def test_decision_tree_criterion_iris_dtc(self):
iris = datasets.load_iris()
X, y = iris.data, iris.target
clr1 = DecisionTreeRegressor()
clr1.fit(X, y)
p1 = clr1.predict(X)
clr2 = PiecewiseTreeRegressor(criterion='simple')
clr2.fit(X, y)
p2 = clr2.predict(X)
self.assertEqual(p1[:10], p2[:10])
def test_decision_tree_criterion_iris_dtc(self):
iris = datasets.load_iris()
X, y = iris.data, iris.target
clr1 = DecisionTreeRegressor()
clr1.fit(X, y)
p1 = clr1.predict(X)
clr2 = PiecewiseTreeRegressor(criterion='mselin')
clr2.fit(X, y)
p2 = clr2.predict(X)
self.assertEqual(p1.shape, p2.shape)
self.assertTrue(hasattr(clr2, 'betas_'))
self.assertTrue(hasattr(clr2, 'leaves_mapping_'))
self.assertEqual(len(clr2.leaves_index_), clr2.tree_.n_leaves)
self.assertEqual(len(clr2.leaves_mapping_), clr2.tree_.n_leaves)
self.assertEqual(clr2.betas_.shape[1], X.shape[1] + 1)
self.assertEqual(clr2.betas_.shape[0], clr2.tree_.n_leaves)
sc1 = clr1.score(X, y)
sc2 = clr2.score(X, y)
self.assertGreater(sc1, sc2)
mp = clr2._mapping_train(X) # pylint: disable=W0212
self.assertIsInstance(mp, dict)
self.assertGreater(len(mp), 2)
def test_decision_tree_criterion_iris_dtc_traintest(self):
iris = datasets.load_iris()
X, y = iris.data, iris.target
X_train, X_test, y_train, y_test = train_test_split(X, y)
clr1 = DecisionTreeRegressor()
clr1.fit(X_train, y_train)
p1 = clr1.predict(X_train)
clr2 = PiecewiseTreeRegressor(criterion='mselin')
clr2.fit(X_train, y_train)
p2 = clr2.predict(X_train)
self.assertEqual(p1.shape, p2.shape)
self.assertTrue(hasattr(clr2, 'betas_'))
self.assertTrue(hasattr(clr2, 'leaves_mapping_'))
self.assertEqual(len(clr2.leaves_index_), clr2.tree_.n_leaves)
self.assertEqual(len(clr2.leaves_mapping_), clr2.tree_.n_leaves)
self.assertEqual(clr2.betas_.shape[1], X.shape[1] + 1)
self.assertEqual(clr2.betas_.shape[0], clr2.tree_.n_leaves)
sc1 = clr1.score(X_test, y_test)
sc2 = clr2.score(X_test, y_test)
self.assertGreater(abs(sc1 - sc2), -0.1)