def test_quantile_strategy_multioutput_regressor():
random_state = np.random.RandomState(seed=1)
X_learn = random_state.randn(10, 10)
y_learn = random_state.randn(10, 5)
median = np.median(y_learn, axis=0).reshape((1, -1))
quantile_values = np.percentile(y_learn, axis=0, q=80).reshape((1, -1))
X_test = random_state.randn(20, 10)
y_test = random_state.randn(20, 5)
# Correctness oracle
est = DummyRegressor(strategy="quantile", quantile=0.5)
est.fit(X_learn, y_learn)
y_pred_learn = est.predict(X_learn)
y_pred_test = est.predict(X_test)
_check_equality_regressor(
median, y_learn, y_pred_learn, y_test, y_pred_test)
_check_behavior_2d(est)
# Correctness oracle
est = DummyRegressor(strategy="quantile", quantile=0.8)
est.fit(X_learn, y_learn)
y_pred_learn = est.predict(X_learn)
y_pred_test = est.predict(X_test)
_check_equality_regressor(
quantile_values, y_learn, y_pred_learn, y_test, y_pred_test)
_check_behavior_2d(est)
def test_weights_regressor():
"""Check weighted average regression prediction on boston dataset."""
reg1 = DummyRegressor(strategy='mean')
reg2 = DummyRegressor(strategy='median')
reg3 = DummyRegressor(strategy='quantile', quantile=.2)
ereg = VotingRegressor([('mean', reg1), ('median', reg2),
('quantile', reg3)], weights=[1, 2, 10])
X_r_train, X_r_test, y_r_train, y_r_test = \
train_test_split(X_r, y_r, test_size=.25)
reg1_pred = reg1.fit(X_r_train, y_r_train).predict(X_r_test)
reg2_pred = reg2.fit(X_r_train, y_r_train).predict(X_r_test)
reg3_pred = reg3.fit(X_r_train, y_r_train).predict(X_r_test)
ereg_pred = ereg.fit(X_r_train, y_r_train).predict(X_r_test)
avg = np.average(np.asarray([reg1_pred, reg2_pred, reg3_pred]), axis=0,
weights=[1, 2, 10])
assert_almost_equal(ereg_pred, avg, decimal=2)
ereg_weights_none = VotingRegressor([('mean', reg1), ('median', reg2),
('quantile', reg3)], weights=None)
ereg_weights_equal = VotingRegressor([('mean', reg1), ('median', reg2),
('quantile', reg3)],
weights=[1, 1, 1])
ereg_weights_none.fit(X_r_train, y_r_train)
ereg_weights_equal.fit(X_r_train, y_r_train)
ereg_none_pred = ereg_weights_none.predict(X_r_test)
ereg_equal_pred = ereg_weights_equal.predict(X_r_test)
assert_almost_equal(ereg_none_pred, ereg_equal_pred, decimal=2)
def test_dummy_regressor_on_3D_array():
X = np.array([[['foo']], [['bar']], [['baz']]])
y = np.array([2, 2, 2])
y_expected = np.array([2, 2, 2])
cls = DummyRegressor()
cls.fit(X, y)
y_pred = cls.predict(X)
assert_array_equal(y_pred, y_expected)
def test_y_mean_attribute_regressor():
X = [[0]] * 5
y = [1, 2, 4, 6, 8]
# when strategy = 'mean'
est = DummyRegressor(strategy='mean')
est.fit(X, y)
assert est.constant_ == np.mean(y)
def test_median_strategy_regressor():
random_state = np.random.RandomState(seed=1)
X = [[0]] * 5 # ignored
y = random_state.randn(5)
reg = DummyRegressor(strategy="median")
reg.fit(X, y)
assert_array_equal(reg.predict(X), [np.median(y)] * len(X))
def test_dummy_regressor_return_std():
X = [[0]] * 3 # ignored
y = np.array([2, 2, 2])
y_std_expected = np.array([0, 0, 0])
cls = DummyRegressor()
cls.fit(X, y)
y_pred_list = cls.predict(X, return_std=True)
# there should be two elements when return_std is True
assert len(y_pred_list) == 2
# the second element should be all zeros
assert_array_equal(y_pred_list[1], y_std_expected)
def test_regressor_prediction_independent_of_X(strategy):
y = [0, 2, 1, 1]
X1 = [[0]] * 4
reg1 = DummyRegressor(strategy=strategy, constant=0, quantile=0.7)
reg1.fit(X1, y)
predictions1 = reg1.predict(X1)
X2 = [[1]] * 4
reg2 = DummyRegressor(strategy=strategy, constant=0, quantile=0.7)
reg2.fit(X2, y)
predictions2 = reg2.predict(X2)
assert_array_equal(predictions1, predictions2)
def test_constant_strategy_regressor():
random_state = np.random.RandomState(seed=1)
X = [[0]] * 5 # ignored
y = random_state.randn(5)
reg = DummyRegressor(strategy="constant", constant=[43])
reg.fit(X, y)
assert_array_equal(reg.predict(X), [43] * len(X))
reg = DummyRegressor(strategy="constant", constant=43)
reg.fit(X, y)
assert_array_equal(reg.predict(X), [43] * len(X))
def test_mean_strategy_multioutput_regressor():
random_state = np.random.RandomState(seed=1)
X_learn = random_state.randn(10, 10)
y_learn = random_state.randn(10, 5)
mean = np.mean(y_learn, axis=0).reshape((1, -1))
X_test = random_state.randn(20, 10)
y_test = random_state.randn(20, 5)
# Correctness oracle
est = DummyRegressor()
est.fit(X_learn, y_learn)
y_pred_learn = est.predict(X_learn)
y_pred_test = est.predict(X_test)
_check_equality_regressor(mean, y_learn, y_pred_learn, y_test, y_pred_test)
_check_behavior_2d(est)
def test_constant_strategy_multioutput_regressor():
random_state = np.random.RandomState(seed=1)
X_learn = random_state.randn(10, 10)
y_learn = random_state.randn(10, 5)
# test with 2d array
constants = random_state.randn(5)
X_test = random_state.randn(20, 10)
y_test = random_state.randn(20, 5)
# Correctness oracle
est = DummyRegressor(strategy="constant", constant=constants)
est.fit(X_learn, y_learn)
y_pred_learn = est.predict(X_learn)
y_pred_test = est.predict(X_test)
_check_equality_regressor(
constants, y_learn, y_pred_learn, y_test, y_pred_test)
_check_behavior_2d_for_constant(est)
def test_quantile_strategy_regressor():
random_state = np.random.RandomState(seed=1)
X = [[0]] * 5 # ignored
y = random_state.randn(5)
reg = DummyRegressor(strategy="quantile", quantile=0.5)
reg.fit(X, y)
assert_array_equal(reg.predict(X), [np.median(y)] * len(X))
reg = DummyRegressor(strategy="quantile", quantile=0)
reg.fit(X, y)
assert_array_equal(reg.predict(X), [np.min(y)] * len(X))
reg = DummyRegressor(strategy="quantile", quantile=1)
reg.fit(X, y)
assert_array_equal(reg.predict(X), [np.max(y)] * len(X))
reg = DummyRegressor(strategy="quantile", quantile=0.3)
reg.fit(X, y)
assert_array_equal(reg.predict(X), [np.percentile(y, q=30)] * len(X))
def test_regressor_score_with_None(y, y_test):
reg = DummyRegressor()
reg.fit(None, y)
assert reg.score(None, y_test) == 1.0