(d), c) for d, c in test_data]
return nltk.classify.accuracy(self.classifier, test_features)
def accuracy(self, test_set, format=None):
"""Compute the accuracy on a test set.
:param test_set: A list of tuples of the form ``(text, label)``, or a
file pointer.
:param format: If ``test_set`` is a filename, the file format, e.g.
``"csv"`` or ``"json"``. If ``None``, will attempt to detect the
file format.
"""
if is_filelike(test_set):
test_data = self._read_data(test_set)
else: # test_set is a list of tuples
test_data = test_set
test_features = [(self.extract_features(d), c) for d, c in test_data]
return nltk.classify.accuracy(self.classifier, test_features)
def test_is_filelike():
with open(CSV_FILE) as fp:
assert_true(is_filelike(fp))
assert_false(is_filelike('notafile'))
assert_false(is_filelike(12.3))
def test_is_filelike():
with open(CSV_FILE) as fp:
assert_true(is_filelike(fp))
assert_false(is_filelike('notafile'))
assert_false(is_filelike(12.3))
