def testEntireEnsembleBuilder(ensemble_backend):
ensbuilder = EnsembleBuilder(
backend=ensemble_backend,
dataset_name="TEST",
task_type=BINARY_CLASSIFICATION,
metric=roc_auc,
seed=0, # important to find the test files
ensemble_nbest=2,
)
ensbuilder.SAVE2DISC = False
ensbuilder.compute_loss_per_model()
d2 = os.path.join(
ensemble_backend.temporary_directory,
".auto-sklearn/runs/0_2_0.0/predictions_ensemble_0_2_0.0.npy")
sel_keys = ensbuilder.get_n_best_preds()
assert len(sel_keys) > 0
ensemble = ensbuilder.fit_ensemble(selected_keys=sel_keys)
print(ensemble, sel_keys)
n_sel_valid, n_sel_test = ensbuilder.get_valid_test_preds(
selected_keys=sel_keys)
# both valid and test prediction files are available
assert len(n_sel_valid) > 0
assert n_sel_valid == n_sel_test
y_valid = ensbuilder.predict(
set_="valid",
ensemble=ensemble,
selected_keys=n_sel_valid,
n_preds=len(sel_keys),
index_run=1,
)
y_test = ensbuilder.predict(
set_="test",
ensemble=ensemble,
selected_keys=n_sel_test,
n_preds=len(sel_keys),
index_run=1,
)
# predictions for valid and test are the same
# --> should results in the same predictions
np.testing.assert_array_almost_equal(y_valid, y_test)
# since d2 provides perfect predictions
# it should get a higher weight
# so that y_valid should be exactly y_valid_d2
y_valid_d2 = ensbuilder.read_preds[d2][Y_VALID][:, 1]
np.testing.assert_array_almost_equal(y_valid, y_valid_d2)
def testMaxModelsOnDisc(ensemble_backend, test_case, exp):
ensemble_nbest = 4
ensbuilder = EnsembleBuilder(
backend=ensemble_backend,
dataset_name="TEST",
task_type=BINARY_CLASSIFICATION,
metric=roc_auc,
seed=0, # important to find the test files
ensemble_nbest=ensemble_nbest,
max_models_on_disc=test_case,
)
with unittest.mock.patch('os.path.getsize') as mock:
mock.return_value = 100 * 1024 * 1024
ensbuilder.compute_loss_per_model()
sel_keys = ensbuilder.get_n_best_preds()
assert len(sel_keys) == exp, test_case
def testGetValidTestPreds(ensemble_backend):
ensbuilder = EnsembleBuilder(
backend=ensemble_backend,
dataset_name="TEST",
task_type=BINARY_CLASSIFICATION,
metric=roc_auc,
seed=0, # important to find the test files
ensemble_nbest=1)
ensbuilder.compute_loss_per_model()
# d1 is a dummt prediction. d2 and d3 have the same prediction with
# different name. num_run=2 is selected when doing sorted()
d1 = os.path.join(
ensemble_backend.temporary_directory,
".auto-sklearn/runs/0_1_0.0/predictions_ensemble_0_1_0.0.npy")
d2 = os.path.join(
ensemble_backend.temporary_directory,
".auto-sklearn/runs/0_2_0.0/predictions_ensemble_0_2_0.0.npy")
d3 = os.path.join(
ensemble_backend.temporary_directory,
".auto-sklearn/runs/0_3_100.0/predictions_ensemble_0_3_100.0.npy")
sel_keys = ensbuilder.get_n_best_preds()
assert len(sel_keys) == 1
ensbuilder.get_valid_test_preds(selected_keys=sel_keys)
# Number of read files should be three and
# predictions_ensemble_0_4_0.0.npy must not be in there
assert len(ensbuilder.read_preds) == 3
assert os.path.join(
ensemble_backend.temporary_directory,
".auto-sklearn/runs/0_4_0.0/predictions_ensemble_0_4_0.0.npy"
) not in ensbuilder.read_preds
# not selected --> should still be None
assert ensbuilder.read_preds[d1][Y_VALID] is None
assert ensbuilder.read_preds[d1][Y_TEST] is None
assert ensbuilder.read_preds[d3][Y_VALID] is None
assert ensbuilder.read_preds[d3][Y_TEST] is None
# selected --> read valid and test predictions
assert ensbuilder.read_preds[d2][Y_VALID] is not None
assert ensbuilder.read_preds[d2][Y_TEST] is not None
def testNBest(ensemble_backend, ensemble_nbest, max_models_on_disc, exp):
ensbuilder = EnsembleBuilder(
backend=ensemble_backend,
dataset_name="TEST",
task_type=BINARY_CLASSIFICATION,
metric=roc_auc,
seed=0, # important to find the test files
ensemble_nbest=ensemble_nbest,
max_models_on_disc=max_models_on_disc,
)
ensbuilder.compute_loss_per_model()
sel_keys = ensbuilder.get_n_best_preds()
assert len(sel_keys) == exp
fixture = os.path.join(
ensemble_backend.temporary_directory,
".auto-sklearn/runs/0_2_0.0/predictions_ensemble_0_2_0.0.npy")
assert sel_keys[0] == fixture
def testFallBackNBest(ensemble_backend):
ensbuilder = EnsembleBuilder(
backend=ensemble_backend,
dataset_name="TEST",
task_type=BINARY_CLASSIFICATION,
metric=roc_auc,
seed=0, # important to find the test files
ensemble_nbest=1)
ensbuilder.compute_loss_per_model()
print()
print(ensbuilder.read_preds.keys())
print(ensbuilder.read_losses.keys())
print(ensemble_backend.temporary_directory)
filename = os.path.join(
ensemble_backend.temporary_directory,
".auto-sklearn/runs/0_2_0.0/predictions_ensemble_0_2_0.0.npy")
ensbuilder.read_losses[filename]["ens_loss"] = -1
filename = os.path.join(
ensemble_backend.temporary_directory,
".auto-sklearn/runs/0_3_100.0/predictions_ensemble_0_3_100.0.npy")
ensbuilder.read_losses[filename]["ens_loss"] = -1
filename = os.path.join(
ensemble_backend.temporary_directory,
".auto-sklearn/runs/0_1_0.0/predictions_ensemble_0_1_0.0.npy")
ensbuilder.read_losses[filename]["ens_loss"] = -1
sel_keys = ensbuilder.get_n_best_preds()
fixture = os.path.join(
ensemble_backend.temporary_directory,
".auto-sklearn/runs/0_1_0.0/predictions_ensemble_0_1_0.0.npy")
assert len(sel_keys) == 1
assert sel_keys[0] == fixture
def testRead(ensemble_backend):
ensbuilder = EnsembleBuilder(
backend=ensemble_backend,
dataset_name="TEST",
task_type=BINARY_CLASSIFICATION,
metric=roc_auc,
seed=0, # important to find the test files
)
success = ensbuilder.compute_loss_per_model()
assert success, str(ensbuilder.read_preds)
assert len(ensbuilder.read_preds) == 3, ensbuilder.read_preds.keys()
assert len(ensbuilder.read_losses) == 3, ensbuilder.read_losses.keys()
filename = os.path.join(
ensemble_backend.temporary_directory,
".auto-sklearn/runs/0_1_0.0/predictions_ensemble_0_1_0.0.npy")
assert ensbuilder.read_losses[filename]["ens_loss"] == 0.5
filename = os.path.join(
ensemble_backend.temporary_directory,
".auto-sklearn/runs/0_2_0.0/predictions_ensemble_0_2_0.0.npy")
assert ensbuilder.read_losses[filename]["ens_loss"] == 0.0