7e24a8d245
* Add a readme with link to doc. * Add more comments in the demonstrations code. * Workaround https://github.com/dask/distributed/issues/3081 .
45 lines
1.5 KiB
Python
45 lines
1.5 KiB
Python
from dask_cuda import LocalCUDACluster
|
|
from dask.distributed import Client
|
|
from dask import array as da
|
|
import xgboost as xgb
|
|
from xgboost.dask import DaskDMatrix
|
|
|
|
|
|
def main(client):
|
|
n = 100
|
|
m = 100000
|
|
partition_size = 1000
|
|
X = da.random.random((m, n), partition_size)
|
|
y = da.random.random(m, partition_size)
|
|
|
|
# DaskDMatrix acts like normal DMatrix, works as a proxy for local
|
|
# DMatrix scatter around workers.
|
|
dtrain = DaskDMatrix(client, X, y)
|
|
|
|
# Use train method from xgboost.dask instead of xgboost. This
|
|
# distributed version of train returns a dictionary containing the
|
|
# resulting booster and evaluation history obtained from
|
|
# evaluation metrics.
|
|
output = xgb.dask.train(client,
|
|
{'verbosity': 2,
|
|
'nthread': 1,
|
|
'tree_method': 'gpu_hist'},
|
|
dtrain,
|
|
num_boost_round=4, evals=[(dtrain, 'train')])
|
|
bst = output['booster']
|
|
history = output['history']
|
|
|
|
# you can pass output directly into `predict` too.
|
|
prediction = xgb.dask.predict(client, bst, dtrain)
|
|
print('Evaluation history:', history)
|
|
return prediction
|
|
|
|
|
|
if __name__ == '__main__':
|
|
# `LocalCUDACluster` is used for assigning GPU to XGBoost processes. Here
|
|
# `n_workers` represents the number of GPUs since we use one GPU per worker
|
|
# process.
|
|
with LocalCUDACluster(n_workers=2, threads_per_worker=1) as cluster:
|
|
with Client(cluster) as client:
|
|
main(client)
|