def __init__(self, large_file=False):
if large_file:
HashingVectorizer.__init__(self)
else:
# Over ride the built in string processing by assigning the
# tokenizer, preprocessor and lowercase parameters as below.
CountVectorizer.__init__(self, tokenizer=identity,
preprocessor=None,
lowercase=False)
def __init__(self, chunksize=100000, **kwargs):
self.chunksize = chunksize
HashingVectorizer.__init__(self, **kwargs)