def get_data(data_id, randomstate=42):
dataset = openml.datasets.get_dataset(dataset_id=data_id)
X, y, categorical_indicator, attribute_names = dataset.get_data(
dataset_format="array", target=dataset.default_target_attribute)
X_train, X_test, y_train, y_test = sklearn.model_selection.train_test_split(
X, y, random_state=randomstate, stratify=y, train_size=0.6)
calculate_all_metafeatures_with_labels(X_train,
y_train,
categorical=categorical_indicator,
dataset_name='data')
def _calculate_metafeatures(data_feat_type, data_info_task, basename,
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]
EXCLUDE_META_FEATURES = EXCLUDE_META_FEATURES_CLASSIFICATION \
if data_info_task in CLASSIFICATION_TASKS else EXCLUDE_META_FEATURES_REGRESSION
if data_info_task in [MULTICLASS_CLASSIFICATION, BINARY_CLASSIFICATION,
MULTILABEL_CLASSIFICATION, REGRESSION]:
logger.info('Start calculating metafeatures for %s', basename)
result = calculate_all_metafeatures_with_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]
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 _calculate_metafeatures__(data_feat_type, data_info_task, basename,
x_train, y_train):
# == Calculate metafeatures
task_name = 'CalculateMetafeatures'
categorical = [
True if feat_type.lower() in ['categorical'] else False
for feat_type in data_feat_type
]
EXCLUDE_META_FEATURES = EXCLUDE_META_FEATURES_CLASSIFICATION \
if data_info_task in CLASSIFICATION_TASKS else EXCLUDE_META_FEATURES_REGRESSION
if data_info_task in [
MULTICLASS_CLASSIFICATION, BINARY_CLASSIFICATION,
MULTILABEL_CLASSIFICATION, REGRESSION
]:
result = calculate_all_metafeatures_with_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]
else:
result = None
return result
def _calculate_metafeatures(data_feat_type, data_info_task, basename,
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]
EXCLUDE_META_FEATURES = EXCLUDE_META_FEATURES_CLASSIFICATION \
if data_info_task in CLASSIFICATION_TASKS else EXCLUDE_META_FEATURES_REGRESSION
if data_info_task in [MULTICLASS_CLASSIFICATION, BINARY_CLASSIFICATION,
MULTILABEL_CLASSIFICATION, REGRESSION]:
logger.info('Start calculating metafeatures for %s', basename)
result = calculate_all_metafeatures_with_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]
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 data2features(X_train, y_train, categorical_indicator):
metafeatures = calculate_all_metafeatures_with_labels(X_train, y_train, categorical=categorical_indicator,
dataset_name='data')
metafeature_values = np.zeros((1, len(metafeature_names_new)))
for m_i in range(len(metafeature_names_new)):
try:
metafeature_values[0, m_i] = metafeatures[metafeature_names_new[m_i]].value
except:
pass
return metafeature_values
def calc_meta_features(X_train, Y_train, categorical, dataset_name):
"""
Calculate meta features with label
:param X_train:
:param Y_train:
:param categorical:
:param dataset_name:
:return:
"""
return calculate_all_metafeatures_with_labels(
X_train, Y_train, categorical, dataset_name + SENTINEL,
dont_calculate=EXCLUDE_META_FUTURES)
def calc_meta_features(X_train, Y_train, categorical, dataset_name):
"""
Calculate meta features with label
:param X_train:
:param Y_train:
:param categorical:
:param dataset_name:
:return:
"""
return calculate_all_metafeatures_with_labels(
X_train,
Y_train,
categorical,
dataset_name + SENTINEL,
dont_calculate=EXCLUDE_META_FUTURES)
def calculate_metafeatures(task_id):
print(task_id)
X_train, y_train, X_test, y_test, cat = load_task(task_id)
categorical = [True if 'categorical' == c else False for c in cat]
_metafeatures_labels = metafeatures.calculate_all_metafeatures_with_labels(
X_train, y_train, [False] * X_train.shape[1], task_id)
X_train, sparse = perform_one_hot_encoding(scipy.sparse.issparse(X_train),
categorical, [X_train])
X_train = X_train[0]
categorical = [False] * X_train.shape[1]
start_time = time.time()
obj = pynisher.enforce_limits(mem_in_mb=3072)(
metafeatures.calculate_all_metafeatures_encoded_labels)
_metafeatures_encoded_labels = obj(X_train, y_train, categorical, task_id)
end_time = time.time()
if obj.exit_status == pynisher.MemorylimitException:
# During the conversion of the dataset (rescaling, etc...), it can
# happen that we run out of memory.
_metafeatures_encoded_labels = \
metafeature.DatasetMetafeatures(task_id, dict())
metafeature_calculation_time = (end_time - start_time) / \
len(metafeatures.npy_metafeatures)
for metafeature_name in metafeatures.npy_metafeatures:
type_ = "HELPERFUNCTION" if metafeature_name not in \
metafeatures.metafeatures.functions \
else "METAFEATURE"
_metafeatures_encoded_labels.metafeature_values[metafeature_name] = \
metafeature.MetaFeatureValue(metafeature_name, type_, 0, 0,
np.NaN, metafeature_calculation_time,
"Memory error during dataset scaling.")
mf = _metafeatures_labels
mf.metafeature_values.update(
_metafeatures_encoded_labels.metafeature_values)
return mf
def calculate_metafeatures(profile, basename, x_train, y_train):
is_class = profile.has_categorical_target()
pf = profile.get_raw_profile()
categorical = pf.loc[~pf['drop'] & ~pf['target'] & ~(pf['col_type'] == 'datetime'), 'is_cat'].values
if is_class:
EXCLUDE_META_FEATURES = EXCLUDE_META_FEATURES_CLASSIFICATION
else:
EXCLUDE_META_FEATURES = EXCLUDE_META_FEATURES_REGRESSION
logger.info('Start calculating metafeatures')
result = calculate_all_metafeatures_with_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]
return result
def calculate_metafeatures(self, data_manager, dataset_name):
"""
A function to calculate the dataset's meta features
internally called Auto-SKLearn's caclulate_all_metafeatures_with_labels()
and stores the returned DatasetMetaFeatures Object
"""
categorical = [
True if feat_type.lower() in ['categorical'] else False
for feat_type in data_manager.feat_type
]
EXCLUDE_META_FEATURES = EXCLUDE_META_FEATURES_CLASSIFICATION \
if data_manager.info['task'] in ask_const.CLASSIFICATION_TASKS else EXCLUDE_META_FEATURES_REGRESSION
if data_manager.info['task'] in [
ask_const.MULTICLASS_CLASSIFICATION,
ask_const.BINARY_CLASSIFICATION,
ask_const.MULTILABEL_CLASSIFICATION, ask_const.REGRESSION
]:
result = calculate_all_metafeatures_with_labels(
data_manager.data['X_train'],
data_manager.data['Y_train'],
categorical=categorical,
dataset_name=dataset_name,
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]
else:
result = None
return result
res = suggest_via_metalearning(meta_base,'198_a_metric',metric,task,False,1)
print(res)
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]