def test_5000_classes(self):
weights = ([0.0002] * 4750) + ([0.0001] * 250)
X, Y = sklearn.datasets.make_classification(
n_samples=10000,
n_features=20,
n_classes=5000,
n_clusters_per_class=1,
n_informative=15,
n_redundant=5,
n_repeated=0,
weights=weights,
flip_y=0,
class_sep=1.0,
hypercube=True,
shift=None,
scale=1.0,
shuffle=True,
random_state=1,
)
self.assertEqual(250, np.sum(np.bincount(Y) == 1))
D = Dummy()
D.info = {"metric": ACC_METRIC, "task": MULTICLASS_CLASSIFICATION, "is_sparse": False, "label_num": 1}
D.data = {"X_train": X, "Y_train": Y, "X_valid": X, "X_test": X}
D.feat_type = ["numerical"] * 5000
configuration_space = get_configuration_space(
D.info, include_estimators=["lda"], include_preprocessors=["no_preprocessing"]
)
configuration = configuration_space.sample_configuration()
D_ = copy.deepcopy(D)
evaluator = HoldoutEvaluator(D_, configuration)
evaluator.fit()
def test_5000_classes(self):
weights = ([0.0002] * 4750) + ([0.0001] * 250)
X, Y = sklearn.datasets.make_classification(n_samples=10000,
n_features=20,
n_classes=5000,
n_clusters_per_class=1,
n_informative=15,
n_redundant=5,
n_repeated=0,
weights=weights,
flip_y=0,
class_sep=1.0,
hypercube=True,
shift=None,
scale=1.0,
shuffle=True,
random_state=1)
self.assertEqual(250, np.sum(np.bincount(Y) == 1))
D = Dummy()
D.info = {
'metric': ACC_METRIC,
'task': MULTICLASS_CLASSIFICATION,
'is_sparse': False,
'label_num': 1
}
D.data = {'X_train': X, 'Y_train': Y, 'X_valid': X, 'X_test': X}
D.feat_type = ['numerical'] * 5000
configuration_space = get_configuration_space(
D.info,
include_estimators=['lda'],
include_preprocessors=['no_preprocessing'])
configuration = configuration_space.sample_configuration()
D_ = copy.deepcopy(D)
evaluator = HoldoutEvaluator(D_, configuration)
evaluator.fit()
