Example of training with Dask on CPU

from dask import array as da
from dask.distributed import Client, LocalCluster

import xgboost as xgb
from xgboost.dask import DaskDMatrix

def main(client):
    # generate some random data for demonstration
    m = 100000
    n = 100
    X = da.random.random(size=(m, n), chunks=100)
    y = da.random.random(size=(m,), chunks=100)

    # 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(
        {"verbosity": 1, "tree_method": "hist"},
        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__":
    # or use other clusters for scaling
    with LocalCluster(n_workers=7, threads_per_worker=4) as cluster:
        with Client(cluster) as client:

Total running time of the script: (0 minutes 0.000 seconds)

Gallery generated by Sphinx-Gallery