def test_generic_estimator_with_distribution_param():
# Note that in normal situations (release build), init_connection_args can be omitted
# otherwise, it should be set to the first H2O element in the pipeline
pipeline = Pipeline([('svd', TruncatedSVD(n_components=3,
random_state=seed)),
('estimator',
H2OGradientBoostingEstimator(
distribution='bernoulli',
seed=seed,
init_connection_args=init_connection_args))])
data = _get_data(format='numpy')
assert isinstance(data.X_train, np.ndarray)
pipeline.fit(data.X_train, data.y_train)
preds = pipeline.predict(data.X_test)
assert isinstance(preds, np.ndarray)
assert preds.shape == (len(data.X_test), )
probs = pipeline.predict_proba(data.X_test)
assert probs.shape == (len(data.X_test), 2)
assert np.allclose(np.sum(probs, axis=1),
1.), "`predict_proba` didn't return probabilities"
score = pipeline.score(data.X_test, data.y_test)
assert isinstance(score, float)
skl_score = accuracy_score(data.y_test, preds)
assert abs(score - skl_score) < 1e-6
scores['generic_estimator_with_distribution_param'] = score
def test_params_are_correctly_passed_to_underlying_estimator():
estimator = H2OGradientBoostingEstimator(seed=seed)
estimator.set_params(max_depth=10, learn_rate=0.5)
estimator.model_id = "dummy"
assert estimator.estimator is None
estimator._make_estimator() # normally done when calling `fit`
real_estimator = estimator.estimator
assert real_estimator
parms = real_estimator._parms
assert real_estimator.seed == parms['seed'] == seed
assert real_estimator.max_depth == parms['max_depth'] == 10
assert real_estimator.learn_rate == parms['learn_rate'] == 0.5
assert real_estimator._id == parms['model_id'] == "dummy"
assert real_estimator.training_frame == parms['training_frame'] is None
def test_all_params_can_be_set_as_properties():
pipeline = Pipeline([('standardize', H2OScaler()), ('pca', H2OPCA()),
('estimator', H2OGradientBoostingEstimator())])
pipeline.named_steps.standardize.center = True
pipeline.named_steps.standardize.scale = False
pipeline.named_steps.pca.k = 2
pipeline.named_steps.pca.seed = seed
pipeline.named_steps.estimator.ntrees = 20
pipeline.named_steps.estimator.max_depth = 5
pipeline.named_steps.estimator.seed = seed
params = pipeline.get_params()
assert isinstance(params['standardize'], H2OScaler)
assert params['standardize__center'] is True
assert params['standardize__scale'] is False
assert isinstance(params['pca'], H2OPCA)
assert params['pca__k'] == 2
assert params['pca__seed'] == seed
assert isinstance(params['estimator'], H2OGradientBoostingEstimator)
assert params['estimator__ntrees'] == 20
assert params['estimator__max_depth'] == 5
assert params['estimator__seed'] == seed
def test_all_params_can_be_set_using_set_params():
pipeline = Pipeline([('standardize', H2OScaler()), ('pca', H2OPCA()),
('estimator', H2OGradientBoostingEstimator())])
pipeline.set_params(standardize__center=True,
standardize__scale=False,
pca__k=2,
pca__seed=seed,
estimator__ntrees=20,
estimator__max_depth=5,
estimator__seed=seed)
assert isinstance(pipeline.named_steps.standardize, H2OScaler)
assert pipeline.named_steps.standardize.center is True
assert pipeline.named_steps.standardize.scale is False
assert isinstance(pipeline.named_steps.pca, H2OPCA)
assert pipeline.named_steps.pca.k == 2
assert pipeline.named_steps.pca.seed == seed
assert isinstance(pipeline.named_steps.estimator,
H2OGradientBoostingEstimator)
assert pipeline.named_steps.estimator.ntrees == 20
assert pipeline.named_steps.estimator.max_depth == 5
assert pipeline.named_steps.estimator.seed == seed
def test_all_params_are_accessible_as_properties():
pipeline = Pipeline([('standardize', H2OScaler(center=True, scale=False)),
('pca', H2OPCA(k=2, seed=seed)),
('estimator',
H2OGradientBoostingEstimator(ntrees=20,
max_depth=5,
seed=seed))])
assert isinstance(pipeline.named_steps.standardize, H2OScaler)
assert pipeline.named_steps.standardize.center is True
assert pipeline.named_steps.standardize.scale is False
assert isinstance(pipeline.named_steps.pca, H2OPCA)
assert pipeline.named_steps.pca.k == 2
assert pipeline.named_steps.pca.seed == seed
assert isinstance(pipeline.named_steps.estimator,
H2OGradientBoostingEstimator)
assert pipeline.named_steps.estimator.ntrees == 20
assert pipeline.named_steps.estimator.max_depth == 5
assert pipeline.named_steps.estimator.seed == seed
# also the ones that were not set explicitly
assert pipeline.named_steps.pca.max_iterations is None
assert pipeline.named_steps.estimator.learn_rate is None
def test_all_params_are_visible_in_get_params():
pipeline = Pipeline([('standardize', H2OScaler(center=True, scale=False)),
('pca', H2OPCA(k=2, seed=seed)),
('estimator',
H2OGradientBoostingEstimator(ntrees=20,
max_depth=5,
seed=seed))])
params = pipeline.get_params()
assert isinstance(params['standardize'], H2OScaler)
assert params['standardize__center'] is True
assert params['standardize__scale'] is False
assert isinstance(params['pca'], H2OPCA)
assert params['pca__k'] == 2
assert params['pca__seed'] == seed
assert isinstance(params['estimator'], H2OGradientBoostingEstimator)
assert params['estimator__ntrees'] == 20
assert params['estimator__max_depth'] == 5
assert params['estimator__seed'] == seed
# also the ones that were not set explicitly
assert params['pca__max_iterations'] is None
assert params['estimator__learn_rate'] is None
def test_generic_estimator_with_distribution_param():
# Note that in normal situations (release build), init_connection_args can be omitted
# otherwise, it should be set to the first H2O element in the pipeline
pipeline = Pipeline([('standardize', StandardScaler()),
('pca', PCA(n_components=2, random_state=seed)),
('estimator',
H2OGradientBoostingEstimator(
distribution='gaussian',
seed=seed,
init_connection_args=init_connection_args))])
data = _get_data(format='numpy')
assert isinstance(data.X_train, np.ndarray)
pipeline.fit(data.X_train, data.y_train)
preds = pipeline.predict(data.X_test)
assert isinstance(preds, np.ndarray)
assert preds.shape == (len(data.X_test), )
score = pipeline.score(data.X_test, data.y_test)
assert isinstance(score, float)
skl_score = r2_score(data.y_test, preds)
assert abs(score - skl_score) < 1e-6
scores['generic_estimator_with_distribution_param'] = score