def test_early_stopping(self, local_cuda_cluster: LocalCUDACluster) -> None:
from sklearn.datasets import load_breast_cancer
with Client(local_cuda_cluster) as client:
X, y = load_breast_cancer(return_X_y=True)
X, y = da.from_array(X), da.from_array(y)
m = dxgb.DaskDMatrix(client, X, y)
valid = dxgb.DaskDMatrix(client, X, y)
early_stopping_rounds = 5
booster = dxgb.train(client, {'objective': 'binary:logistic',
'eval_metric': 'error',
'tree_method': 'gpu_hist'}, m,
evals=[(valid, 'Valid')],
num_boost_round=1000,
early_stopping_rounds=early_stopping_rounds)[
'booster']
assert hasattr(booster, 'best_score')
dump = booster.get_dump(dump_format='json')
assert len(dump) - booster.best_iteration == early_stopping_rounds + 1
valid_X = X
valid_y = y
cls = dxgb.DaskXGBClassifier(objective='binary:logistic',
tree_method='gpu_hist',
n_estimators=100)
cls.client = client
cls.fit(X, y, early_stopping_rounds=early_stopping_rounds,
eval_set=[(valid_X, valid_y)])
booster = cls.get_booster()
dump = booster.get_dump(dump_format='json')
assert len(dump) - booster.best_iteration == early_stopping_rounds + 1
def test_categorical(local_cuda_cluster: LocalCUDACluster) -> None:
with Client(local_cuda_cluster) as client:
import dask_cudf
rounds = 10
X, y = make_categorical(client, 10000, 30, 13)
X = dask_cudf.from_dask_dataframe(X)
X_onehot, _ = make_categorical(client, 10000, 30, 13, True)
X_onehot = dask_cudf.from_dask_dataframe(X_onehot)
parameters = {"tree_method": "gpu_hist"}
m = dxgb.DaskDMatrix(client, X_onehot, y, enable_categorical=True)
by_etl_results = dxgb.train(
client,
parameters,
m,
num_boost_round=rounds,
evals=[(m, "Train")],
)["history"]
m = dxgb.DaskDMatrix(client, X, y, enable_categorical=True)
output = dxgb.train(
client,
parameters,
m,
num_boost_round=rounds,
evals=[(m, "Train")],
)
by_builtin_results = output["history"]
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"])
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)
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)
def test_data_initialization(self, local_cuda_cluster: LocalCUDACluster) -> None:
with Client(local_cuda_cluster) as client:
X, y, _ = generate_array()
fw = da.random.random((random_cols, ))
fw = fw - fw.min()
m = dxgb.DaskDMatrix(client, X, y, feature_weights=fw)
workers = _get_client_workers(client)
rabit_args = client.sync(dxgb._get_rabit_args, len(workers), client)
def worker_fn(worker_addr: str, data_ref: Dict) -> None:
with dxgb.RabitContext(rabit_args):
local_dtrain = dxgb._dmatrix_from_list_of_parts(**data_ref)
fw_rows = local_dtrain.get_float_info("feature_weights").shape[0]
assert fw_rows == local_dtrain.num_col()
futures = []
for i in range(len(workers)):
futures.append(
client.submit(
worker_fn,
workers[i],
m._create_fn_args(workers[i]),
pure=False,
workers=[workers[i]]
)
)
client.gather(futures)
def test_dask_array(self):
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
import cupy as cp
cp.cuda.runtime.setDevice(0)
X, y = generate_array()
X = X.map_blocks(cp.asarray)
y = y.map_blocks(cp.asarray)
dtrain = dxgb.DaskDMatrix(client, X, y)
out = dxgb.train(client, {'tree_method': 'gpu_hist'},
dtrain=dtrain,
evals=[(dtrain, 'X')],
num_boost_round=2)
from_dmatrix = dxgb.predict(client, out, dtrain).compute()
inplace_predictions = dxgb.inplace_predict(client, out,
X).compute()
single_node = out['booster'].predict(
xgboost.DMatrix(X.compute()))
np.testing.assert_allclose(single_node, from_dmatrix)
device = cp.cuda.runtime.getDevice()
assert device == inplace_predictions.device.id
single_node = cp.array(single_node)
assert device == single_node.device.id
cp.testing.assert_allclose(single_node, inplace_predictions)
def test_gpu_hist(self, params, num_rounds, dataset):
with LocalCUDACluster(n_workers=2) as cluster:
with Client(cluster) as client:
params['tree_method'] = 'gpu_hist'
params = dataset.set_params(params)
# multi class doesn't handle empty dataset well (empty
# means at least 1 worker has data).
if params['objective'] == "multi:softmax":
return
# It doesn't make sense to distribute a completely
# empty dataset.
if dataset.X.shape[0] == 0:
return
chunk = 128
X = da.from_array(dataset.X,
chunks=(chunk, dataset.X.shape[1]))
y = da.from_array(dataset.y, chunks=(chunk, ))
if dataset.w is not None:
w = da.from_array(dataset.w, chunks=(chunk, ))
else:
w = None
m = dxgb.DaskDMatrix(client, data=X, label=y, weight=w)
history = dxgb.train(client,
params=params,
dtrain=m,
num_boost_round=num_rounds,
evals=[(m, 'train')])['history']
note(history)
assert tm.non_increasing(history['train'][dataset.metric])
def test_dask_dataframe(self):
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
import cupy
X, y = generate_array()
X = dd.from_dask_array(X)
y = dd.from_dask_array(y)
X = X.map_partitions(cudf.from_pandas)
y = y.map_partitions(cudf.from_pandas)
dtrain = dxgb.DaskDMatrix(client, X, y)
out = dxgb.train(client, {'tree_method': 'gpu_hist'},
dtrain=dtrain,
evals=[(dtrain, 'X')],
num_boost_round=2)
assert isinstance(out['booster'], dxgb.Booster)
assert len(out['history']['X']['rmse']) == 2
predictions = dxgb.predict(client, out, dtrain).compute()
assert isinstance(predictions, np.ndarray)
series_predictions = dxgb.inplace_predict(client, out, X)
assert isinstance(series_predictions, dd.Series)
series_predictions = series_predictions.compute()
single_node = out['booster'].predict(
xgboost.DMatrix(X.compute()))
cupy.testing.assert_allclose(single_node, predictions)
cupy.testing.assert_allclose(single_node, series_predictions)
def test_empty_dmatrix(self):
def _check_outputs(out, predictions):
assert isinstance(out['booster'], dxgb.Booster)
assert len(out['history']['validation']['rmse']) == 2
assert isinstance(predictions, np.ndarray)
assert predictions.shape[0] == 1
parameters = {
'tree_method': 'gpu_hist',
'verbosity': 3,
'debug_synchronize': True
}
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
kRows, kCols = 1, 97
X = dd.from_array(np.random.randn(kRows, kCols))
y = dd.from_array(np.random.rand(kRows))
dtrain = dxgb.DaskDMatrix(client, X, y)
out = dxgb.train(client,
parameters,
dtrain=dtrain,
evals=[(dtrain, 'validation')],
num_boost_round=2)
predictions = dxgb.predict(client=client,
model=out,
data=dtrain).compute()
_check_outputs(out, predictions)
# train has more rows than evals
valid = dtrain
kRows += 1
X = dd.from_array(np.random.randn(kRows, kCols))
y = dd.from_array(np.random.rand(kRows))
dtrain = dxgb.DaskDMatrix(client, X, y)
out = dxgb.train(client,
parameters,
dtrain=dtrain,
evals=[(valid, 'validation')],
num_boost_round=2)
predictions = dxgb.predict(client=client,
model=out,
data=valid).compute()
_check_outputs(out, predictions)
def test_dask_dataframe(self):
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
import cupy as cp
cp.cuda.runtime.setDevice(0)
X, y = generate_array()
X = dd.from_dask_array(X)
y = dd.from_dask_array(y)
X = X.map_partitions(cudf.from_pandas)
y = y.map_partitions(cudf.from_pandas)
dtrain = dxgb.DaskDMatrix(client, X, y)
out = dxgb.train(client, {
'tree_method': 'gpu_hist',
'debug_synchronize': True
},
dtrain=dtrain,
evals=[(dtrain, 'X')],
num_boost_round=4)
assert isinstance(out['booster'], dxgb.Booster)
assert len(out['history']['X']['rmse']) == 4
predictions = dxgb.predict(client, out, dtrain).compute()
assert isinstance(predictions, np.ndarray)
series_predictions = dxgb.inplace_predict(client, out, X)
assert isinstance(series_predictions, dd.Series)
series_predictions = series_predictions.compute()
single_node = out['booster'].predict(
xgboost.DMatrix(X.compute()))
cp.testing.assert_allclose(single_node, predictions)
np.testing.assert_allclose(single_node,
series_predictions.to_array())
predt = dxgb.predict(client, out, X)
assert isinstance(predt, dd.Series)
def is_df(part):
assert isinstance(part, cudf.DataFrame), part
return part
predt.map_partitions(is_df,
meta=dd.utils.make_meta(
{'prediction': 'f4'}))
cp.testing.assert_allclose(predt.values.compute(), single_node)
def test_dask_dataframe(client):
X, y = generate_array()
X = dd.from_dask_array(X)
y = dd.from_dask_array(y)
X = X.map_partitions(cudf.from_pandas)
y = y.map_partitions(cudf.from_pandas)
dtrain = dxgb.DaskDMatrix(client, X, y)
out = dxgb.train(client, {'tree_method': 'gpu_hist'},
dtrain=dtrain,
evals=[(dtrain, 'X')],
num_boost_round=2)
assert isinstance(out['booster'], dxgb.Booster)
assert len(out['history']['X']['rmse']) == 2
def test_dask_dataframe(self):
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
X, y = generate_array()
X = dd.from_dask_array(X)
y = dd.from_dask_array(y)
X = X.map_partitions(cudf.from_pandas)
y = y.map_partitions(cudf.from_pandas)
dtrain = dxgb.DaskDMatrix(client, X, y)
out = dxgb.train(client, {'tree_method': 'gpu_hist'},
dtrain=dtrain,
evals=[(dtrain, 'X')],
num_boost_round=2)
assert isinstance(out['booster'], dxgb.Booster)
assert len(out['history']['X']['rmse']) == 2
predictions = dxgb.predict(client, out, dtrain).compute()
assert isinstance(predictions, np.ndarray)