def test_missing_boston(self):
# regression, categoricals+numbers, synthetically added missing values
all_X, all_y = sklearn.datasets.load_boston(return_X_y=True)
with_missing_X = lale.helpers.add_missing_values(all_X)
with self.assertRaisesRegex(ValueError, "Input contains NaN"):
lr_trainable = LinearRegression()
_ = lr_trainable.fit(with_missing_X, all_y)
self._fit_predict("regression", with_missing_X, all_y)
def test_scorers_regression(self):
fairness_info = self.boston["fairness_info"]
trainable = LinearRegression()
train_X = self.boston["train_X"]
train_y = self.boston["train_y"]
trained = trainable.fit(train_X, train_y)
test_X = self.boston["test_X"]
test_y = self.boston["test_y"]
self._attempt_scorers(fairness_info, trained, test_X, test_y)
def test_hyperparam_estimator(self):
lr = LogisticRegression()
linear_reg = LinearRegression()
ada = AdaBoostRegressor(base_estimator=lr)
replaced_ada = ada.replace(lr, linear_reg)
expected_ada = AdaBoostRegressor(base_estimator=linear_reg)
self.assertEqual(replaced_ada.to_json(), expected_ada.to_json())
replaced_ada = ada.replace(LogisticRegression, linear_reg)
expected_ada = AdaBoostRegressor(base_estimator=linear_reg)
self.assertEqual(replaced_ada.to_json(), expected_ada.to_json())
ada_pipeline = PCA >> SimpleImputer >> ada
replaced_pipeline = ada_pipeline.replace(lr, linear_reg)
expected_pipeline = (
PCA >> SimpleImputer >> AdaBoostRegressor(base_estimator=linear_reg)
)
self.assertEqual(replaced_pipeline.to_json(), expected_pipeline.to_json())
ada_choice = PCA | ada
replaced_choice = ada_choice.replace(lr, linear_reg)
expected_choice = PCA | AdaBoostRegressor(base_estimator=linear_reg)
self.assertEqual(replaced_choice.to_json(), expected_choice.to_json())
rfe = RFE(estimator=lr)
replaced_rfe = rfe.replace(lr, linear_reg)
expected_rfe = RFE(estimator=linear_reg)
self.assertEqual(replaced_rfe.to_json(), expected_rfe.to_json())
def test_hyperparam_estimator_list(self):
lr = LogisticRegression()
linear_reg = LinearRegression()
dtc = DecisionTreeClassifier()
cls_list = [("lr", lr), ("linear_reg", linear_reg)]
vc = VotingClassifier(estimators=cls_list)
replaced_vc = vc.replace(linear_reg, dtc)
new_cls_list = [("lr", lr), ("linear_reg", dtc)]
expected_vc = VotingClassifier(estimators=new_cls_list)
self.assertEqual(replaced_vc.to_json(), expected_vc.to_json())
sc = StackingClassifier(estimators=cls_list, final_estimator=vc)
replaced_sc = sc.replace(linear_reg, dtc)
new_cls_list = [("lr", lr), ("linear_reg", dtc)]
expected_sc = StackingClassifier(
estimators=new_cls_list, final_estimator=expected_vc
)
self.assertEqual(replaced_sc.to_json(), expected_sc.to_json())
def test_with_defaults(self):
trainable = LinearRegression()
trained = trainable.fit(self.train_X, self.train_y)
_ = trained.predict(self.test_X)