def _calculate_meta_features(data_feat_type, data_info_task, basename,
metalearning_cnt, x_train, y_train, watcher,
log_function):
# == 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 and data_info_task in \
[MULTICLASS_CLASSIFICATION, BINARY_CLASSIFICATION]:
log_function('Start calculating metafeatures for %s' % basename)
result = calc_meta_features(x_train,
y_train,
categorical=categorical,
dataset_name=basename)
else:
result = None
log_function('Metafeatures not calculated')
watcher.stop_task(task_name)
log_function(
'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 \" "
"-adaboost:algorithm 'SAMME.R' "
"-adaboost:learning_rate '0.400363929326' "
"-adaboost:max_depth '5' "
"-adaboost:n_estimators '319' "
"-balancing:strategy 'none' "
"-classifier 'adaboost' "
"-imputation:strategy 'most_frequent' "
"-preprocessor 'no_preprocessing' "
"-rescaling:strategy 'min/max'\""],
'auc_metric': ["--initial-challengers \" "
"-adaboost:algorithm 'SAMME.R' "
"-adaboost:learning_rate '0.966883114819' "
"-adaboost:max_depth '5' "
"-adaboost:n_estimators '412' "
"-balancing:strategy 'weighting' "
"-classifier 'adaboost' "
"-imputation:strategy 'median' "
"-preprocessor 'no_preprocessing' "
"-rescaling:strategy 'min/max'\""],
'bac_metric': ["--initial-challengers \" "
"-adaboost:algorithm 'SAMME.R' "
"-adaboost:learning_rate '0.400363929326' "
"-adaboost:max_depth '5' "
"-adaboost:n_estimators '319' "
"-balancing:strategy 'none' "
"-classifier 'adaboost' "
"-imputation:strategy 'most_frequent' "
"-preprocessor 'no_preprocessing' "
"-rescaling:strategy 'min/max'\""],
'f1_metric': ["--initial-challengers \" "
"-adaboost:algorithm 'SAMME.R' "
"-adaboost:learning_rate '0.966883114819' "
"-adaboost:max_depth '5' "
"-adaboost:n_estimators '412' "
"-balancing:strategy 'weighting' "
"-classifier 'adaboost' "
"-imputation:strategy 'median' "
"-preprocessor 'no_preprocessing' "
"-rescaling:strategy 'min/max'\""],
'pac_metric': ["--initial-challengers \" "
"-adaboost:algorithm 'SAMME.R' "
"-adaboost:learning_rate '0.400363929326' "
"-adaboost:max_depth '5' "
"-adaboost:n_estimators '319' "
"-balancing:strategy 'none' "
"-classifier 'adaboost' "
"-imputation:strategy 'most_frequent' "
"-preprocessor 'no_preprocessing' "
"-rescaling:strategy 'min/max'\""]
}
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)
self.assertEqual(initial_challengers[metric],
initial_configuration_strings_for_smac)
