def _calculate_metafeatures_encoded(data_feat_type, basename, x_train, y_train,
watcher, task, logger):
EXCLUDE_META_FEATURES = EXCLUDE_META_FEATURES_CLASSIFICATION \
if task in CLASSIFICATION_TASKS else EXCLUDE_META_FEATURES_REGRESSION
task_name = 'CalculateMetafeaturesEncoded'
watcher.start_task(task_name)
categorical = [
True if feat_type.lower() in ['categorical'] else False
for feat_type in data_feat_type
]
result = calculate_all_metafeatures_encoded_labels(
x_train,
y_train,
categorical=categorical,
dataset_name=basename,
dont_calculate=EXCLUDE_META_FEATURES)
for key in list(result.metafeature_values.keys()):
if result.metafeature_values[key].type_ != 'METAFEATURE':
del result.metafeature_values[key]
watcher.stop_task(task_name)
logger.info('Calculating Metafeatures (encoded attributes) took %5.2fsec',
watcher.wall_elapsed(task_name))
return result
def _calculate_metafeatures_encoded(data_feat_type, basename, x_train, y_train,
watcher, task, logger_):
with warnings.catch_warnings():
warnings.showwarning = get_send_warnings_to_logger(logger_)
EXCLUDE_META_FEATURES = EXCLUDE_META_FEATURES_CLASSIFICATION \
if task in CLASSIFICATION_TASKS else EXCLUDE_META_FEATURES_REGRESSION
task_name = 'CalculateMetafeaturesEncoded'
watcher.start_task(task_name)
categorical = {
col: True if feat_type.lower() == 'categorical' else False
for col, feat_type in data_feat_type.items()
}
result = calculate_all_metafeatures_encoded_labels(
x_train,
y_train,
categorical=categorical,
dataset_name=basename,
dont_calculate=EXCLUDE_META_FEATURES,
logger=logger_)
for key in list(result.metafeature_values.keys()):
if result.metafeature_values[key].type_ != 'METAFEATURE':
del result.metafeature_values[key]
watcher.stop_task(task_name)
logger_.info(
'Calculating Metafeatures (encoded attributes) took %5.2fsec',
watcher.wall_elapsed(task_name))
return result
def calc_meta_features_encoded(X_train, Y_train, categorical, dataset_name):
"""
Calculate meta features with encoded labels
:param X_train:
:param Y_train:
:param categorical:
:param dataset_name:
:return:
"""
if np.sum(categorical) != 0:
raise ValueError("Training matrix doesn't look OneHotEncoded!")
return calculate_all_metafeatures_encoded_labels(
X_train, Y_train, categorical, dataset_name + SENTINEL,
dont_calculate=EXCLUDE_META_FUTURES)
def _calculate_metafeatures_encoded__(basename, x_train, y_train):
EXCLUDE_META_FEATURES = EXCLUDE_META_FEATURES_CLASSIFICATION \
if task in CLASSIFICATION_TASKS else EXCLUDE_META_FEATURES_REGRESSION
task_name = 'CalculateMetafeaturesEncoded'
result = calculate_all_metafeatures_encoded_labels(
x_train,
y_train,
categorical=[False] * x_train.shape[1],
dataset_name=basename,
dont_calculate=EXCLUDE_META_FEATURES)
for key in list(result.metafeature_values.keys()):
if result.metafeature_values[key].type_ != 'METAFEATURE':
del result.metafeature_values[key]
return result
def calc_meta_features_encoded(X_train, Y_train, categorical, dataset_name):
"""
Calculate meta features with encoded labels
:param X_train:
:param Y_train:
:param categorical:
:param dataset_name:
:return:
"""
if np.sum(categorical) != 0:
raise ValueError("Training matrix doesn't look OneHotEncoded!")
return calculate_all_metafeatures_encoded_labels(
X_train,
Y_train,
categorical,
dataset_name + SENTINEL,
dont_calculate=EXCLUDE_META_FUTURES)
def _calculate_metafeatures_encoded(basename, x_train, y_train, watcher,
task, logger):
EXCLUDE_META_FEATURES = EXCLUDE_META_FEATURES_CLASSIFICATION \
if task in CLASSIFICATION_TASKS else EXCLUDE_META_FEATURES_REGRESSION
task_name = 'CalculateMetafeaturesEncoded'
watcher.start_task(task_name)
result = calculate_all_metafeatures_encoded_labels(
x_train, y_train, categorical=[False] * x_train.shape[1],
dataset_name=basename, dont_calculate=EXCLUDE_META_FEATURES)
for key in list(result.metafeature_values.keys()):
if result.metafeature_values[key].type_ != 'METAFEATURE':
del result.metafeature_values[key]
watcher.stop_task(task_name)
logger.info(
'Calculating Metafeatures (encoded attributes) took %5.2fsec',
watcher.wall_elapsed(task_name))
return result
print(type(res))
print(len(res))
from autosklearn.metalearning.metafeatures.metafeatures import \
calculate_all_metafeatures_with_labels, \
calculate_all_metafeatures_encoded_labels, subsets
X_train, Y_train, X_test, Y_test = get_dataset(dataset_name)
print(Y_train)
categorical = [False] * X_train.shape[1]
meta_features_label = calculate_all_metafeatures_with_labels(
X_train, Y_train, categorical, dataset_name)
print(meta_features_label)
meta_features_encoded_label = calculate_all_metafeatures_encoded_labels(
X_train, Y_train, categorical, dataset_name)
print(meta_features_encoded_label)
#configuration_space = get_configuration_space(
# {
# 'metric': metric,
# 'task': task,
# '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]
#categorical = [False] * X_train.shape[1]
#meta_features_label = calc_meta_features(X_train, y_train, categorical, 'a', REGRESSION)
#meta_features_encoded_label = calc_meta_features_encoded(X_train, y_train, categorical, 'b', task)
