def train(data_file_name, learner_opts="", liblinear_opts=""):
"""
Return a :class:`LearnerModel`.
*data_file_name* is the file path of the LIBSVM-format data. *learner_opts* is a
:class:`str`. Refer to :ref:`learner_param`. *liblinear_opts* is a :class:`str` of
LIBLINEAR's parameters. Refer to LIBLINEAR's document.
"""
learner_prob = LearnerProblem(data_file_name)
learner_param = LearnerParameter(learner_opts, liblinear_opts)
idf = None
if learner_param.inverse_document_frequency:
idf = learner_prob.compute_idf()
learner_prob.normalize(learner_param, idf)
m = liblinear_train(learner_prob, learner_param)
if not learner_param.cross_validation:
m.x_space = None # This is required to reduce the memory usage...
m = LearnerModel(m, learner_param, idf)
return m
def train(data_file_name, learner_opts="", liblinear_opts=""):
"""
Return a :class:`LearnerModel`.
*data_file_name* is the file path of the LIBSVM-format data. *learner_opts* is a
:class:`str`. Refer to :ref:`learner_param`. *liblinear_opts* is a :class:`str` of
LIBLINEAR's parameters. Refer to LIBLINEAR's document.
"""
learner_prob = LearnerProblem(data_file_name)
learner_param = LearnerParameter(learner_opts, liblinear_opts)
idf = None
if learner_param.inverse_document_frequency:
idf = learner_prob.compute_idf()
learner_prob.normalize(learner_param, idf)
m = liblinear_train(learner_prob, learner_param)
if not learner_param.cross_validation:
m.x_space = None # This is required to reduce the memory usage...
m = LearnerModel(m, learner_param, idf)
return m