Created
June 2, 2020 15:03
-
-
Save ogrisel/8f1c4975173f2f3c540da0a7f6be304d to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
@pytest.mark.parametrize("loss", ['huber', 'ls', 'lad', 'quantile']) | |
@pytest.mark.parametrize("use_sample_weight", [False, True]) | |
def test_regressor_train_loss_convergence(loss, use_sample_weight): | |
rng = np.random.RandomState(42) | |
n_samples, n_features = 30, 5 | |
n_estimators = 300 | |
# Make random data (without duplicated samples) to make sure | |
# it's possible to build an invertible (overfitting) mapping | |
# from X to y that therefore should lead to a regression loss | |
# of zero if n_estimators is large enough. | |
X = rng.randn(n_samples, n_features) | |
y = rng.randn(n_samples) | |
if use_sample_weight: | |
sample_weight = rng.uniform(0, 10, size=n_samples) | |
sample_weight[sample_weight < 2] = 0 | |
else: | |
sample_weight = None | |
gbr = GradientBoostingRegressor( | |
learning_rate=0.1, | |
max_depth=3, | |
loss=loss, | |
n_estimators=n_estimators, | |
n_iter_no_change=None, # make sure early stopping is disabled | |
) | |
gbr.fit(X, y, sample_weight=sample_weight) | |
train_loss = gbr.loss_(y, gbr._raw_predict(X), | |
sample_weight=sample_weight) | |
assert len(gbr.train_score_) == n_estimators | |
# assert gbr.train_score_[-1] == pytest.approx(train_loss) | |
assert train_loss < 1e-6, gbr.train_score_ |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
train_loss
is probably wrong but I do not know why. Maybe in the mean time we should just check: