def test_params_conflicting_with_sklearn_api_are_still_available():
pca = H2OPCA()
assert pca.transform != 'none'
assert callable(
pca.transform
), "`transform` method from sklearn API has been replaced by a property"
# conflicting param can be accessed normally using get_params()
print(pca.get_params())
assert pca.get_params()['transform'] == 'none'
# property is accessible directly using a trailing underscore
assert pca.transform_ == 'none'
pca = H2OPCA(transform='demean')
assert callable(
pca.transform
), "`transform` method from sklearn API has been replaced by a property"
assert pca.get_params()['transform'] == 'demean'
assert pca.transform_ == 'demean'
# conflicting param can be modified normally using set_params()
pca.set_params(transform='descale')
assert pca.get_params()['transform'] == 'descale'
assert pca.transform_ == 'descale'
# conflicting property can be set directly using a trailing underscore
pca.transform_ = 'normalize'
assert pca.get_params()['transform'] == 'normalize'
assert pca.transform_ == 'normalize'
def test_params_conflicting_with_sklearn_api_are_still_available():
pca = H2OPCA()
assert pca.transform != 'NONE'
assert callable(
pca.transform
), "`transform` method from sklearn API has been replaced by a property"
# conflicting param can be accessed normally using get_params()
assert pca.get_params()['transform'] == 'NONE'
# property is accessible directly using a trailing underscore
assert pca.transform_ == 'NONE'
pca = H2OPCA(transform='DEMEAN')
assert callable(
pca.transform
), "`transform` method from sklearn API has been replaced by a property"
assert pca.get_params()['transform'] == 'DEMEAN'
assert pca.transform_ == 'DEMEAN'
# conflicting param can be modified normally using set_params()
pca.set_params(transform='DESCALE')
assert pca.get_params()['transform'] == 'DESCALE'
assert pca.transform_ == 'DESCALE'
# conflicting property can be set directly using a trailing underscore
pca.transform_ = 'NORMALIZE'
assert pca.get_params()['transform'] == 'NORMALIZE'
assert pca.transform_ == 'NORMALIZE'
def test_params_are_correctly_passed_to_underlying_transformer():
pca = H2OPCA(seed=seed)
pca.set_params(transform='demean', k=3)
pca.model_id = "dummy"
assert pca.estimator is None
pca._make_estimator() # normally done when calling `fit`
assert pca.estimator
parms = pca.estimator._parms
assert parms['seed'] == seed
assert parms['transform'] == 'demean'
assert parms['k'] == 3
assert parms['model_id'] == "dummy"
assert parms['max_iterations'] 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_h2o_only_pipeline_with_h2o_frames():
pipeline = Pipeline([('standardize', H2OScaler()),
('pca', H2OPCA(k=2, seed=seed)),
('estimator', H2OGradientBoostingRegressor(seed=seed))
])
data = _get_data(format='h2o')
assert isinstance(data.X_train, h2o.H2OFrame)
pipeline.fit(data.X_train, data.y_train)
preds = pipeline.predict(data.X_test)
assert isinstance(preds, h2o.H2OFrame)
assert preds.dim == [len(data.X_test), 1]
# to get it working, we need to score a fresh H2OFrame
data = _get_data(format='h2o')
score = pipeline.score(data.X_test, data.y_test)
assert isinstance(score, float)
skl_score = r2_score(data.y_test.as_data_frame().values,
preds.as_data_frame().values)
assert abs(score - skl_score) < 1e-6, "score={}, skl_score={}".format(
score, skl_score)
scores['h2o_only_pipeline_with_h2o_frame'] = score
def test_h2o_only_pipeline_with_numpy_arrays():
# 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.
# Also note that in this specific case mixing numpy inputs with a fully H2O pipeline,
# the last estimator requires the `data_conversion=True` param in order to return numpy arrays in predictions.
pipeline = Pipeline([
('standardize', H2OScaler(init_connection_args=init_connection_args)),
('pca', H2OPCA(k=2, seed=seed)),
('estimator',
H2OGradientBoostingRegressor(seed=seed, data_conversion=True))
])
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['h2o_only_pipeline_with_numpy_arrays'] = score