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

Handle categorical split in model histogram and dataframe. (#7065)

Browse Source 
* Error on get_split_value_histogram when feature is categorical
* Add a category column to output dataframe
This commit is contained in:
Jiaming Yuan
2021-07-02 13:10:36 +08:00
committed by GitHub
parent 1cd20efe68
commit a5d222fcdb
3 changed files with 96 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
tests/python-gpu/test_gpu_updaters.py
View File

@@ -32,15 +32,14 @@ def train_result(param, dmat, num_rounds):
class TestGPUUpdaters:
@given(parameter_strategy, strategies.integers(1, 20),
tm.dataset_strategy)
@given(parameter_strategy, strategies.integers(1, 20), tm.dataset_strategy)
@settings(deadline=None)
def test_gpu_hist(self, param, num_rounds, dataset):
param['tree_method'] = 'gpu_hist'
param["tree_method"] = "gpu_hist"
param = dataset.set_params(param)
result = train_result(param, dataset.get_dmat(), num_rounds)
note(result)
assert tm.non_increasing(result['train'][dataset.metric])
assert tm.non_increasing(result["train"][dataset.metric])
def run_categorical_basic(self, rows, cols, rounds, cats):
onehot, label = tm.make_categorical(rows, cols, cats, True)
@@ -49,25 +48,40 @@ class TestGPUUpdaters:
by_etl_results = {}
by_builtin_results = {}
parameters = {'tree_method': 'gpu_hist', 'predictor': 'gpu_predictor'}
parameters = {"tree_method": "gpu_hist", "predictor": "gpu_predictor"}
m = xgb.DMatrix(onehot, label, enable_categorical=True)
xgb.train(parameters, m,
num_boost_round=rounds,
evals=[(m, 'Train')], evals_result=by_etl_results)
m = xgb.DMatrix(onehot, label, enable_categorical=False)
xgb.train(
parameters,
m,
num_boost_round=rounds,
evals=[(m, "Train")],
evals_result=by_etl_results,
)
m = xgb.DMatrix(cat, label, enable_categorical=True)
xgb.train(parameters, m,
num_boost_round=rounds,
evals=[(m, 'Train')], evals_result=by_builtin_results)
xgb.train(
parameters,
m,
num_boost_round=rounds,
evals=[(m, "Train")],
evals_result=by_builtin_results,
)
# There are guidelines on how to specify tolerance based on considering output as
# random variables. But in here the tree construction is extremely sensitive to
# floating point errors. An 1e-5 error in a histogram bin can lead to an entirely
# different tree. So even though the test is quite lenient, hypothesis can still
# pick up falsifying examples from time to time.
np.testing.assert_allclose(
np.array(by_etl_results['Train']['rmse']),
np.array(by_builtin_results['Train']['rmse']),
rtol=1e-3)
assert tm.non_increasing(by_builtin_results['Train']['rmse'])
np.array(by_etl_results["Train"]["rmse"]),
np.array(by_builtin_results["Train"]["rmse"]),
rtol=1e-3,
)
assert tm.non_increasing(by_builtin_results["Train"]["rmse"])
@given(strategies.integers(10, 400), strategies.integers(3, 8),
strategies.integers(1, 5), strategies.integers(4, 7))
strategies.integers(1, 2), strategies.integers(4, 7))
@settings(deadline=None)
@pytest.mark.skipif(**tm.no_pandas())
def test_categorical(self, rows, cols, rounds, cats):