def _get_train_stream(self, data):
""" returns training instances stream from data file name or
data source"""
feature_alphabet = self._feature_alphabet
if isinstance(data, str):
stream = Source(data,
feature_alphabet=feature_alphabet,
alphabet_lock=False,
alphabet_pop=False,
bias=self._bias)
elif isinstance(data, Source):
stream = data
elif callable(data):
stream = Source(data,
feature_alphabet=feature_alphabet,
alphabet_lock=False,
alphabet_pop=False,
bias=self._bias)
else:
raise Exception(
"Error: data is either string for file name or ClassificationSource!"
)
# set alphabet from data
self.set_alphabet(stream.get_alphabet())
return stream
def _get_test_stream( self, data ):
""" returns test instances stream from data file name or
data source"""
if isinstance(data,str):
stream = Source( data, alphabet_lock=True,\
alphabet_pop=False, bias=self._bias )
elif isinstance(data,Source):
stream = data
else:
raise Exception("Error: data is either string for file name or ClassificationSource!")
# use model alphabet
stream.set_alphabet( self.get_alphabet() )
return stream
def _get_test_stream(self, data):
""" returns test instances stream from data file name or
data source"""
if isinstance(data, str):
stream = Source( data, alphabet_lock=True,\
alphabet_pop=False, bias=self._bias )
elif isinstance(data, Source):
stream = data
else:
raise Exception(
"Error: data is either string for file name or ClassificationSource!"
)
# use model alphabet
stream.set_alphabet(self.get_alphabet())
return stream
def _get_train_stream( self, data ):
""" returns training instances stream from data file name or
data source"""
feature_alphabet = self._feature_alphabet
if isinstance(data,str):
stream = Source(data, feature_alphabet=feature_alphabet, alphabet_lock=False, alphabet_pop=False, bias=self._bias)
elif isinstance(data,Source):
stream = data
elif callable(data):
stream = Source(data, feature_alphabet=feature_alphabet, alphabet_lock=False, alphabet_pop=False, bias=self._bias)
else:
raise Exception("Error: data is either string for file name or ClassificationSource!")
# set alphabet from data
self.set_alphabet( stream.get_alphabet() )
return stream