def test_XGBClassifier_resume(self): self._init_ray() from sklearn.datasets import load_breast_cancer from sklearn.metrics import log_loss with TemporaryDirectory() as tempdir: model1_path = os.path.join(tempdir, "test_XGBClassifier.model") model1_booster_path = os.path.join(tempdir, "test_XGBClassifier.booster") X, Y = load_breast_cancer(return_X_y=True) model1 = RayXGBClassifier( learning_rate=0.3, random_state=0, n_estimators=8) model1.fit(X, Y) pred1 = model1.predict(X) log_loss1 = log_loss(pred1, Y) # file name of stored xgb model model1.save_model(model1_path) model2 = RayXGBClassifier( learning_rate=0.3, random_state=0, n_estimators=8) model2.fit(X, Y, xgb_model=model1_path) pred2 = model2.predict(X) log_loss2 = log_loss(pred2, Y) assert np.any(pred1 != pred2) assert log_loss1 > log_loss2 # file name of 'Booster' instance Xgb model model1.get_booster().save_model(model1_booster_path) model2 = RayXGBClassifier( learning_rate=0.3, random_state=0, n_estimators=8) model2.fit(X, Y, xgb_model=model1_booster_path) pred2 = model2.predict(X) log_loss2 = log_loss(pred2, Y) assert np.any(pred1 != pred2) assert log_loss1 > log_loss2
def test_estimator_type(self): self._init_ray() assert RayXGBClassifier._estimator_type == "classifier" assert RayXGBRFClassifier._estimator_type == "classifier" assert RayXGBRegressor._estimator_type == "regressor" assert RayXGBRFRegressor._estimator_type == "regressor" assert RayXGBRanker._estimator_type == "ranker" from sklearn.datasets import load_digits X, y = load_digits(n_class=2, return_X_y=True) cls = RayXGBClassifier(n_estimators=2).fit(X, y) with tempfile.TemporaryDirectory() as tmpdir: path = os.path.join(tmpdir, "cls.json") cls.save_model(path) reg = RayXGBRegressor() with self.assertRaises(TypeError): reg.load_model(path) cls = RayXGBClassifier() cls.load_model(path) # no error
def save_load_model(self, model_path): from sklearn.datasets import load_digits from sklearn.model_selection import KFold digits = load_digits(n_class=2) y = digits["target"] X = digits["data"] kf = KFold(n_splits=2, shuffle=True, random_state=self.rng) for train_index, test_index in kf.split(X, y): xgb_model = RayXGBClassifier(use_label_encoder=False).fit( X[train_index], y[train_index]) xgb_model.save_model(model_path) xgb_model = RayXGBClassifier() xgb_model.load_model(model_path) assert xgb_model.use_label_encoder is False assert isinstance(xgb_model.classes_, np.ndarray) assert isinstance(xgb_model._Booster, xgb.Booster) preds = xgb_model.predict(X[test_index]) labels = y[test_index] err = sum(1 for i in range(len(preds)) if int(preds[i] > 0.5) != labels[i]) / float(len(preds)) assert err < 0.1 assert xgb_model.get_booster().attr("scikit_learn") is None # test native booster preds = xgb_model.predict(X[test_index], output_margin=True) booster = xgb.Booster(model_file=model_path) predt_1 = booster.predict( xgb.DMatrix(X[test_index]), output_margin=True) assert np.allclose(preds, predt_1) with self.assertRaises(TypeError): xgb_model = xgb.XGBModel() xgb_model.load_model(model_path)