def test_configured(self):
X_train, X_test, y_train, y_test, feature_names = self.load_data(
multiclass=False)
actual = GradientBoostingClassifier(random_state=42)
config = self.get_config(actual)
actual.set_hyperparameters(config)
actual.fit(X_train, y_train)
y_actual = actual.predict(X_test)
config['max_depth'] = max(
resolve_factor(config['max_depth_factor'], X_train.shape[1]), 2)
del config['max_depth_factor']
config['max_leaf_nodes'] = max(
resolve_factor(config['max_leaf_nodes_factor'], X_train.shape[0]),
2)
del config['max_leaf_nodes_factor']
config['min_samples_leaf'] = resolve_factor(
config['min_samples_leaf_factor'], X_train.shape[0])
del config['min_samples_leaf_factor']
expected = HistGradientBoostingClassifier(**config,
scoring='f1_weighted',
random_state=42)
expected.fit(X_train, y_train)
y_expected = expected.predict(X_test)
assert actual.get_feature_names_out(feature_names).tolist() == [
'prediction'
]
assert repr(actual.estimator_) == repr(expected)
assert np.allclose(y_actual, y_expected)
def _run_GB_trees_classifier_converter(self, num_classes, extra_config={}, labels_shift=0):
warnings.filterwarnings("ignore")
for max_depth in [2, 3, 8, 10, 12, None]:
model = HistGradientBoostingClassifier(max_iter=10, max_depth=max_depth)
X = [[0, 1], [1, 1], [2, 0]]
X = np.array(X, dtype=np.float32)
y = np.array([100, -10, 50]) + labels_shift
model.fit(X, y)
pytorch_model = hummingbird.ml.convert(model, "pytorch", extra_config=extra_config)
self.assertTrue(pytorch_model is not None)
np.testing.assert_allclose(model.predict_proba(X), pytorch_model.predict_proba(X), rtol=1e-06, atol=1e-06)
def test_float64_GB_trees_classifier_converter(self):
warnings.filterwarnings("ignore")
num_classes = 3
for max_depth in [2, 3, 8, 10, 12, None]:
model = HistGradientBoostingClassifier(max_iter=10, max_depth=max_depth)
np.random.seed(0)
X = np.random.rand(100, 200)
y = np.random.randint(num_classes, size=100)
model.fit(X, y)
torch_model = hummingbird.ml.convert(model, "torch", extra_config={})
self.assertTrue(torch_model is not None)
np.testing.assert_allclose(model.predict_proba(X), torch_model.predict_proba(X), rtol=1e-06, atol=1e-06)
def _run_GB_trees_classifier_converter(self, num_classes, extra_config={}, labels_shift=0):
warnings.filterwarnings("ignore")
for max_depth in [2, 3, 8, 10, 12, None]:
model = HistGradientBoostingClassifier(max_iter=10, max_depth=max_depth)
np.random.seed(0)
X = np.random.rand(100, 200)
X = np.array(X, dtype=np.float32)
y = np.random.randint(num_classes, size=100) + labels_shift
model.fit(X, y)
torch_model = hummingbird.ml.convert(model, "torch", extra_config=extra_config)
self.assertTrue(torch_model is not None)
np.testing.assert_allclose(model.predict_proba(X), torch_model.predict_proba(X), rtol=1e-06, atol=1e-06)
def test_default(self):
X_train, X_test, y_train, y_test, feature_names = self.load_data()
actual = GradientBoostingClassifier(random_state=42)
config = self.get_default(actual)
actual.set_hyperparameters(config)
actual.fit(X_train, y_train)
y_actual = actual.predict(X_test)
expected = HistGradientBoostingClassifier(n_iter_no_change=10,
l2_regularization=1e-10,
scoring='f1_weighted',
random_state=42)
expected.fit(X_train, y_train)
y_expected = expected.predict(X_test)
assert actual.get_feature_names_out(feature_names).tolist() == [
'prediction'
]
assert repr(actual.estimator_) == repr(expected)
assert np.allclose(y_actual, y_expected)