def test_arff_format(self):
dataset = os.path.join(self.data_dir, "germancredit")
namespace = NameSpace(dataset, 'arff',
task='binary.classification',
metric='acc_metric',
target='class')
D = factory.get_data_manager(namespace)
def test_arff_format(self):
dataset = os.path.join(self.data_dir, "germancredit")
namespace = NameSpace(dataset,
'arff',
task='binary.classification',
metric='acc_metric',
target='class')
D = factory.get_data_manager(namespace)
def run(self):
if self._parser is None:
raise ValueError('You must invoke run() only via start_automl()')
self._backend.save_start_time(self._seed)
self._stopwatch = StopWatch()
datamanager = get_data_manager(namespace=self._parser)
self._stopwatch.start_task(datamanager.name)
self._logger = self._get_logger(datamanager.name)
self._datamanager = datamanager
self._dataset_name = datamanager.name
self._fit(self._datamanager)
def start_automl(self, parser):
self._backend.save_start_time(self._seed)
self._stopwatch = StopWatch()
datamanager = get_data_manager(namespace=parser)
self._stopwatch.start_task(datamanager.name)
logger_name = 'AutoML(%d):%s' % (self._seed, datamanager.name)
setup_logger(os.path.join(self._tmp_dir, '%s.log' % str(logger_name)))
self._logger = get_logger(logger_name)
self._datamanager = datamanager
self._dataset_name = datamanager.name
self.start()
def start_automl(self, parser):
self._backend.save_start_time(self._seed)
self._stopwatch = StopWatch()
datamanager = get_data_manager(namespace=parser)
self._stopwatch.start_task(datamanager.name)
logger_name = 'AutoML(%d):%s' % (self._seed, datamanager.name)
setup_logger(os.path.join(self._tmp_dir, '%s.log' % str(logger_name)))
self._logger = get_logger(logger_name)
self._datamanager = datamanager
self._dataset_name = datamanager.name
self.start()
def run(self):
if self._parser is None:
raise ValueError('You must invoke run() only via start_automl()')
self._backend.save_start_time(self._seed)
self._stopwatch = StopWatch()
datamanager = get_data_manager(namespace=self._parser)
self._stopwatch.start_task(datamanager.name)
self._logger = self._get_logger(datamanager.name)
self._datamanager = datamanager
self._dataset_name = datamanager.name
self._fit(self._datamanager)
def test_arff_format(self):
dataset = os.path.join(self.data_dir, "germancredit")
namespace = NameSpace(dataset, "arff", task="binary.classification", metric="acc_metric", target="class")
D = factory.get_data_manager(namespace)
print D
def test_competition_format(self):
dataset = os.path.join(self.data_dir, "31_bac")
namespace = NameSpace(dataset, "automl-competition-format")
D = factory.get_data_manager(namespace)
print D
_metafeatures_encoded_labels = \
autosklearn.metalearning.metafeatures.metafeature.DatasetMetafeatures(
D.name, dict())
for metafeature_name in \
autosklearn.metalearning.metafeatures.metafeatures.npy_metafeatures:
type_ = "HELPERFUNCTION" if metafeature_name not in \
autosklearn.metalearning.metafeatures.metafeatures.metafeatures.functions \
else "METAFEATURE"
_metafeatures_encoded_labels.metafeature_values[metafeature_name] = \
autosklearn.metalearning.metafeatures.metafeature.MetaFeatureValue(
metafeature_name, type_, 0, 0, np.NaN, np.NaN,
"Memory error during dataset scaling.")
mf = _metafeatures_labels
mf.metafeature_values.update(
_metafeatures_encoded_labels.metafeature_values)
mf.dump(mf_filename)
return mf
if __name__ == "__main__":
parser = ArgumentParser()
parser.add_argument("--output-dir", type=str, required=True)
parser.add_argument("--memory-limit", type=int, default=3072)
parser = data_manager_factory.populate_argparse_with_data_options(parser)
args = parser.parse_args()
D = data_manager_factory.get_data_manager(args, encode_labels=False)
mf = calculate_metafeatures(D, args.output_dir, args.memory_limit)
def test_competition_format(self):
dataset = os.path.join(self.data_dir, "31_bac")
namespace = NameSpace(dataset, "automl-competition-format")
D = factory.get_data_manager(namespace)
_metafeatures_encoded_labels = \
autosklearn.metalearning.metafeatures.metafeature.DatasetMetafeatures(
D.name, dict())
for metafeature_name in \
autosklearn.metalearning.metafeatures.metafeatures.npy_metafeatures:
type_ = "HELPERFUNCTION" if metafeature_name not in \
autosklearn.metalearning.metafeatures.metafeatures.metafeatures.functions \
else "METAFEATURE"
_metafeatures_encoded_labels.metafeature_values[metafeature_name] = \
autosklearn.metalearning.metafeatures.metafeature.MetaFeatureValue(
metafeature_name, type_, 0, 0, np.NaN, np.NaN,
"Memory error during dataset scaling.")
mf = _metafeatures_labels
mf.metafeature_values.update(
_metafeatures_encoded_labels.metafeature_values)
mf.dump(mf_filename)
return mf
if __name__ == "__main__":
parser = ArgumentParser()
parser.add_argument("--output-dir", type=str, required=True)
parser.add_argument("--memory-limit", type=int, default=3072)
parser = data_manager_factory.populate_argparse_with_data_options(parser)
args = parser.parse_args()
D = data_manager_factory.get_data_manager(args, encode_labels=False)
mf = calculate_metafeatures(D, args.output_dir, args.memory_limit)
