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_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_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_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_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_constant_size_multioutput_regressor():
random_state = np.random.RandomState(seed=1)
X = random_state.randn(10, 10)
y = random_state.randn(10, 5)
est = DummyRegressor(strategy='constant', constant=[1, 2, 3, 4])
assert_raises(ValueError, est.fit, X, y)
def test_dummy_regressor_sample_weight(n_samples=10):
random_state = np.random.RandomState(seed=1)
X = [[0]] * n_samples
y = random_state.rand(n_samples)
sample_weight = random_state.rand(n_samples)
est = DummyRegressor(strategy="mean").fit(X, y, sample_weight)
assert est.constant_ == np.average(y, weights=sample_weight)
est = DummyRegressor(strategy="median").fit(X, y, sample_weight)
assert est.constant_ == _weighted_percentile(y, sample_weight, 50.)
est = DummyRegressor(strategy="quantile", quantile=.95).fit(X, y,
sample_weight)
assert est.constant_ == _weighted_percentile(y, sample_weight, 95.)
class NoWeightRegressor(BaseEstimator, RegressorMixin):
def fit(self, X, y):
self.reg = DummyRegressor()
return self.reg.fit(X, y)
def predict(self, X):
return np.ones(X.shape[0])
def test_notfitted():
eclf = VotingClassifier(estimators=[('lr1', LogisticRegression()),
('lr2', LogisticRegression())],
voting='soft')
ereg = VotingRegressor([('dr', DummyRegressor())])
msg = ("This %s instance is not fitted yet. Call \'fit\'"
" with appropriate arguments before using this estimator.")
assert_raise_message(NotFittedError, msg % 'VotingClassifier',
eclf.predict, X)
assert_raise_message(NotFittedError, msg % 'VotingClassifier',
eclf.predict_proba, X)
assert_raise_message(NotFittedError, msg % 'VotingClassifier',
eclf.transform, X)
assert_raise_message(NotFittedError, msg % 'VotingRegressor', ereg.predict,
X_r)
assert_raise_message(NotFittedError, msg % 'VotingRegressor',
ereg.transform, X_r)
def test_multidimensional_X():
"""
Check that the AdaBoost estimators can work with n-dimensional
data matrix
"""
rng = np.random.RandomState(0)
X = rng.randn(50, 3, 3)
yc = rng.choice([0, 1], 50)
yr = rng.randn(50)
boost = AdaBoostClassifier(DummyClassifier(strategy='most_frequent'))
boost.fit(X, yc)
boost.predict(X)
boost.predict_proba(X)
boost = AdaBoostRegressor(DummyRegressor())
boost.fit(X, yr)
boost.predict(X)
def test_regression():
# Check regression for various parameter settings.
rng = check_random_state(0)
X_train, X_test, y_train, y_test = train_test_split(boston.data[:50],
boston.target[:50],
random_state=rng)
grid = ParameterGrid({
"max_samples": [0.5, 1.0],
"max_features": [0.5, 1.0],
"bootstrap": [True, False],
"bootstrap_features": [True, False]
})
for base_estimator in [
None,
DummyRegressor(),
DecisionTreeRegressor(),
KNeighborsRegressor(),
SVR()
]:
for params in grid:
BaggingRegressor(base_estimator=base_estimator,
random_state=rng,
**params).fit(X_train, y_train).predict(X_test)
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_invalid():
X = [[0]] * 5 # ignored
y = [0] * 5 # ignored
est = DummyRegressor(strategy="quantile")
assert_raises(ValueError, est.fit, X, y)
est = DummyRegressor(strategy="quantile", quantile=None)
assert_raises(ValueError, est.fit, X, y)
est = DummyRegressor(strategy="quantile", quantile=[0])
assert_raises(ValueError, est.fit, X, y)
est = DummyRegressor(strategy="quantile", quantile=-0.1)
assert_raises(ValueError, est.fit, X, y)
est = DummyRegressor(strategy="quantile", quantile=1.1)
assert_raises(ValueError, est.fit, X, y)
est = DummyRegressor(strategy="quantile", quantile='abc')
assert_raises(TypeError, est.fit, X, y)
def fit(self, X, y):
self.reg = DummyRegressor()
return self.reg.fit(X, y)
def test_regressor_score_with_None(y, y_test):
reg = DummyRegressor()
reg.fit(None, y)
assert reg.score(None, y_test) == 1.0
def test_regressor_exceptions():
reg = DummyRegressor()
assert_raises(NotFittedError, reg.predict, [])
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_constants_not_specified_regressor():
X = [[0]] * 5
y = [1, 2, 4, 6, 8]
est = DummyRegressor(strategy='constant')
assert_raises(TypeError, est.fit, X, y)
def test_unknown_strategey_regressor():
X = [[0]] * 5
y = [1, 2, 4, 6, 8]
est = DummyRegressor(strategy='gona')
assert_raises(ValueError, est.fit, X, y)
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)
if imputation_order == 'roman':
assert np.all(ordered_idx[:d-1] == np.arange(1, d))
elif imputation_order == 'arabic':
assert np.all(ordered_idx[:d-1] == np.arange(d-1, 0, -1))
elif imputation_order == 'random':
ordered_idx_round_1 = ordered_idx[:d-1]
ordered_idx_round_2 = ordered_idx[d-1:]
assert ordered_idx_round_1 != ordered_idx_round_2
elif 'ending' in imputation_order:
assert len(ordered_idx) == max_iter * (d - 1)
@pytest.mark.parametrize(
"estimator",
[None, DummyRegressor(), BayesianRidge(), ARDRegression(), RidgeCV()]
)
def test_iterative_imputer_estimators(estimator):
rng = np.random.RandomState(0)
n = 100
d = 10
X = _sparse_random_matrix(n, d, density=0.10, random_state=rng).toarray()
imputer = IterativeImputer(missing_values=0,
max_iter=1,
estimator=estimator,
random_state=rng)
imputer.fit_transform(X)
# check that types are correct for estimators
def test_quantile_strategy_empty_train():
est = DummyRegressor(strategy="quantile", quantile=0.4)
assert_raises(ValueError, est.fit, [], [])
def test_set_params_nested_pipeline():
estimator = Pipeline([('a', Pipeline([('b', DummyRegressor())]))])
estimator.set_params(a__b__alpha=0.001, a__b=Lasso())
estimator.set_params(a__steps=[('b', LogisticRegression())], a__b__C=5)
reg_drop = StackingRegressor(estimators=estimators,
final_estimator=rf,
cv=5)
reg.fit(X_train, y_train)
reg_drop.fit(X_train, y_train)
assert_allclose(reg.predict(X_test), reg_drop.predict(X_test))
assert_allclose(reg.transform(X_test), reg_drop.transform(X_test))
@pytest.mark.parametrize(
"cv", [3, KFold(n_splits=3, shuffle=True, random_state=42)])
@pytest.mark.parametrize("final_estimator, predict_params",
[(None, {}),
(RandomForestRegressor(random_state=42), {}),
(DummyRegressor(), {
'return_std': True
})])
@pytest.mark.parametrize("passthrough", [False, True])
def test_stacking_regressor_diabetes(cv, final_estimator, predict_params,
passthrough):
# prescale the data to avoid convergence warning without using a pipeline
# for later assert
X_train, X_test, y_train, _ = train_test_split(scale(X_diabetes),
y_diabetes,
random_state=42)
estimators = [('lr', LinearRegression()), ('svr', LinearSVR())]
reg = StackingRegressor(estimators=estimators,
final_estimator=final_estimator,
cv=cv,
passthrough=passthrough)