Fix SketchBatchNumElements test to clamp with kIntMax

.gitattributes

@@ -15,4 +15,4 @@
 
 *.rst text eol=lf
 *.md  text eol=lf
-*.csv text eol=lf
+*.csv text eol=lf

.gitignore

@@ -165,4 +165,4 @@ Rplots.pdf
 
 # nsys
 *.nsys-rep
-rmm_log.dev*
+rmm_log.dev*

CONTRIBUTORS.md

@@ -2,9 +2,9 @@ Contributors of DMLC/XGBoost
 ============================
 XGBoost has been developed and used by a group of active community. Everyone is more than welcomed to is a great way to make the project better and more accessible to more users.
 
-Project Management Committee(PMC) 
+Project Management Committee(PMC)
 ----------
-The Project Management Committee(PMC) consists group of active committers that moderate the discussion, manage the project release, and proposes new committer/PMC members. 
+The Project Management Committee(PMC) consists group of active committers that moderate the discussion, manage the project release, and proposes new committer/PMC members.
 
 * [Tianqi Chen](https://github.com/tqchen), University of Washington
   - Tianqi is a Ph.D. student working on large-scale machine learning. He is the creator of the project.
@@ -19,7 +19,7 @@ The Project Management Committee(PMC) consists group of active committers that m
 * [Hyunsu Cho](http://hyunsu-cho.io/), NVIDIA
   - Hyunsu is the maintainer of the XGBoost Python package. He also manages the Jenkins continuous integration system (https://xgboost-ci.net/). He is the initial author of the CPU 'hist' updater.
 * [Rory Mitchell](https://github.com/RAMitchell), University of Waikato
-  - Rory is a Ph.D. student at University of Waikato. He is the original creator of the GPU training algorithms. He improved the CMake build system and continuous integration. 
+  - Rory is a Ph.D. student at University of Waikato. He is the original creator of the GPU training algorithms. He improved the CMake build system and continuous integration.
 * [Hongliang Liu](https://github.com/phunterlau)
 
 

cmake/RPackageInstall.cmake.in

@@ -31,4 +31,4 @@ set(XGB_DEPS_SCRIPT
 check_call(COMMAND "${LIBR_EXECUTABLE}" -q -e "${XGB_DEPS_SCRIPT}")
 
 # Install the XGBoost R package
-check_call(COMMAND "${LIBR_EXECUTABLE}" CMD INSTALL --no-multiarch --build "${build_dir}/R-package")
+check_call(COMMAND "${LIBR_EXECUTABLE}" CMD INSTALL --no-multiarch --build "${build_dir}/R-package")

demo/aft_survival/aft_survival_demo.py

@@ -9,54 +9,63 @@
 
 import numpy as np
 import pandas as pd
-from sklearn.model_selection import ShuffleSplit
-
 import xgboost as xgb
+from sklearn.model_selection import ShuffleSplit
 
 # The Veterans' Administration Lung Cancer Trial
 # The Statistical Analysis of Failure Time Data by Kalbfleisch J. and Prentice R (1980)
 CURRENT_DIR = os.path.dirname(__file__)
-df = pd.read_csv(os.path.join(CURRENT_DIR, '../data/veterans_lung_cancer.csv'))
-print('Training data:')
+df = pd.read_csv(os.path.join(CURRENT_DIR, "../data/veterans_lung_cancer.csv"))
+print("Training data:")
 print(df)
 
 # Split features and labels
-y_lower_bound = df['Survival_label_lower_bound']
-y_upper_bound = df['Survival_label_upper_bound']
-X = df.drop(['Survival_label_lower_bound', 'Survival_label_upper_bound'], axis=1)
+y_lower_bound = df["Survival_label_lower_bound"]
+y_upper_bound = df["Survival_label_upper_bound"]
+X = df.drop(["Survival_label_lower_bound", "Survival_label_upper_bound"], axis=1)
 
 # Split data into training and validation sets
-rs = ShuffleSplit(n_splits=2, test_size=.7, random_state=0)
+rs = ShuffleSplit(n_splits=2, test_size=0.7, random_state=0)
 train_index, valid_index = next(rs.split(X))
 dtrain = xgb.DMatrix(X.values[train_index, :])
-dtrain.set_float_info('label_lower_bound', y_lower_bound[train_index])
-dtrain.set_float_info('label_upper_bound', y_upper_bound[train_index])
+dtrain.set_float_info("label_lower_bound", y_lower_bound[train_index])
+dtrain.set_float_info("label_upper_bound", y_upper_bound[train_index])
 dvalid = xgb.DMatrix(X.values[valid_index, :])
-dvalid.set_float_info('label_lower_bound', y_lower_bound[valid_index])
-dvalid.set_float_info('label_upper_bound', y_upper_bound[valid_index])
+dvalid.set_float_info("label_lower_bound", y_lower_bound[valid_index])
+dvalid.set_float_info("label_upper_bound", y_upper_bound[valid_index])
 
 # Train gradient boosted trees using AFT loss and metric
-params = {'verbosity': 0,
-          'objective': 'survival:aft',
-          'eval_metric': 'aft-nloglik',
-          'tree_method': 'hist',
-          'learning_rate': 0.05,
-          'aft_loss_distribution': 'normal',
-          'aft_loss_distribution_scale': 1.20,
-          'max_depth': 6,
-          'lambda': 0.01,
-          'alpha': 0.02}
-bst = xgb.train(params, dtrain, num_boost_round=10000,
-                evals=[(dtrain, 'train'), (dvalid, 'valid')],
-                early_stopping_rounds=50)
+params = {
+    "verbosity": 0,
+    "objective": "survival:aft",
+    "eval_metric": "aft-nloglik",
+    "tree_method": "hist",
+    "learning_rate": 0.05,
+    "aft_loss_distribution": "normal",
+    "aft_loss_distribution_scale": 1.20,
+    "max_depth": 6,
+    "lambda": 0.01,
+    "alpha": 0.02,
+}
+bst = xgb.train(
+    params,
+    dtrain,
+    num_boost_round=10000,
+    evals=[(dtrain, "train"), (dvalid, "valid")],
+    early_stopping_rounds=50,
+)
 
 # Run prediction on the validation set
-df = pd.DataFrame({'Label (lower bound)': y_lower_bound[valid_index],
-                   'Label (upper bound)': y_upper_bound[valid_index],
-                   'Predicted label': bst.predict(dvalid)})
+df = pd.DataFrame(
+    {
+        "Label (lower bound)": y_lower_bound[valid_index],
+        "Label (upper bound)": y_upper_bound[valid_index],
+        "Predicted label": bst.predict(dvalid),
+    }
+)
 print(df)
 # Show only data points with right-censored labels
-print(df[np.isinf(df['Label (upper bound)'])])
+print(df[np.isinf(df["Label (upper bound)"])])
 
 # Save trained model
-bst.save_model('aft_model.json')
+bst.save_model("aft_model.json")

demo/aft_survival/aft_survival_demo_with_optuna.py

@@ -6,78 +6,108 @@
 using Optuna to tune hyperparameters
 
 """
+
 import numpy as np
 import optuna
 import pandas as pd
-from sklearn.model_selection import ShuffleSplit
-
 import xgboost as xgb
+from sklearn.model_selection import ShuffleSplit
 
 # The Veterans' Administration Lung Cancer Trial
 # The Statistical Analysis of Failure Time Data by Kalbfleisch J. and Prentice R (1980)
-df = pd.read_csv('../data/veterans_lung_cancer.csv')
-print('Training data:')
+df = pd.read_csv("../data/veterans_lung_cancer.csv")
+print("Training data:")
 print(df)
 
 # Split features and labels
-y_lower_bound = df['Survival_label_lower_bound']
-y_upper_bound = df['Survival_label_upper_bound']
-X = df.drop(['Survival_label_lower_bound', 'Survival_label_upper_bound'], axis=1)
+y_lower_bound = df["Survival_label_lower_bound"]
+y_upper_bound = df["Survival_label_upper_bound"]
+X = df.drop(["Survival_label_lower_bound", "Survival_label_upper_bound"], axis=1)
 
 # Split data into training and validation sets
-rs = ShuffleSplit(n_splits=2, test_size=.7, random_state=0)
+rs = ShuffleSplit(n_splits=2, test_size=0.7, random_state=0)
 train_index, valid_index = next(rs.split(X))
 dtrain = xgb.DMatrix(X.values[train_index, :])
-dtrain.set_float_info('label_lower_bound', y_lower_bound[train_index])
-dtrain.set_float_info('label_upper_bound', y_upper_bound[train_index])
+dtrain.set_float_info("label_lower_bound", y_lower_bound[train_index])
+dtrain.set_float_info("label_upper_bound", y_upper_bound[train_index])
 dvalid = xgb.DMatrix(X.values[valid_index, :])
-dvalid.set_float_info('label_lower_bound', y_lower_bound[valid_index])
-dvalid.set_float_info('label_upper_bound', y_upper_bound[valid_index])
+dvalid.set_float_info("label_lower_bound", y_lower_bound[valid_index])
+dvalid.set_float_info("label_upper_bound", y_upper_bound[valid_index])
 
 # Define hyperparameter search space
-base_params = {'verbosity': 0,
-              'objective': 'survival:aft',
-              'eval_metric': 'aft-nloglik',
-              'tree_method': 'hist'}  # Hyperparameters common to all trials
+base_params = {
+    "verbosity": 0,
+    "objective": "survival:aft",
+    "eval_metric": "aft-nloglik",
+    "tree_method": "hist",
+}  # Hyperparameters common to all trials
+
+
 def objective(trial):
-    params = {'learning_rate': trial.suggest_loguniform('learning_rate', 0.01, 1.0),
-              'aft_loss_distribution': trial.suggest_categorical('aft_loss_distribution',
-                                                                  ['normal', 'logistic', 'extreme']),
-              'aft_loss_distribution_scale': trial.suggest_loguniform('aft_loss_distribution_scale', 0.1, 10.0),
-              'max_depth': trial.suggest_int('max_depth', 3, 8),
-              'lambda': trial.suggest_loguniform('lambda', 1e-8, 1.0),
-              'alpha': trial.suggest_loguniform('alpha', 1e-8, 1.0)}  # Search space
+    params = {
+        "learning_rate": trial.suggest_loguniform("learning_rate", 0.01, 1.0),
+        "aft_loss_distribution": trial.suggest_categorical(
+            "aft_loss_distribution", ["normal", "logistic", "extreme"]
+        ),
+        "aft_loss_distribution_scale": trial.suggest_loguniform(
+            "aft_loss_distribution_scale", 0.1, 10.0
+        ),
+        "max_depth": trial.suggest_int("max_depth", 3, 8),
+        "lambda": trial.suggest_loguniform("lambda", 1e-8, 1.0),
+        "alpha": trial.suggest_loguniform("alpha", 1e-8, 1.0),
+    }  # Search space
     params.update(base_params)
-    pruning_callback = optuna.integration.XGBoostPruningCallback(trial, 'valid-aft-nloglik')
-    bst = xgb.train(params, dtrain, num_boost_round=10000,
-                    evals=[(dtrain, 'train'), (dvalid, 'valid')],
-                    early_stopping_rounds=50, verbose_eval=False, callbacks=[pruning_callback])
+    pruning_callback = optuna.integration.XGBoostPruningCallback(
+        trial, "valid-aft-nloglik"
+    )
+    bst = xgb.train(
+        params,
+        dtrain,
+        num_boost_round=10000,
+        evals=[(dtrain, "train"), (dvalid, "valid")],
+        early_stopping_rounds=50,
+        verbose_eval=False,
+        callbacks=[pruning_callback],
+    )
     if bst.best_iteration >= 25:
         return bst.best_score
     else:
         return np.inf  # Reject models with < 25 trees
 
+
 # Run hyperparameter search
-study = optuna.create_study(direction='minimize')
+study = optuna.create_study(direction="minimize")
 study.optimize(objective, n_trials=200)
-print('Completed hyperparameter tuning with best aft-nloglik = {}.'.format(study.best_trial.value))
+print(
+    "Completed hyperparameter tuning with best aft-nloglik = {}.".format(
+        study.best_trial.value
+    )
+)
 params = {}
 params.update(base_params)
 params.update(study.best_trial.params)
 
 # Re-run training with the best hyperparameter combination
-print('Re-running the best trial... params = {}'.format(params))
-bst = xgb.train(params, dtrain, num_boost_round=10000,
-                evals=[(dtrain, 'train'), (dvalid, 'valid')],
-                early_stopping_rounds=50)
+print("Re-running the best trial... params = {}".format(params))
+bst = xgb.train(
+    params,
+    dtrain,
+    num_boost_round=10000,
+    evals=[(dtrain, "train"), (dvalid, "valid")],
+    early_stopping_rounds=50,
+)
 
 # Run prediction on the validation set
-df = pd.DataFrame({'Label (lower bound)': y_lower_bound[valid_index],
-                   'Label (upper bound)': y_upper_bound[valid_index],
-                   'Predicted label': bst.predict(dvalid)})
+df = pd.DataFrame(
+    {
+        "Label (lower bound)": y_lower_bound[valid_index],
+        "Label (upper bound)": y_upper_bound[valid_index],
+        "Predicted label": bst.predict(dvalid),
+    }
+)
 print(df)
 # Show only data points with right-censored labels
-print(df[np.isinf(df['Label (upper bound)'])])
+print(df[np.isinf(df["Label (upper bound)"])])
 
 # Save trained model
-bst.save_model('aft_best_model.json')
+bst.save_model("aft_best_model.json")

demo/aft_survival/aft_survival_viz_demo.py

@@ -9,7 +9,6 @@
 
 import matplotlib.pyplot as plt
 import numpy as np
-
 import xgboost as xgb
 
 plt.rcParams.update({"font.size": 13})

demo/c-api/external-memory/README.md

@@ -13,4 +13,4 @@ In the example, we define a custom data iterator with 2 methods: `reset` and `ne
 its end, and the `reset` method resets iterations. One important detail when using the C
 API for data iterator is users need to make sure that the data passed into `next` method
 must be kept in memory until the next iteration or `reset` is called.  The external memory
-DMatrix is not limited to training, but also valid for other features like prediction.
+DMatrix is not limited to training, but also valid for other features like prediction.

demo/dask/cpu_survival.py

@@ -9,7 +9,6 @@
 import dask.array as da
 import dask.dataframe as dd
 from dask.distributed import Client, LocalCluster
-
 from xgboost import dask as dxgb
 from xgboost.dask import DaskDMatrix
 

demo/dask/cpu_training.py

@@ -6,7 +6,6 @@
 
 from dask import array as da
 from dask.distributed import Client, LocalCluster
-
 from xgboost import dask as dxgb
 from xgboost.dask import DaskDMatrix
 

demo/dask/dask_callbacks.py

@@ -6,12 +6,11 @@
 from typing import Any
 
 import numpy as np
+import xgboost as xgb
+import xgboost.dask as dxgb
 from dask.distributed import Client, LocalCluster
 from dask_ml.datasets import make_regression
 from dask_ml.model_selection import train_test_split
-
-import xgboost as xgb
-import xgboost.dask as dxgb
 from xgboost.dask import DaskDMatrix
 
 

demo/dask/dask_learning_to_rank.py

@@ -25,7 +25,6 @@
 from dask import dataframe as dd
 from distributed import Client, LocalCluster, wait
 from sklearn.datasets import load_svmlight_file
-
 from xgboost import dask as dxgb
 
 

demo/dask/forward_logging.py

@@ -14,7 +14,6 @@
 from dask import array as da
 from dask_cuda import LocalCUDACluster
 from distributed import Client
-
 from xgboost import dask as dxgb
 from xgboost.callback import EvaluationMonitor
 

demo/dask/gpu_training.py

@@ -9,7 +9,6 @@
 from dask import dataframe as dd
 from dask.distributed import Client
 from dask_cuda import LocalCUDACluster
-
 from xgboost import dask as dxgb
 from xgboost.dask import DaskDMatrix
 

demo/dask/sklearn_cpu_training.py

@@ -5,7 +5,6 @@
 
 from dask import array as da
 from dask.distributed import Client, LocalCluster
-
 from xgboost import dask as dxgb
 
 

demo/dask/sklearn_gpu_training.py

@@ -9,7 +9,6 @@
 
 # It's recommended to use dask_cuda for GPU assignment
 from dask_cuda import LocalCUDACluster
-
 from xgboost import dask as dxgb