Merge branch 'master' into sync-2024Jan24

demo/aft_survival/aft_survival_viz_demo.py

@@ -6,6 +6,7 @@ This demo uses 1D toy data and visualizes how XGBoost fits a tree ensemble. The
 model starts out as a flat line and evolves into a step function in order to account for
 all ranged labels.
 """
+
 import matplotlib.pyplot as plt
 import numpy as np
 

demo/dask/cpu_training.py

@@ -3,6 +3,7 @@ Example of training with Dask on CPU
 ====================================
 
 """
+
 from dask import array as da
 from dask.distributed import Client, LocalCluster
 
@@ -14,8 +15,9 @@ 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)
+    rng = da.random.default_rng(1)
+    X = rng.normal(size=(m, n))
+    y = X.sum(axis=1)
 
     # DaskDMatrix acts like normal DMatrix, works as a proxy for local
     # DMatrix scatter around workers.

demo/dask/dask_callbacks.py

@@ -2,6 +2,7 @@
 Example of using callbacks with Dask
 ====================================
 """
+
 import numpy as np
 from dask.distributed import Client, LocalCluster
 from dask_ml.datasets import make_regression

demo/dask/gpu_training.py

@@ -2,6 +2,8 @@
 Example of training with Dask on GPU
 ====================================
 """
+
+import cupy as cp
 import dask_cudf
 from dask import array as da
 from dask import dataframe as dd
@@ -72,10 +74,12 @@ if __name__ == "__main__":
     with LocalCUDACluster(n_workers=2, threads_per_worker=4) as cluster:
         with Client(cluster) as client:
             # generate some random data for demonstration
+            rng = da.random.default_rng(1)
+
             m = 100000
             n = 100
-            X = da.random.random(size=(m, n), chunks=10000)
-            y = da.random.random(size=(m,), chunks=10000)
+            X = rng.normal(size=(m, n))
+            y = X.sum(axis=1)
 
             print("Using DaskQuantileDMatrix")
             from_ddqdm = using_quantile_device_dmatrix(client, X, y)

demo/dask/sklearn_cpu_training.py

@@ -2,6 +2,7 @@
 Use scikit-learn regressor interface with CPU histogram tree method
 ===================================================================
 """
+
 from dask import array as da
 from dask.distributed import Client, LocalCluster
 

demo/guide-python/callbacks.py

@@ -4,6 +4,7 @@ Demo for using and defining callback functions
 
     .. versionadded:: 1.3.0
 """
+
 import argparse
 import os
 import tempfile

demo/guide-python/cat_pipeline.py

@@ -13,6 +13,7 @@ See Also
 - :ref:`sphx_glr_python_examples_cat_in_the_dat.py`
 
 """
+
 from typing import List, Tuple
 
 import numpy as np

demo/guide-python/categorical.py

@@ -17,6 +17,7 @@ See Also
 - :ref:`sphx_glr_python_examples_cat_pipeline.py`
 
 """
+
 from typing import Tuple
 
 import numpy as np

demo/guide-python/external_memory.py

@@ -11,6 +11,7 @@ instead of Quantile DMatrix.  The feature is not ready for production use yet.
 See :doc:`the tutorial </tutorials/external_memory>` for more details.
 
 """
+
 import os
 import tempfile
 from typing import Callable, List, Tuple

demo/guide-python/individual_trees.py

@@ -2,6 +2,7 @@
 Demo for prediction using individual trees and model slices
 ===========================================================
 """
+
 import os
 
 import numpy as np

demo/guide-python/learning_to_rank.py

@@ -15,6 +15,7 @@ position debiasing training.
 For an overview of learning to rank in XGBoost, please see
 :doc:`Learning to Rank </tutorials/learning_to_rank>`.
 """
+
 from __future__ import annotations
 
 import argparse

demo/guide-python/quantile_regression.py

@@ -13,6 +13,7 @@ https://scikit-learn.org/stable/auto_examples/ensemble/plot_gradient_boosting_qu
     crossing can happen due to limitation in the algorithm.
 
 """
+
 import argparse
 from typing import Dict
 

demo/guide-python/sklearn_examples.py

@@ -9,6 +9,7 @@ Created on 1 Apr 2015
 
 @author: Jamie Hall
 """
+
 import pickle
 
 import numpy as np

demo/guide-python/sklearn_parallel.py

@@ -2,6 +2,7 @@
 Demo for using xgboost with sklearn
 ===================================
 """
+
 import multiprocessing
 
 from sklearn.datasets import fetch_california_housing

demo/guide-python/spark_estimator_examples.py

@@ -4,6 +4,7 @@ Collection of examples for using xgboost.spark estimator interface
 
 @author: Weichen Xu
 """
+
 import sklearn.datasets
 from pyspark.ml.evaluation import MulticlassClassificationEvaluator, RegressionEvaluator
 from pyspark.ml.linalg import Vectors

demo/rmm_plugin/rmm_mgpu_with_dask.py

@@ -2,6 +2,7 @@
 Using rmm with Dask
 ===================
 """
+
 import dask
 from dask.distributed import Client
 from dask_cuda import LocalCUDACluster

demo/rmm_plugin/rmm_singlegpu.py

@@ -2,6 +2,7 @@
 Using rmm on a single node device
 =================================
 """
+
 import rmm
 from sklearn.datasets import make_classification