Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Tests for dask skl categorical data support. (#7054)

Browse Source
This commit is contained in:
Jiaming Yuan 2021-06-24 16:33:57 +08:00 committed by GitHub
parent da1ad798ca
commit 1d4d345634
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 33 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
python-package/xgboost/sklearn.py
View File

@ -632,6 +632,12 @@ class XGBModel(XGBModelBase):
eval_metric = None
else:
params.update({"eval_metric": eval_metric})
if self.enable_categorical and params.get("tree_method", None) != "gpu_hist":
raise ValueError(
"Experimental support for categorical data is not implemented for"
" current tree method yet."
)
return model, feval, params
def _set_evaluation_result(self, evals_result: TrainingCallback.EvalsLog) -> None:

40
tests/python-gpu/test_gpu_with_dask.py
View File

@ -211,20 +211,34 @@ def test_categorical(local_cuda_cluster: LocalCUDACluster) -> None:
)
assert tm.non_increasing(by_builtin_results["Train"]["rmse"])
model = output["booster"]
with tempfile.TemporaryDirectory() as tempdir:
path = os.path.join(tempdir, "model.json")
model.save_model(path)
with open(path, "r") as fd:
categorical = json.load(fd)
def check_model_output(model: dxgb.Booster) -> None:
with tempfile.TemporaryDirectory() as tempdir:
path = os.path.join(tempdir, "model.json")
model.save_model(path)
with open(path, "r") as fd:
categorical = json.load(fd)
categories_sizes = np.array(
categorical["learner"]["gradient_booster"]["model"]["trees"][-1][
"categories_sizes"
]
)
assert categories_sizes.shape[0] != 0
np.testing.assert_allclose(categories_sizes, 1)
categories_sizes = np.array(
categorical["learner"]["gradient_booster"]["model"]["trees"][-1][
"categories_sizes"
]
)
assert categories_sizes.shape[0] != 0
np.testing.assert_allclose(categories_sizes, 1)
check_model_output(output["booster"])
reg = dxgb.DaskXGBRegressor(
enable_categorical=True, n_estimators=10, tree_method="gpu_hist"
)
reg.fit(X, y)
check_model_output(reg.get_booster())
reg = dxgb.DaskXGBRegressor(
enable_categorical=True, n_estimators=10
)
with pytest.raises(ValueError):
reg.fit(X, y)
def to_cp(x: Any, DMatrixT: Type) -> Any: