def test_transform_target_regressor_2d_transformer(X, y):
# Check consistency with transformer accepting only 2D array and a 1D/2D y
# array.
transformer = StandardScaler()
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=transformer)
y_pred = regr.fit(X, y).predict(X)
assert y.shape == y_pred.shape
# consistency forward transform
if y.ndim == 1: # create a 2D array and squeeze results
y_tran = regr.transformer_.transform(y.reshape(-1, 1)).squeeze()
else:
y_tran = regr.transformer_.transform(y)
_check_standard_scaled(y, y_tran)
assert y.shape == y_pred.shape
# consistency inverse transform
assert_allclose(y, regr.transformer_.inverse_transform(y_tran).squeeze())
# consistency of the regressor
lr = LinearRegression()
transformer2 = clone(transformer)
if y.ndim == 1: # create a 2D array and squeeze results
lr.fit(X, transformer2.fit_transform(y.reshape(-1, 1)).squeeze())
else:
lr.fit(X, transformer2.fit_transform(y))
y_lr_pred = lr.predict(X)
assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_plot_partial_dependence_passing_numpy_axes(pyplot, clf_boston,
boston):
grid_resolution = 25
feature_names = boston.feature_names.tolist()
disp1 = plot_partial_dependence(clf_boston, boston.data,
['CRIM', 'ZN'],
grid_resolution=grid_resolution,
feature_names=feature_names)
assert disp1.axes_.shape == (1, 2)
assert disp1.axes_[0, 0].get_ylabel() == "Partial dependence"
assert disp1.axes_[0, 1].get_ylabel() == ""
assert len(disp1.axes_[0, 0].get_lines()) == 1
assert len(disp1.axes_[0, 1].get_lines()) == 1
lr = LinearRegression()
lr.fit(boston.data, boston.target)
disp2 = plot_partial_dependence(lr, boston.data,
['CRIM', 'ZN'],
grid_resolution=grid_resolution,
feature_names=feature_names,
ax=disp1.axes_)
assert np.all(disp1.axes_ == disp2.axes_)
assert len(disp2.axes_[0, 0].get_lines()) == 2
assert len(disp2.axes_[0, 1].get_lines()) == 2
def test_omp_reaches_least_squares():
# Use small simple data; it's a sanity check but OMP can stop early
rng = check_random_state(0)
n_samples, n_features = (10, 8)
n_targets = 3
X = rng.randn(n_samples, n_features)
Y = rng.randn(n_samples, n_targets)
omp = OrthogonalMatchingPursuit(n_nonzero_coefs=n_features)
lstsq = LinearRegression()
omp.fit(X, Y)
lstsq.fit(X, Y)
assert_array_almost_equal(omp.coef_, lstsq.coef_)
def test_linear_regression_multiple_outcome(random_state=0):
# Test multiple-outcome linear regressions
X, y = make_regression(random_state=random_state)
Y = np.vstack((y, y)).T
n_features = X.shape[1]
reg = LinearRegression()
reg.fit((X), Y)
assert reg.coef_.shape == (2, n_features)
Y_pred = reg.predict(X)
reg.fit(X, y)
y_pred = reg.predict(X)
assert_array_almost_equal(np.vstack((y_pred, y_pred)).T, Y_pred, decimal=3)
def test_linear_regression_sparse(random_state=0):
# Test that linear regression also works with sparse data
random_state = check_random_state(random_state)
for i in range(10):
n = 100
X = sparse.eye(n, n)
beta = random_state.rand(n)
y = X * beta[:, np.newaxis]
ols = LinearRegression()
ols.fit(X, y.ravel())
assert_array_almost_equal(beta, ols.coef_ + ols.intercept_)
assert_array_almost_equal(ols.predict(X) - y.ravel(), 0)
def test_linear_regression_sparse_multiple_outcome(random_state=0):
# Test multiple-outcome linear regressions with sparse data
random_state = check_random_state(random_state)
X, y = make_sparse_uncorrelated(random_state=random_state)
X = sparse.coo_matrix(X)
Y = np.vstack((y, y)).T
n_features = X.shape[1]
ols = LinearRegression()
ols.fit(X, Y)
assert ols.coef_.shape == (2, n_features)
Y_pred = ols.predict(X)
ols.fit(X, y.ravel())
y_pred = ols.predict(X)
assert_array_almost_equal(np.vstack((y_pred, y_pred)).T, Y_pred, decimal=3)
def test_linear_regression_sparse_equal_dense(normalize, fit_intercept):
# Test that linear regression agrees between sparse and dense
rng = check_random_state(0)
n_samples = 200
n_features = 2
X = rng.randn(n_samples, n_features)
X[X < 0.1] = 0.
Xcsr = sparse.csr_matrix(X)
y = rng.rand(n_samples)
params = dict(normalize=normalize, fit_intercept=fit_intercept)
clf_dense = LinearRegression(**params)
clf_sparse = LinearRegression(**params)
clf_dense.fit(X, y)
clf_sparse.fit(Xcsr, y)
assert clf_dense.intercept_ == pytest.approx(clf_sparse.intercept_)
assert_allclose(clf_dense.coef_, clf_sparse.coef_)
def test_plot_partial_dependence_fig_deprecated(pyplot):
# Make sure fig object is correctly used if not None
X, y = make_regression(n_samples=50, random_state=0)
clf = LinearRegression()
clf.fit(X, y)
fig = pyplot.figure()
grid_resolution = 25
msg = ("The fig parameter is deprecated in version 0.22 and will be "
"removed in version 0.24")
with pytest.warns(FutureWarning, match=msg):
plot_partial_dependence(
clf, X, [0, 1], target=0, grid_resolution=grid_resolution, fig=fig)
assert pyplot.gcf() is fig
def test_raises_value_error_if_sample_weights_greater_than_1d():
# Sample weights must be either scalar or 1D
n_sampless = [2, 3]
n_featuress = [3, 2]
for n_samples, n_features in zip(n_sampless, n_featuress):
X = rng.randn(n_samples, n_features)
y = rng.randn(n_samples)
sample_weights_OK = rng.randn(n_samples)**2 + 1
sample_weights_OK_1 = 1.
sample_weights_OK_2 = 2.
reg = LinearRegression()
# make sure the "OK" sample weights actually work
reg.fit(X, y, sample_weights_OK)
reg.fit(X, y, sample_weights_OK_1)
reg.fit(X, y, sample_weights_OK_2)
def test_ridge_vs_lstsq():
# On alpha=0., Ridge and OLS yield the same solution.
rng = np.random.RandomState(0)
# we need more samples than features
n_samples, n_features = 5, 4
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
ridge = Ridge(alpha=0., fit_intercept=False)
ols = LinearRegression(fit_intercept=False)
ridge.fit(X, y)
ols.fit(X, y)
assert_almost_equal(ridge.coef_, ols.coef_)
ridge.fit(X, y)
ols.fit(X, y)
assert_almost_equal(ridge.coef_, ols.coef_)
def test_linear_regression_sample_weights():
# TODO: loop over sparse data as well
rng = np.random.RandomState(0)
# It would not work with under-determined systems
for n_samples, n_features in ((6, 5), ):
y = rng.randn(n_samples)
X = rng.randn(n_samples, n_features)
sample_weight = 1.0 + rng.rand(n_samples)
for intercept in (True, False):
# LinearRegression with explicit sample_weight
reg = LinearRegression(fit_intercept=intercept)
reg.fit(X, y, sample_weight=sample_weight)
coefs1 = reg.coef_
inter1 = reg.intercept_
assert reg.coef_.shape == (X.shape[1], ) # sanity checks
assert reg.score(X, y) > 0.5
# Closed form of the weighted least square
# theta = (X^T W X)^(-1) * X^T W y
W = np.diag(sample_weight)
if intercept is False:
X_aug = X
else:
dummy_column = np.ones(shape=(n_samples, 1))
X_aug = np.concatenate((dummy_column, X), axis=1)
coefs2 = linalg.solve(
X_aug.T.dot(W).dot(X_aug),
X_aug.T.dot(W).dot(y))
if intercept is False:
assert_array_almost_equal(coefs1, coefs2)
else:
assert_array_almost_equal(coefs1, coefs2[1:])
assert_almost_equal(inter1, coefs2[0])
def test_linear_regression():
# Test LinearRegression on a simple dataset.
# a simple dataset
X = [[1], [2]]
Y = [1, 2]
reg = LinearRegression()
reg.fit(X, Y)
assert_array_almost_equal(reg.coef_, [1])
assert_array_almost_equal(reg.intercept_, [0])
assert_array_almost_equal(reg.predict(X), [1, 2])
# test it also for degenerate input
X = [[1]]
Y = [0]
reg = LinearRegression()
reg.fit(X, Y)
assert_array_almost_equal(reg.coef_, [0])
assert_array_almost_equal(reg.intercept_, [0])
assert_array_almost_equal(reg.predict(X), [0])
def test_transform_target_regressor_2d_transformer_multioutput():
# Check consistency with transformer accepting only 2D array and a 2D y
# array.
X = friedman[0]
y = np.vstack((friedman[1], friedman[1]**2 + 1)).T
transformer = StandardScaler()
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=transformer)
y_pred = regr.fit(X, y).predict(X)
assert y.shape == y_pred.shape
# consistency forward transform
y_tran = regr.transformer_.transform(y)
_check_standard_scaled(y, y_tran)
assert y.shape == y_pred.shape
# consistency inverse transform
assert_allclose(y, regr.transformer_.inverse_transform(y_tran).squeeze())
# consistency of the regressor
lr = LinearRegression()
transformer2 = clone(transformer)
lr.fit(X, transformer2.fit_transform(y))
y_lr_pred = lr.predict(X)
assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
assert_allclose(regr.regressor_.coef_, lr.coef_)
def test_transform_target_regressor_1d_transformer(X, y):
# All transformer in scikit-learn expect 2D data. FunctionTransformer with
# validate=False lift this constraint without checking that the input is a
# 2D vector. We check the consistency of the data shape using a 1D and 2D y
# array.
transformer = FunctionTransformer(func=lambda x: x + 1,
inverse_func=lambda x: x - 1)
regr = TransformedTargetRegressor(regressor=LinearRegression(),
transformer=transformer)
y_pred = regr.fit(X, y).predict(X)
assert y.shape == y_pred.shape
# consistency forward transform
y_tran = regr.transformer_.transform(y)
_check_shifted_by_one(y, y_tran)
assert y.shape == y_pred.shape
# consistency inverse transform
assert_allclose(y, regr.transformer_.inverse_transform(y_tran).squeeze())
# consistency of the regressor
lr = LinearRegression()
transformer2 = clone(transformer)
lr.fit(X, transformer2.fit_transform(y))
y_lr_pred = lr.predict(X)
assert_allclose(y_pred, transformer2.inverse_transform(y_lr_pred))
assert_allclose(regr.regressor_.coef_, lr.coef_)