xgboost/tests/python-gpu/test_gpu_parse_tree.py
Jiaming Yuan a5d222fcdb
Handle categorical split in model histogram and dataframe. (#7065)
* Error on get_split_value_histogram when feature is categorical
* Add a category column to output dataframe
2021-07-02 13:10:36 +08:00

26 lines
767 B
Python

import sys
import pytest
import xgboost as xgb
sys.path.append("tests/python")
import testing as tm
def test_tree_to_df_categorical():
X, y = tm.make_categorical(100, 10, 31, False)
Xy = xgb.DMatrix(X, y, enable_categorical=True)
booster = xgb.train({"tree_method": "gpu_hist"}, Xy, num_boost_round=10)
df = booster.trees_to_dataframe()
for _, x in df.iterrows():
if x["Feature"] != "Leaf":
assert len(x["Category"]) == 1
def test_split_value_histograms():
X, y = tm.make_categorical(1000, 10, 13, False)
reg = xgb.XGBRegressor(tree_method="gpu_hist", enable_categorical=True)
reg.fit(X, y)
with pytest.raises(ValueError, match="doesn't"):
reg.get_booster().get_split_value_histogram("3", bins=5)