Traktor/myenv/Lib/site-packages/sklearn/tests/test_kernel_ridge.py
2024-05-23 01:57:24 +02:00

81 lines
2.8 KiB
Python

import numpy as np
import pytest
from sklearn.datasets import make_regression
from sklearn.kernel_ridge import KernelRidge
from sklearn.linear_model import Ridge
from sklearn.metrics.pairwise import pairwise_kernels
from sklearn.utils._testing import assert_array_almost_equal, ignore_warnings
from sklearn.utils.fixes import CSC_CONTAINERS, CSR_CONTAINERS
X, y = make_regression(n_features=10, random_state=0)
Y = np.array([y, y]).T
def test_kernel_ridge():
pred = Ridge(alpha=1, fit_intercept=False).fit(X, y).predict(X)
pred2 = KernelRidge(kernel="linear", alpha=1).fit(X, y).predict(X)
assert_array_almost_equal(pred, pred2)
@pytest.mark.parametrize("sparse_container", [*CSR_CONTAINERS, *CSC_CONTAINERS])
def test_kernel_ridge_sparse(sparse_container):
X_sparse = sparse_container(X)
pred = (
Ridge(alpha=1, fit_intercept=False, solver="cholesky")
.fit(X_sparse, y)
.predict(X_sparse)
)
pred2 = KernelRidge(kernel="linear", alpha=1).fit(X_sparse, y).predict(X_sparse)
assert_array_almost_equal(pred, pred2)
def test_kernel_ridge_singular_kernel():
# alpha=0 causes a LinAlgError in computing the dual coefficients,
# which causes a fallback to a lstsq solver. This is tested here.
pred = Ridge(alpha=0, fit_intercept=False).fit(X, y).predict(X)
kr = KernelRidge(kernel="linear", alpha=0)
ignore_warnings(kr.fit)(X, y)
pred2 = kr.predict(X)
assert_array_almost_equal(pred, pred2)
def test_kernel_ridge_precomputed():
for kernel in ["linear", "rbf", "poly", "cosine"]:
K = pairwise_kernels(X, X, metric=kernel)
pred = KernelRidge(kernel=kernel).fit(X, y).predict(X)
pred2 = KernelRidge(kernel="precomputed").fit(K, y).predict(K)
assert_array_almost_equal(pred, pred2)
def test_kernel_ridge_precomputed_kernel_unchanged():
K = np.dot(X, X.T)
K2 = K.copy()
KernelRidge(kernel="precomputed").fit(K, y)
assert_array_almost_equal(K, K2)
def test_kernel_ridge_sample_weights():
K = np.dot(X, X.T) # precomputed kernel
sw = np.random.RandomState(0).rand(X.shape[0])
pred = Ridge(alpha=1, fit_intercept=False).fit(X, y, sample_weight=sw).predict(X)
pred2 = KernelRidge(kernel="linear", alpha=1).fit(X, y, sample_weight=sw).predict(X)
pred3 = (
KernelRidge(kernel="precomputed", alpha=1)
.fit(K, y, sample_weight=sw)
.predict(K)
)
assert_array_almost_equal(pred, pred2)
assert_array_almost_equal(pred, pred3)
def test_kernel_ridge_multi_output():
pred = Ridge(alpha=1, fit_intercept=False).fit(X, Y).predict(X)
pred2 = KernelRidge(kernel="linear", alpha=1).fit(X, Y).predict(X)
assert_array_almost_equal(pred, pred2)
pred3 = KernelRidge(kernel="linear", alpha=1).fit(X, y).predict(X)
pred3 = np.array([pred3, pred3]).T
assert_array_almost_equal(pred2, pred3)