def run_with_dask_dataframe(DMatrixT: Type, client: Client) -> None:
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 = DMatrixT(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)
assert isinstance(predictions.compute(), np.ndarray)
series_predictions = dxgb.inplace_predict(client, out, X)
assert isinstance(series_predictions, dd.Series)
single_node = out['booster'].predict(xgboost.DMatrix(X.compute()))
cp.testing.assert_allclose(single_node, predictions.compute())
np.testing.assert_allclose(single_node,
series_predictions.compute().to_array())
predt = dxgb.predict(client, out, X)
assert isinstance(predt, dd.Series)
T = TypeVar('T')
def is_df(part: T) -> T:
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)
# Make sure the output can be integrated back to original dataframe
X["predict"] = predictions
X["inplace_predict"] = series_predictions
has_null = X.isnull().values.any().compute()
assert bool(has_null) is False
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 run_with_dask_array(DMatrixT, 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 = DMatrixT(client, X, y)
out = dxgb.train(client, {'tree_method': 'gpu_hist',
'debug_synchronize': True},
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_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_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_empty_partition(self,
local_cuda_cluster: LocalCUDACluster) -> None:
import dask_cudf
import cudf
import cupy
with Client(local_cuda_cluster) as client:
mult = 100
df = cudf.DataFrame({
"a": [1, 2, 3, 4, 5.1] * mult,
"b": [10, 15, 29.3, 30, 31] * mult,
"y": [10, 20, 30, 40., 50] * mult,
})
parameters = {"tree_method": "gpu_hist", "debug_synchronize": True}
empty = df.iloc[:0]
ddf = dask_cudf.concat(
[dask_cudf.from_cudf(empty, npartitions=1)] +
[dask_cudf.from_cudf(df, npartitions=3)] +
[dask_cudf.from_cudf(df, npartitions=3)])
X = ddf[ddf.columns.difference(["y"])]
y = ddf[["y"]]
dtrain = dxgb.DaskDeviceQuantileDMatrix(client, X, y)
bst_empty = xgb.dask.train(client,
parameters,
dtrain,
evals=[(dtrain, "train")])
predt_empty = dxgb.predict(client, bst_empty, X).compute().values
ddf = dask_cudf.concat([dask_cudf.from_cudf(df, npartitions=3)] +
[dask_cudf.from_cudf(df, npartitions=3)])
X = ddf[ddf.columns.difference(["y"])]
y = ddf[["y"]]
dtrain = dxgb.DaskDeviceQuantileDMatrix(client, X, y)
bst = xgb.dask.train(client,
parameters,
dtrain,
evals=[(dtrain, "train")])
predt = dxgb.predict(client, bst, X).compute().values
cupy.testing.assert_allclose(predt, predt_empty)
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
predictions = dxgb.predict(out, dtrain)
predictions = predictions.compute()