def test_cross_val_score_with_score_func_regression():
X, y = make_regression(n_samples=30, n_features=20, n_informative=5,
random_state=0)
reg = Ridge()
# Default score of the Ridge regression estimator
scores = cross_val_score(reg, X, y, cv=5)
assert_array_almost_equal(scores, [0.94, 0.97, 0.97, 0.99, 0.92], 2)
# R2 score (aka. determination coefficient) - should be the
# same as the default estimator score
r2_scores = cross_val_score(reg, X, y, scoring="r2", cv=5)
assert_array_almost_equal(r2_scores, [0.94, 0.97, 0.97, 0.99, 0.92], 2)
# Mean squared error; this is a loss function, so "scores" are negative
mse_scores = cross_val_score(reg, X, y, cv=5, scoring="mean_squared_error")
expected_mse = np.array([-763.07, -553.16, -274.38, -273.26, -1681.99])
assert_array_almost_equal(mse_scores, expected_mse, 2)
# Explained variance
scoring = make_scorer(explained_variance_score)
ev_scores = cross_val_score(reg, X, y, cv=5, scoring=scoring)
assert_array_almost_equal(ev_scores, [0.94, 0.97, 0.97, 0.99, 0.92], 2)
评论列表
文章目录
