class TestDistributedGPU(unittest.TestCase):
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_cudf())
@pytest.mark.skipif(**tm.no_dask_cudf())
@pytest.mark.skipif(**tm.no_dask_cuda())
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)
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
def test_empty_dmatrix(self):
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
parameters = {'tree_method': 'gpu_hist'}
run_empty_dmatrix(client, parameters)
class TestWithDask:
def run_updater_test(self, client, params, num_rounds, dataset,
tree_method):
params['tree_method'] = tree_method
params = dataset.set_params(params)
# 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 = xgb.dask.DaskDMatrix(client, data=X, label=y, weight=w)
history = xgb.dask.train(client,
params=params,
dtrain=m,
num_boost_round=num_rounds,
evals=[(m, 'train')])['history']
note(history)
history = history['train'][dataset.metric]
assert tm.non_increasing(history)
# Make sure that it's decreasing
assert history[-1] < history[0]
@given(params=hist_parameter_strategy, dataset=tm.dataset_strategy)
@settings(deadline=None)
def test_hist(self, params, dataset, client):
num_rounds = 30
self.run_updater_test(client, params, num_rounds, dataset, 'hist')
@given(params=exact_parameter_strategy, dataset=tm.dataset_strategy)
@settings(deadline=None)
def test_approx(self, client, params, dataset):
num_rounds = 30
self.run_updater_test(client, params, num_rounds, dataset, 'approx')
def run_quantile(self, name):
if sys.platform.startswith("win"):
pytest.skip("Skipping dask tests on Windows")
exe = None
for possible_path in {
'./testxgboost', './build/testxgboost', '../build/testxgboost',
'../cpu-build/testxgboost'
}:
if os.path.exists(possible_path):
exe = possible_path
if exe is None:
return
test = "--gtest_filter=Quantile." + name
def runit(worker_addr, rabit_args):
port = None
# setup environment for running the c++ part.
for arg in rabit_args:
if arg.decode('utf-8').startswith('DMLC_TRACKER_PORT'):
port = arg.decode('utf-8')
port = port.split('=')
env = os.environ.copy()
env[port[0]] = port[1]
return subprocess.run([exe, test], env=env, capture_output=True)
with LocalCluster(n_workers=4) as cluster:
with Client(cluster) as client:
workers = list(xgb.dask._get_client_workers(client).keys())
rabit_args = client.sync(xgb.dask._get_rabit_args, workers,
client)
futures = client.map(runit,
workers,
pure=False,
workers=workers,
rabit_args=rabit_args)
results = client.gather(futures)
for ret in results:
msg = ret.stdout.decode('utf-8')
assert msg.find('1 test from Quantile') != -1, msg
assert ret.returncode == 0, msg
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.gtest
def test_quantile_basic(self):
self.run_quantile('DistributedBasic')
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.gtest
def test_quantile(self):
self.run_quantile('Distributed')
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.gtest
def test_quantile_same_on_all_workers(self):
self.run_quantile('SameOnAllWorkers')
import testing as tm
import pytest
import xgboost as xgb
import sys
import numpy as np
import json
import asyncio
from sklearn.datasets import make_classification
import os
import subprocess
from hypothesis import given, settings, note
from test_updaters import hist_parameter_strategy, exact_parameter_strategy
if sys.platform.startswith("win"):
pytest.skip("Skipping dask tests on Windows", allow_module_level=True)
if tm.no_dask()['condition']:
pytest.skip(msg=tm.no_dask()['reason'], allow_module_level=True)
try:
from distributed import LocalCluster, Client, get_client
from distributed.utils_test import client, loop, cluster_fixture
import dask.dataframe as dd
import dask.array as da
from xgboost.dask import DaskDMatrix
import dask
except ImportError:
LocalCluster = None
Client = None
get_client = None
client = None
loop = None
class TestDistributedGPU(unittest.TestCase):
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_cudf())
@pytest.mark.skipif(**tm.no_dask_cudf())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
def test_dask_dataframe(self):
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
run_with_dask_dataframe(dxgb.DaskDMatrix, client)
run_with_dask_dataframe(dxgb.DaskDeviceQuantileDMatrix, client)
@given(parameter_strategy, strategies.integers(1, 20),
tm.dataset_strategy)
@settings(deadline=duration(seconds=120))
@pytest.mark.mgpu
def test_gpu_hist(self, params, num_rounds, dataset):
with LocalCUDACluster(n_workers=2) as cluster:
with Client(cluster) as client:
run_gpu_hist(params, num_rounds, dataset, dxgb.DaskDMatrix,
client)
run_gpu_hist(params, num_rounds, dataset,
dxgb.DaskDeviceQuantileDMatrix, client)
@pytest.mark.skipif(**tm.no_cupy())
@pytest.mark.mgpu
def test_dask_array(self):
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
run_with_dask_array(dxgb.DaskDMatrix, client)
run_with_dask_array(dxgb.DaskDeviceQuantileDMatrix, client)
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
def test_empty_dmatrix(self):
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
parameters = {'tree_method': 'gpu_hist',
'debug_synchronize': True}
run_empty_dmatrix_reg(client, parameters)
run_empty_dmatrix_cls(client, parameters)
def run_quantile(self, name):
if sys.platform.startswith("win"):
pytest.skip("Skipping dask tests on Windows")
exe = None
for possible_path in {'./testxgboost', './build/testxgboost',
'../build/testxgboost', '../gpu-build/testxgboost'}:
if os.path.exists(possible_path):
exe = possible_path
assert exe, 'No testxgboost executable found.'
test = "--gtest_filter=GPUQuantile." + name
def runit(worker_addr, rabit_args):
port = None
# setup environment for running the c++ part.
for arg in rabit_args:
if arg.decode('utf-8').startswith('DMLC_TRACKER_PORT'):
port = arg.decode('utf-8')
port = port.split('=')
env = os.environ.copy()
env[port[0]] = port[1]
return subprocess.run([exe, test], env=env, stdout=subprocess.PIPE)
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
workers = list(dxgb._get_client_workers(client).keys())
rabit_args = client.sync(dxgb._get_rabit_args, workers, client)
futures = client.map(runit,
workers,
pure=False,
workers=workers,
rabit_args=rabit_args)
results = client.gather(futures)
for ret in results:
msg = ret.stdout.decode('utf-8')
assert msg.find('1 test from GPUQuantile') != -1, msg
assert ret.returncode == 0, msg
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.mgpu
@pytest.mark.gtest
def test_quantile_basic(self):
self.run_quantile('AllReduceBasic')
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.mgpu
@pytest.mark.gtest
def test_quantile_same_on_all_workers(self):
self.run_quantile('SameOnAllWorkers')
class TestDistributedGPU:
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_cudf())
@pytest.mark.skipif(**tm.no_dask_cudf())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
def test_dask_dataframe(self, local_cuda_cluster: LocalCUDACluster) -> None:
with Client(local_cuda_cluster) as client:
run_with_dask_dataframe(dxgb.DaskDMatrix, client)
run_with_dask_dataframe(dxgb.DaskDeviceQuantileDMatrix, client)
@given(
params=parameter_strategy,
num_rounds=strategies.integers(1, 20),
dataset=tm.dataset_strategy,
)
@settings(deadline=duration(seconds=120), suppress_health_check=suppress)
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.skipif(**tm.no_cupy())
@pytest.mark.parametrize(
"local_cuda_cluster", [{"n_workers": 2}], indirect=["local_cuda_cluster"]
)
@pytest.mark.mgpu
def test_gpu_hist(
self,
params: Dict,
num_rounds: int,
dataset: tm.TestDataset,
local_cuda_cluster: LocalCUDACluster,
) -> None:
with Client(local_cuda_cluster) as client:
run_gpu_hist(params, num_rounds, dataset, dxgb.DaskDMatrix, client)
run_gpu_hist(
params, num_rounds, dataset, dxgb.DaskDeviceQuantileDMatrix, client
)
@pytest.mark.skipif(**tm.no_cupy())
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
def test_dask_array(self, local_cuda_cluster: LocalCUDACluster) -> None:
with Client(local_cuda_cluster) as client:
run_with_dask_array(dxgb.DaskDMatrix, client)
run_with_dask_array(dxgb.DaskDeviceQuantileDMatrix, client)
@pytest.mark.skipif(**tm.no_cupy())
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
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
@pytest.mark.skipif(**tm.no_cudf())
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.parametrize("model", ["boosting"])
def test_dask_classifier(
self, model: str, local_cuda_cluster: LocalCUDACluster
) -> None:
import dask_cudf
with Client(local_cuda_cluster) as client:
X_, y_, w_ = generate_array(with_weights=True)
y_ = (y_ * 10).astype(np.int32)
X = dask_cudf.from_dask_dataframe(dd.from_dask_array(X_))
y = dask_cudf.from_dask_dataframe(dd.from_dask_array(y_))
w = dask_cudf.from_dask_dataframe(dd.from_dask_array(w_))
run_dask_classifier(X, y, w, model, client, 10)
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
def test_empty_dmatrix(self, local_cuda_cluster: LocalCUDACluster) -> None:
with Client(local_cuda_cluster) as client:
parameters = {'tree_method': 'gpu_hist',
'debug_synchronize': True}
run_empty_dmatrix_reg(client, parameters)
run_empty_dmatrix_cls(client, parameters)
def test_empty_dmatrix_auc(self, local_cuda_cluster: LocalCUDACluster) -> None:
with Client(local_cuda_cluster) as client:
n_workers = len(_get_client_workers(client))
run_empty_dmatrix_auc(client, "gpu_hist", n_workers)
def test_auc(self, local_cuda_cluster: LocalCUDACluster) -> None:
with Client(local_cuda_cluster) as client:
run_auc(client, "gpu_hist")
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_interface_consistency(self) -> None:
sig = OrderedDict(signature(dxgb.DaskDMatrix).parameters)
del sig["client"]
ddm_names = list(sig.keys())
sig = OrderedDict(signature(dxgb.DaskDeviceQuantileDMatrix).parameters)
del sig["client"]
del sig["max_bin"]
ddqdm_names = list(sig.keys())
assert len(ddm_names) == len(ddqdm_names)
# between dask
for i in range(len(ddm_names)):
assert ddm_names[i] == ddqdm_names[i]
sig = OrderedDict(signature(xgb.DMatrix).parameters)
del sig["nthread"] # no nthread in dask
dm_names = list(sig.keys())
sig = OrderedDict(signature(xgb.DeviceQuantileDMatrix).parameters)
del sig["nthread"]
del sig["max_bin"]
dqdm_names = list(sig.keys())
# between single node
assert len(dm_names) == len(dqdm_names)
for i in range(len(dm_names)):
assert dm_names[i] == dqdm_names[i]
# ddm <-> dm
for i in range(len(ddm_names)):
assert ddm_names[i] == dm_names[i]
# dqdm <-> ddqdm
for i in range(len(ddqdm_names)):
assert ddqdm_names[i] == dqdm_names[i]
sig = OrderedDict(signature(xgb.XGBRanker.fit).parameters)
ranker_names = list(sig.keys())
sig = OrderedDict(signature(xgb.dask.DaskXGBRanker.fit).parameters)
dranker_names = list(sig.keys())
for rn, drn in zip(ranker_names, dranker_names):
assert rn == drn
def run_quantile(self, name: str, local_cuda_cluster: LocalCUDACluster) -> None:
if sys.platform.startswith("win"):
pytest.skip("Skipping dask tests on Windows")
exe = None
for possible_path in {'./testxgboost', './build/testxgboost',
'../build/testxgboost', '../gpu-build/testxgboost'}:
if os.path.exists(possible_path):
exe = possible_path
assert exe, 'No testxgboost executable found.'
test = "--gtest_filter=GPUQuantile." + name
def runit(
worker_addr: str, rabit_args: List[bytes]
) -> subprocess.CompletedProcess:
port_env = ''
# setup environment for running the c++ part.
for arg in rabit_args:
if arg.decode('utf-8').startswith('DMLC_TRACKER_PORT'):
port_env = arg.decode('utf-8')
port = port_env.split('=')
env = os.environ.copy()
env[port[0]] = port[1]
return subprocess.run([str(exe), test], env=env, stdout=subprocess.PIPE)
with Client(local_cuda_cluster) as client:
workers = _get_client_workers(client)
rabit_args = client.sync(dxgb._get_rabit_args, workers, client)
futures = client.map(runit,
workers,
pure=False,
workers=workers,
rabit_args=rabit_args)
results = client.gather(futures)
for ret in results:
msg = ret.stdout.decode('utf-8')
assert msg.find('1 test from GPUQuantile') != -1, msg
assert ret.returncode == 0, msg
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
@pytest.mark.gtest
def test_quantile_basic(self, local_cuda_cluster: LocalCUDACluster) -> None:
self.run_quantile('AllReduceBasic', local_cuda_cluster)
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
@pytest.mark.gtest
def test_quantile_same_on_all_workers(
self, local_cuda_cluster: LocalCUDACluster
) -> None:
self.run_quantile('SameOnAllWorkers', local_cuda_cluster)
m = await xgboost.dask.DaskDeviceQuantileDMatrix(client, X, y)
output = await xgboost.dask.train(client, {'tree_method': 'gpu_hist'},
dtrain=m)
with_m = await xgboost.dask.predict(client, output, m)
with_X = await xgboost.dask.predict(client, output, X)
inplace = await xgboost.dask.inplace_predict(client, output, X)
assert isinstance(with_m, da.Array)
assert isinstance(with_X, da.Array)
assert isinstance(inplace, da.Array)
cp.testing.assert_allclose(await client.compute(with_m),
await client.compute(with_X))
cp.testing.assert_allclose(await client.compute(with_m),
await client.compute(inplace))
client.shutdown()
return output
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.skipif(**tm.no_cupy())
@pytest.mark.mgpu
def test_with_asyncio(local_cuda_cluster: LocalCUDACluster) -> None:
with Client(local_cuda_cluster) as client:
address = client.scheduler.address
output = asyncio.run(run_from_dask_array_asyncio(address))
assert isinstance(output['booster'], xgboost.Booster)
assert isinstance(output['history'], dict)
class TestDistributedGPU(unittest.TestCase):
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_cudf())
@pytest.mark.skipif(**tm.no_dask_cudf())
@pytest.mark.skipif(**tm.no_dask_cuda())
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)
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
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)
class TestWithDask:
def test_global_config(self, client: "Client") -> None:
X, y, _ = generate_array()
xgb.config.set_config(verbosity=0)
dtrain = DaskDMatrix(client, X, y)
before_fname = './before_training-test_global_config'
after_fname = './after_training-test_global_config'
class TestCallback(xgb.callback.TrainingCallback):
def write_file(self, fname: str) -> None:
with open(fname, 'w') as fd:
fd.write(str(xgb.config.get_config()['verbosity']))
def before_training(self, model: xgb.Booster) -> xgb.Booster:
self.write_file(before_fname)
assert xgb.config.get_config()['verbosity'] == 0
return model
def after_training(self, model: xgb.Booster) -> xgb.Booster:
assert xgb.config.get_config()['verbosity'] == 0
return model
def before_iteration(self, model: xgb.Booster, epoch: int,
evals_log: Dict) -> bool:
assert xgb.config.get_config()['verbosity'] == 0
return False
def after_iteration(self, model: xgb.Booster, epoch: int,
evals_log: Dict) -> bool:
self.write_file(after_fname)
assert xgb.config.get_config()['verbosity'] == 0
return False
xgb.dask.train(client, {},
dtrain,
num_boost_round=4,
callbacks=[TestCallback()])['booster']
with open(before_fname, 'r') as before, open(after_fname,
'r') as after:
assert before.read() == '0'
assert after.read() == '0'
os.remove(before_fname)
os.remove(after_fname)
def run_updater_test(self, client: "Client", params: Dict, num_rounds: int,
dataset: tm.TestDataset, tree_method: str) -> None:
params['tree_method'] = tree_method
params = dataset.set_params(params)
# 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 = xgb.dask.DaskDMatrix(client, data=X, label=y, weight=w)
history = xgb.dask.train(client,
params=params,
dtrain=m,
num_boost_round=num_rounds,
evals=[(m, 'train')])['history']
note(history)
history = history['train'][dataset.metric]
assert tm.non_increasing(history)
# Make sure that it's decreasing
assert history[-1] < history[0]
@given(params=hist_parameter_strategy, dataset=tm.dataset_strategy)
@settings(deadline=None, suppress_health_check=suppress)
def test_hist(self, params: Dict, dataset: tm.TestDataset,
client: "Client") -> None:
num_rounds = 30
self.run_updater_test(client, params, num_rounds, dataset, 'hist')
@given(params=exact_parameter_strategy, dataset=tm.dataset_strategy)
@settings(deadline=None, suppress_health_check=suppress)
def test_approx(self, client: "Client", params: Dict,
dataset: tm.TestDataset) -> None:
num_rounds = 30
self.run_updater_test(client, params, num_rounds, dataset, 'approx')
def run_quantile(self, name: str) -> None:
if sys.platform.startswith("win"):
pytest.skip("Skipping dask tests on Windows")
exe: Optional[str] = None
for possible_path in {
'./testxgboost', './build/testxgboost', '../build/testxgboost',
'../cpu-build/testxgboost'
}:
if os.path.exists(possible_path):
exe = possible_path
if exe is None:
return
test = "--gtest_filter=Quantile." + name
def runit(worker_addr: str,
rabit_args: List[bytes]) -> subprocess.CompletedProcess:
port_env = ''
# setup environment for running the c++ part.
for arg in rabit_args:
if arg.decode('utf-8').startswith('DMLC_TRACKER_PORT'):
port_env = arg.decode('utf-8')
port = port_env.split('=')
env = os.environ.copy()
env[port[0]] = port[1]
return subprocess.run([str(exe), test],
env=env,
capture_output=True)
with LocalCluster(n_workers=4) as cluster:
with Client(cluster) as client:
workers = list(_get_client_workers(client).keys())
rabit_args = client.sync(xgb.dask._get_rabit_args,
len(workers), client)
futures = client.map(runit,
workers,
pure=False,
workers=workers,
rabit_args=rabit_args)
results = client.gather(futures)
for ret in results:
msg = ret.stdout.decode('utf-8')
assert msg.find('1 test from Quantile') != -1, msg
assert ret.returncode == 0, msg
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.gtest
def test_quantile_basic(self) -> None:
self.run_quantile('DistributedBasic')
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.gtest
def test_quantile(self) -> None:
self.run_quantile('Distributed')
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.gtest
def test_quantile_same_on_all_workers(self) -> None:
self.run_quantile('SameOnAllWorkers')
def test_n_workers(self) -> None:
with LocalCluster(n_workers=2) as cluster:
with Client(cluster) as client:
workers = list(_get_client_workers(client).keys())
from sklearn.datasets import load_breast_cancer
X, y = load_breast_cancer(return_X_y=True)
dX = client.submit(da.from_array, X,
workers=[workers[0]]).result()
dy = client.submit(da.from_array, y,
workers=[workers[0]]).result()
train = xgb.dask.DaskDMatrix(client, dX, dy)
dX = dd.from_array(X)
dX = client.persist(dX, workers={dX: workers[1]})
dy = dd.from_array(y)
dy = client.persist(dy, workers={dy: workers[1]})
valid = xgb.dask.DaskDMatrix(client, dX, dy)
merged = xgb.dask._get_workers_from_data(train,
evals=[(valid,
'Valid')])
assert len(merged) == 2
@pytest.mark.skipif(**tm.no_dask())
def test_feature_weights(self, client: "Client") -> None:
kRows = 1024
kCols = 64
X = da.random.random((kRows, kCols), chunks=(32, -1))
y = da.random.random(kRows, chunks=32)
fw = np.ones(shape=(kCols, ))
for i in range(kCols):
fw[i] *= float(i)
fw = da.from_array(fw)
poly_increasing = run_feature_weights(X,
y,
fw,
model=xgb.dask.DaskXGBRegressor)
fw = np.ones(shape=(kCols, ))
for i in range(kCols):
fw[i] *= float(kCols - i)
fw = da.from_array(fw)
poly_decreasing = run_feature_weights(X,
y,
fw,
model=xgb.dask.DaskXGBRegressor)
# Approxmated test, this is dependent on the implementation of random
# number generator in std library.
assert poly_increasing[0] > 0.08
assert poly_decreasing[0] < -0.08
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_sklearn())
def test_custom_objective(self, client: "Client") -> None:
from sklearn.datasets import load_boston
X, y = load_boston(return_X_y=True)
X, y = da.from_array(X), da.from_array(y)
rounds = 20
with tempfile.TemporaryDirectory() as tmpdir:
path = os.path.join(tmpdir, 'log')
def sqr(labels: np.ndarray,
predts: np.ndarray) -> Tuple[np.ndarray, np.ndarray]:
with open(path, 'a') as fd:
print('Running sqr', file=fd)
grad = predts - labels
hess = np.ones(shape=labels.shape[0])
return grad, hess
reg = xgb.dask.DaskXGBRegressor(n_estimators=rounds,
objective=sqr,
tree_method='hist')
reg.fit(X, y, eval_set=[(X, y)])
# Check the obj is ran for rounds.
with open(path, 'r') as fd:
out = fd.readlines()
assert len(out) == rounds
results_custom = reg.evals_result()
reg = xgb.dask.DaskXGBRegressor(n_estimators=rounds,
tree_method='hist')
reg.fit(X, y, eval_set=[(X, y)])
results_native = reg.evals_result()
np.testing.assert_allclose(results_custom['validation_0']['rmse'],
results_native['validation_0']['rmse'])
tm.non_increasing(results_native['validation_0']['rmse'])
def test_data_initialization(self) -> None:
'''Assert each worker has the correct amount of data, and DMatrix initialization doesn't
generate unnecessary copies of data.
'''
with LocalCluster(n_workers=2) as cluster:
with Client(cluster) as client:
X, y, _ = generate_array()
n_partitions = X.npartitions
m = xgb.dask.DaskDMatrix(client, X, y)
workers = list(_get_client_workers(client).keys())
rabit_args = client.sync(xgb.dask._get_rabit_args,
len(workers), client)
n_workers = len(workers)
def worker_fn(worker_addr: str, data_ref: Dict) -> None:
with xgb.dask.RabitContext(rabit_args):
local_dtrain = xgb.dask._dmatrix_from_list_of_parts(
**data_ref)
total = np.array([local_dtrain.num_row()])
total = xgb.rabit.allreduce(total, xgb.rabit.Op.SUM)
assert total[0] == kRows
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)
has_what = client.has_what()
cnt = 0
data = set()
for k, v in has_what.items():
for d in v:
cnt += 1
data.add(d)
assert len(data) == cnt
# Subtract the on disk resource from each worker
assert cnt - n_workers == n_partitions
def run_shap(self, X: Any, y: Any, params: Dict[str, Any],
client: "Client") -> None:
X, y = da.from_array(X), da.from_array(y)
Xy = xgb.dask.DaskDMatrix(client, X, y)
booster = xgb.dask.train(client, params, Xy,
num_boost_round=10)['booster']
test_Xy = xgb.dask.DaskDMatrix(client, X, y)
shap = xgb.dask.predict(client, booster, test_Xy,
pred_contribs=True).compute()
margin = xgb.dask.predict(client, booster, test_Xy,
output_margin=True).compute()
assert np.allclose(np.sum(shap, axis=len(shap.shape) - 1), margin,
1e-5, 1e-5)
def run_shap_cls_sklearn(self, X: Any, y: Any, client: "Client") -> None:
X, y = da.from_array(X), da.from_array(y)
cls = xgb.dask.DaskXGBClassifier()
cls.client = client
cls.fit(X, y)
booster = cls.get_booster()
test_Xy = xgb.dask.DaskDMatrix(client, X, y)
shap = xgb.dask.predict(client, booster, test_Xy,
pred_contribs=True).compute()
margin = xgb.dask.predict(client, booster, test_Xy,
output_margin=True).compute()
assert np.allclose(np.sum(shap, axis=len(shap.shape) - 1), margin,
1e-5, 1e-5)
def test_shap(self, client: "Client") -> None:
from sklearn.datasets import load_boston, load_digits
X, y = load_boston(return_X_y=True)
params: Dict[str, Any] = {'objective': 'reg:squarederror'}
self.run_shap(X, y, params, client)
X, y = load_digits(return_X_y=True)
params = {'objective': 'multi:softmax', 'num_class': 10}
self.run_shap(X, y, params, client)
params = {'objective': 'multi:softprob', 'num_class': 10}
self.run_shap(X, y, params, client)
self.run_shap_cls_sklearn(X, y, client)
def run_shap_interactions(self, X: Any, y: Any, params: Dict[str, Any],
client: "Client") -> None:
X, y = da.from_array(X), da.from_array(y)
Xy = xgb.dask.DaskDMatrix(client, X, y)
booster = xgb.dask.train(client, params, Xy,
num_boost_round=10)['booster']
test_Xy = xgb.dask.DaskDMatrix(client, X, y)
shap = xgb.dask.predict(client,
booster,
test_Xy,
pred_interactions=True).compute()
margin = xgb.dask.predict(client, booster, test_Xy,
output_margin=True).compute()
assert np.allclose(
np.sum(shap, axis=(len(shap.shape) - 1, len(shap.shape) - 2)),
margin, 1e-5, 1e-5)
def test_shap_interactions(self, client: "Client") -> None:
from sklearn.datasets import load_boston
X, y = load_boston(return_X_y=True)
params = {'objective': 'reg:squarederror'}
self.run_shap_interactions(X, y, params, client)
@pytest.mark.skipif(**tm.no_sklearn())
def test_sklearn_io(self, client: 'Client') -> None:
from sklearn.datasets import load_digits
X_, y_ = load_digits(return_X_y=True)
X, y = da.from_array(X_), da.from_array(y_)
cls = xgb.dask.DaskXGBClassifier(n_estimators=10)
cls.client = client
cls.fit(X, y)
predt_0 = cls.predict(X)
with tempfile.TemporaryDirectory() as tmpdir:
path = os.path.join(tmpdir, 'cls.json')
cls.save_model(path)
cls = xgb.dask.DaskXGBClassifier()
cls.load_model(path)
assert cls.n_classes_ == 10
predt_1 = cls.predict(X)
np.testing.assert_allclose(predt_0.compute(), predt_1.compute())
# Use single node to load
cls = xgb.XGBClassifier()
cls.load_model(path)
assert cls.n_classes_ == 10
predt_2 = cls.predict(X_)
np.testing.assert_allclose(predt_0.compute(), predt_2)
class TestDistributedGPU:
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_cudf())
@pytest.mark.skipif(**tm.no_dask_cudf())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
def test_dask_dataframe(self,
local_cuda_cluster: LocalCUDACluster) -> None:
with Client(local_cuda_cluster) as client:
run_with_dask_dataframe(dxgb.DaskDMatrix, client)
run_with_dask_dataframe(dxgb.DaskDeviceQuantileDMatrix, client)
@given(params=parameter_strategy,
num_rounds=strategies.integers(1, 20),
dataset=tm.dataset_strategy)
@settings(deadline=duration(seconds=120))
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.parametrize('local_cuda_cluster', [{
'n_workers': 2
}],
indirect=['local_cuda_cluster'])
@pytest.mark.mgpu
def test_gpu_hist(self, params: Dict, num_rounds: int,
dataset: tm.TestDataset,
local_cuda_cluster: LocalCUDACluster) -> None:
with Client(local_cuda_cluster) as client:
run_gpu_hist(params, num_rounds, dataset, dxgb.DaskDMatrix, client)
run_gpu_hist(params, num_rounds, dataset,
dxgb.DaskDeviceQuantileDMatrix, client)
@pytest.mark.skipif(**tm.no_cupy())
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
def test_dask_array(self, local_cuda_cluster: LocalCUDACluster) -> None:
with Client(local_cuda_cluster) as client:
run_with_dask_array(dxgb.DaskDMatrix, client)
run_with_dask_array(dxgb.DaskDeviceQuantileDMatrix, client)
@pytest.mark.skipif(**tm.no_cupy())
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
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
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
def test_empty_dmatrix(self, local_cuda_cluster: LocalCUDACluster) -> None:
with Client(local_cuda_cluster) as client:
parameters = {'tree_method': 'gpu_hist', 'debug_synchronize': True}
run_empty_dmatrix_reg(client, parameters)
run_empty_dmatrix_cls(client, parameters)
def run_quantile(self, name: str,
local_cuda_cluster: LocalCUDACluster) -> None:
if sys.platform.startswith("win"):
pytest.skip("Skipping dask tests on Windows")
exe = None
for possible_path in {
'./testxgboost', './build/testxgboost', '../build/testxgboost',
'../gpu-build/testxgboost'
}:
if os.path.exists(possible_path):
exe = possible_path
assert exe, 'No testxgboost executable found.'
test = "--gtest_filter=GPUQuantile." + name
def runit(worker_addr: str,
rabit_args: List[bytes]) -> subprocess.CompletedProcess:
port_env = ''
# setup environment for running the c++ part.
for arg in rabit_args:
if arg.decode('utf-8').startswith('DMLC_TRACKER_PORT'):
port_env = arg.decode('utf-8')
port = port_env.split('=')
env = os.environ.copy()
env[port[0]] = port[1]
return subprocess.run([str(exe), test],
env=env,
stdout=subprocess.PIPE)
with Client(local_cuda_cluster) as client:
workers = list(_get_client_workers(client).keys())
rabit_args = client.sync(dxgb._get_rabit_args, workers, client)
futures = client.map(runit,
workers,
pure=False,
workers=workers,
rabit_args=rabit_args)
results = client.gather(futures)
for ret in results:
msg = ret.stdout.decode('utf-8')
assert msg.find('1 test from GPUQuantile') != -1, msg
assert ret.returncode == 0, msg
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
@pytest.mark.gtest
def test_quantile_basic(self,
local_cuda_cluster: LocalCUDACluster) -> None:
self.run_quantile('AllReduceBasic', local_cuda_cluster)
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
@pytest.mark.gtest
def test_quantile_same_on_all_workers(
self, local_cuda_cluster: LocalCUDACluster) -> None:
self.run_quantile('SameOnAllWorkers', local_cuda_cluster)
import pytest
import xgboost as xgb
import numpy as np
import sys
if sys.platform.startswith("win"):
pytest.skip("Skipping dask tests on Windows", allow_module_level=True)
try:
from distributed.utils_test import client, loop, cluster_fixture
import dask.dataframe as dd
import dask.array as da
except ImportError:
pass
pytestmark = pytest.mark.skipif(**tm.no_dask())
def run_train():
# Contains one label equal to rank
dmat = xgb.DMatrix([[0]], label=[xgb.rabit.get_rank()])
bst = xgb.train({"eta": 1.0, "lambda": 0.0}, dmat, 1)
pred = bst.predict(dmat)
expected_result = np.average(range(xgb.rabit.get_world_size()))
assert all(p == expected_result for p in pred)
def test_train(client):
# Train two workers, the first has label 0, the second has label 1
# If they build the model together the output should be 0.5
xgb.dask.run(client, run_train)
class TestDistributedGPU(unittest.TestCase):
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_cudf())
@pytest.mark.skipif(**tm.no_dask_cudf())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
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'},
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)
@pytest.mark.skipif(**tm.no_cupy())
@pytest.mark.mgpu
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)
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
def test_empty_dmatrix(self):
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
parameters = {'tree_method': 'gpu_hist'}
run_empty_dmatrix(client, parameters)
import sys
import logging
import pytest
import sklearn
sys.path.append("tests/python")
import testing as tm
if tm.no_dask()["condition"]:
pytest.skip(msg=tm.no_spark()["reason"], allow_module_level=True)
if sys.platform.startswith("win"):
pytest.skip("Skipping PySpark tests on Windows", allow_module_level=True)
from pyspark.sql import SparkSession
from pyspark.ml.linalg import Vectors
from xgboost.spark import SparkXGBRegressor, SparkXGBClassifier
@pytest.fixture(scope="module", autouse=True)
def spark_session_with_gpu():
spark_config = {
"spark.master":
"local-cluster[1, 4, 1024]",
"spark.python.worker.reuse":
"false",
"spark.driver.host":
"127.0.0.1",
"spark.task.maxFailures":
"1",
"spark.sql.execution.pyspark.udf.simplifiedTraceback.enabled":
class TestDistributedGPU(unittest.TestCase):
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_cudf())
@pytest.mark.skipif(**tm.no_dask_cudf())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
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)
@given(parameter_strategy, strategies.integers(1, 20), tm.dataset_strategy)
@settings(deadline=None)
@pytest.mark.mgpu
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])
@pytest.mark.skipif(**tm.no_cupy())
@pytest.mark.mgpu
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',
'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)
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.skipif(**tm.no_dask_cuda())
@pytest.mark.mgpu
def test_empty_dmatrix(self):
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
parameters = {
'tree_method': 'gpu_hist',
'debug_synchronize': True
}
run_empty_dmatrix(client, parameters)
def run_quantile(self, name):
if sys.platform.startswith("win"):
pytest.skip("Skipping dask tests on Windows")
exe = None
for possible_path in {
'./testxgboost', './build/testxgboost', '../build/testxgboost',
'../gpu-build/testxgboost'
}:
if os.path.exists(possible_path):
exe = possible_path
assert exe, 'No testxgboost executable found.'
test = "--gtest_filter=GPUQuantile." + name
def runit(worker_addr, rabit_args):
port = None
# setup environment for running the c++ part.
for arg in rabit_args:
if arg.decode('utf-8').startswith('DMLC_TRACKER_PORT'):
port = arg.decode('utf-8')
port = port.split('=')
env = os.environ.copy()
env[port[0]] = port[1]
return subprocess.run([exe, test], env=env, stdout=subprocess.PIPE)
with LocalCUDACluster() as cluster:
with Client(cluster) as client:
workers = list(dxgb._get_client_workers(client).keys())
rabit_args = dxgb._get_rabit_args(workers, client)
futures = client.map(runit,
workers,
pure=False,
workers=workers,
rabit_args=rabit_args)
results = client.gather(futures)
for ret in results:
msg = ret.stdout.decode('utf-8')
assert msg.find('1 test from GPUQuantile') != -1, msg
assert ret.returncode == 0, msg
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.mgpu
@pytest.mark.gtest
def test_quantile_basic(self):
self.run_quantile('AllReduceBasic')
@pytest.mark.skipif(**tm.no_dask())
@pytest.mark.mgpu
@pytest.mark.gtest
def test_quantile_same_on_all_workers(self):
self.run_quantile('SameOnAllWorkers')
