bcc0277338
* Re-implement ROC-AUC. * Binary * MultiClass * LTR * Add documents. This PR resolves a few issues: - Define a value when the dataset is invalid, which can happen if there's an empty dataset, or when the dataset contains only positive or negative values. - Define ROC-AUC for multi-class classification. - Define weighted average value for distributed setting. - A correct implementation for learning to rank task. Previous implementation is just binary classification with averaging across groups, which doesn't measure ordered learning to rank.
48 lines
1.4 KiB
Python
48 lines
1.4 KiB
Python
import sys
|
|
import xgboost
|
|
import pytest
|
|
|
|
sys.path.append("tests/python")
|
|
import test_eval_metrics as test_em # noqa
|
|
|
|
|
|
class TestGPUEvalMetrics:
|
|
cpu_test = test_em.TestEvalMetrics()
|
|
|
|
@pytest.mark.parametrize("n_samples", [4, 100, 1000])
|
|
def test_roc_auc_binary(self, n_samples):
|
|
self.cpu_test.run_roc_auc_binary("gpu_hist", n_samples)
|
|
|
|
@pytest.mark.parametrize("n_samples", [4, 100, 1000])
|
|
def test_roc_auc_multi(self, n_samples):
|
|
self.cpu_test.run_roc_auc_multi("gpu_hist", n_samples)
|
|
|
|
@pytest.mark.parametrize("n_samples", [4, 100, 1000])
|
|
def test_roc_auc_ltr(self, n_samples):
|
|
import numpy as np
|
|
|
|
rng = np.random.RandomState(1994)
|
|
n_samples = n_samples
|
|
n_features = 10
|
|
X = rng.randn(n_samples, n_features)
|
|
y = rng.randint(0, 16, size=n_samples)
|
|
group = np.array([n_samples // 2, n_samples // 2])
|
|
|
|
Xy = xgboost.DMatrix(X, y, group=group)
|
|
|
|
cpu = xgboost.train(
|
|
{"tree_method": "hist", "eval_metric": "auc", "objective": "rank:ndcg"},
|
|
Xy,
|
|
num_boost_round=10,
|
|
)
|
|
cpu_auc = float(cpu.eval(Xy).split(":")[1])
|
|
|
|
gpu = xgboost.train(
|
|
{"tree_method": "gpu_hist", "eval_metric": "auc", "objective": "rank:ndcg"},
|
|
Xy,
|
|
num_boost_round=10,
|
|
)
|
|
gpu_auc = float(gpu.eval(Xy).split(":")[1])
|
|
|
|
np.testing.assert_allclose(cpu_auc, gpu_auc)
|