Use black on more Python files. (#8137)

tests/ci_build/lint_python.py

@@ -112,13 +112,25 @@ if __name__ == "__main__":
         if not all(
             run_formatter(path)
             for path in [
+                # core
+                "python-package/xgboost/__init__.py",
+                "python-package/xgboost/_typing.py",
+                "python-package/xgboost/compat.py",
+                "python-package/xgboost/config.py",
                 "python-package/xgboost/dask.py",
                 "python-package/xgboost/sklearn.py",
                 "python-package/xgboost/spark",
+                "python-package/xgboost/federated.py",
+                "python-package/xgboost/spark",
+                # tests
                 "tests/python/test_config.py",
-                "tests/python/test_spark/test_data.py",
-                "tests/python-gpu/test_gpu_spark/test_data.py",
+                "tests/python/test_spark/",
+                "tests/python-gpu/test_gpu_spark/",
                 "tests/ci_build/lint_python.py",
+                # demo
+                "demo/guide-python/cat_in_the_dat.py",
+                "demo/guide-python/categorical.py",
+                "demo/guide-python/spark_estimator_examples.py",
             ]
         ):
             sys.exit(-1)

tests/python/test_spark/test_spark_local.py

@@ -1,11 +1,10 @@
-import sys
 import logging
 import random
+import sys
 import uuid
 
 import numpy as np
 import pytest
-
 import testing as tm
 
 if tm.no_spark()["condition"]:
@@ -13,26 +12,27 @@ if tm.no_spark()["condition"]:
 if sys.platform.startswith("win") or sys.platform.startswith("darwin"):
     pytest.skip("Skipping PySpark tests on Windows", allow_module_level=True)
 
-from pyspark.ml.functions import vector_to_array
-from pyspark.sql import functions as spark_sql_func
 from pyspark.ml import Pipeline, PipelineModel
 from pyspark.ml.evaluation import (
     BinaryClassificationEvaluator,
     MulticlassClassificationEvaluator,
 )
+from pyspark.ml.functions import vector_to_array
 from pyspark.ml.linalg import Vectors
 from pyspark.ml.tuning import CrossValidator, ParamGridBuilder
-
+from pyspark.sql import functions as spark_sql_func
 from xgboost.spark import (
     SparkXGBClassifier,
     SparkXGBClassifierModel,
     SparkXGBRegressor,
     SparkXGBRegressorModel,
 )
-from .utils import SparkTestCase
-from xgboost import XGBClassifier, XGBRegressor
 from xgboost.spark.core import _non_booster_params
 
+from xgboost import XGBClassifier, XGBRegressor
+
+from .utils import SparkTestCase
+
 logging.getLogger("py4j").setLevel(logging.INFO)
 
 

tests/python/test_spark/test_spark_local_cluster.py

@@ -1,11 +1,11 @@
-import sys
-import random
 import json
-import uuid
 import os
+import random
+import sys
+import uuid
 
-import pytest
 import numpy as np
+import pytest
 import testing as tm
 
 if tm.no_spark()["condition"]:
@@ -13,10 +13,11 @@ if tm.no_spark()["condition"]:
 if sys.platform.startswith("win") or sys.platform.startswith("darwin"):
     pytest.skip("Skipping PySpark tests on Windows", allow_module_level=True)
 
-from .utils import SparkLocalClusterTestCase
+from pyspark.ml.linalg import Vectors
 from xgboost.spark import SparkXGBClassifier, SparkXGBRegressor
 from xgboost.spark.utils import _get_max_num_concurrent_tasks
-from pyspark.ml.linalg import Vectors
+
+from .utils import SparkLocalClusterTestCase
 
 
 class XgboostLocalClusterTestCase(SparkLocalClusterTestCase):

tests/python/test_spark/utils.py

@@ -3,22 +3,18 @@ import logging
 import shutil
 import sys
 import tempfile
-
 import unittest
+
 import pytest
-
-from six import StringIO
-
 import testing as tm
+from six import StringIO
 
 if tm.no_spark()["condition"]:
     pytest.skip(msg=tm.no_spark()["reason"], allow_module_level=True)
 if sys.platform.startswith("win") or sys.platform.startswith("darwin"):
     pytest.skip("Skipping PySpark tests on Windows", allow_module_level=True)
 
-from pyspark.sql import SQLContext
-from pyspark.sql import SparkSession
-
+from pyspark.sql import SparkSession, SQLContext
 from xgboost.spark.utils import _get_default_params_from_func