def _calculate_metafeatures(data_feat_type, data_info_task, basename,
metalearning_cnt, x_train, y_train, watcher,
logger):
# == Calculate metafeatures
task_name = 'CalculateMetafeatures'
watcher.start_task(task_name)
categorical = [
True if feat_type.lower() in ['categorical'] else False
for feat_type in data_feat_type
]
if metalearning_cnt <= 0:
result = None
elif data_info_task in \
[MULTICLASS_CLASSIFICATION, BINARY_CLASSIFICATION, MULTILABEL_CLASSIFICATION]:
logger.info('Start calculating metafeatures for %s' % basename)
result = calc_meta_features(x_train,
y_train,
categorical=categorical,
dataset_name=basename)
else:
result = None
logger.info('Metafeatures not calculated')
watcher.stop_task(task_name)
logger.info(
'Calculating Metafeatures (categorical attributes) took %5.2f' %
watcher.wall_elapsed(task_name))
return result
def test_metalearning(self):
dataset_name = 'digits'
initial_challengers = {
ACC_METRIC: "--initial-challengers \" "
"-balancing:strategy 'weighting' "
"-classifier:__choice__ 'proj_logit'",
AUC_METRIC: "--initial-challengers \" "
"-balancing:strategy 'none' "
"-classifier:__choice__ 'random_forest'",
BAC_METRIC: "--initial-challengers \" "
"-balancing:strategy 'weighting' "
"-classifier:__choice__ 'proj_logit'",
F1_METRIC: "--initial-challengers \" "
"-balancing:strategy 'weighting' "
"-classifier:__choice__ 'proj_logit'",
PAC_METRIC: "--initial-challengers \" "
"-balancing:strategy 'none' "
"-classifier:__choice__ 'random_forest'"
}
for metric in initial_challengers:
configuration_space = get_configuration_space(
{
'metric': metric,
'task': MULTICLASS_CLASSIFICATION,
'is_sparse': False
},
include_preprocessors=['no_preprocessing'])
X_train, Y_train, X_test, Y_test = get_dataset(dataset_name)
categorical = [False] * X_train.shape[1]
meta_features_label = calc_meta_features(X_train, Y_train,
categorical, dataset_name)
meta_features_encoded_label = calc_meta_features_encoded(X_train,
Y_train,
categorical,
dataset_name)
initial_configuration_strings_for_smac = \
create_metalearning_string_for_smac_call(
meta_features_label,
meta_features_encoded_label,
configuration_space, dataset_name, metric,
MULTICLASS_CLASSIFICATION, False, 1, None)
print(metric)
print(initial_configuration_strings_for_smac[0])
self.assertTrue(initial_configuration_strings_for_smac[
0].startswith(initial_challengers[metric]))
def test_metalearning(self):
dataset_name = 'digits'
initial_challengers = {
ACC_METRIC: "--initial-challengers \" "
"-balancing:strategy 'weighting' "
"-classifier:__choice__ 'proj_logit'",
AUC_METRIC: "--initial-challengers \" "
"-balancing:strategy 'none' "
"-classifier:__choice__ 'random_forest'",
BAC_METRIC: "--initial-challengers \" "
"-balancing:strategy 'weighting' "
"-classifier:__choice__ 'proj_logit'",
F1_METRIC: "--initial-challengers \" "
"-balancing:strategy 'weighting' "
"-classifier:__choice__ 'proj_logit'",
PAC_METRIC: "--initial-challengers \" "
"-balancing:strategy 'none' "
"-classifier:__choice__ 'random_forest'"
}
for metric in initial_challengers:
configuration_space = get_configuration_space(
{
'metric': metric,
'task': MULTICLASS_CLASSIFICATION,
'is_sparse': False
},
include_preprocessors=['no_preprocessing'])
X_train, Y_train, X_test, Y_test = get_dataset(dataset_name)
categorical = [False] * X_train.shape[1]
meta_features_label = calc_meta_features(X_train, Y_train,
categorical, dataset_name)
meta_features_encoded_label = calc_meta_features_encoded(X_train,
Y_train,
categorical,
dataset_name)
initial_configuration_strings_for_smac = \
create_metalearning_string_for_smac_call(
meta_features_label,
meta_features_encoded_label,
configuration_space, dataset_name, metric,
MULTICLASS_CLASSIFICATION, False, 1, None)
print(metric)
print(initial_configuration_strings_for_smac[0])
self.assertTrue(initial_configuration_strings_for_smac[
0].startswith(initial_challengers[metric]))
def _calculate_metafeatures(
data_feat_type, data_info_task, basename, metalearning_cnt, x_train, y_train, watcher, logger
):
# == Calculate metafeatures
task_name = "CalculateMetafeatures"
watcher.start_task(task_name)
categorical = [True if feat_type.lower() in ["categorical"] else False for feat_type in data_feat_type]
if metalearning_cnt <= 0:
result = None
elif data_info_task in [MULTICLASS_CLASSIFICATION, BINARY_CLASSIFICATION, MULTILABEL_CLASSIFICATION]:
logger.info("Start calculating metafeatures for %s" % basename)
result = calc_meta_features(x_train, y_train, categorical=categorical, dataset_name=basename)
else:
result = None
logger.info("Metafeatures not calculated")
watcher.stop_task(task_name)
logger.info("Calculating Metafeatures (categorical attributes) took %5.2f" % watcher.wall_elapsed(task_name))
return result