Use black on more Python files. (#8137)

demo/guide-python/cat_in_the_dat.py

@@ -19,13 +19,14 @@ Also, see the tutorial for using XGBoost with categorical data:
 """
 
 from __future__ import annotations
-from time import time
+
 import os
 from tempfile import TemporaryDirectory
+from time import time
 
 import pandas as pd
-from sklearn.model_selection import train_test_split
 from sklearn.metrics import roc_auc_score
+from sklearn.model_selection import train_test_split
 
 import xgboost as xgb
 

demo/guide-python/categorical.py

@@ -16,11 +16,13 @@ categorical data.
     .. versionadded:: 1.5.0
 
 """
-import pandas as pd
-import numpy as np
-import xgboost as xgb
 from typing import Tuple
 
+import numpy as np
+import pandas as pd
+
+import xgboost as xgb
+
 
 def make_categorical(
     n_samples: int, n_features: int, n_categories: int, onehot: bool

demo/guide-python/spark_estimator_examples.py

@@ -1,35 +1,34 @@
-'''
+"""
 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
 from pyspark.sql import SparkSession
 from pyspark.sql.functions import rand
-from pyspark.ml.linalg import Vectors
-import sklearn.datasets
 from sklearn.model_selection import train_test_split
 from xgboost.spark import SparkXGBClassifier, SparkXGBRegressor
-from pyspark.ml.evaluation import RegressionEvaluator, MulticlassClassificationEvaluator
-
 
 spark = SparkSession.builder.master("local[*]").getOrCreate()
 
 
 def create_spark_df(X, y):
     return spark.createDataFrame(
-        spark.sparkContext.parallelize([
-            (Vectors.dense(features), float(label))
-            for features, label in zip(X, y)
-        ]),
-        ["features", "label"]
+        spark.sparkContext.parallelize(
+            [(Vectors.dense(features), float(label)) for features, label in zip(X, y)]
+        ),
+        ["features", "label"],
     )
 
 
 # load diabetes dataset (regression dataset)
 diabetes_X, diabetes_y = sklearn.datasets.load_diabetes(return_X_y=True)
-diabetes_X_train, diabetes_X_test, diabetes_y_train, diabetes_y_test = \
-    train_test_split(diabetes_X, diabetes_y, test_size=0.3, shuffle=True)
+diabetes_X_train, diabetes_X_test, diabetes_y_train, diabetes_y_test = train_test_split(
+    diabetes_X, diabetes_y, test_size=0.3, shuffle=True
+)
 
 diabetes_train_spark_df = create_spark_df(diabetes_X_train, diabetes_y_train)
 diabetes_test_spark_df = create_spark_df(diabetes_X_test, diabetes_y_test)
@@ -38,25 +37,36 @@ diabetes_test_spark_df = create_spark_df(diabetes_X_test, diabetes_y_test)
 xgb_regressor = SparkXGBRegressor(max_depth=5)
 xgb_regressor_model = xgb_regressor.fit(diabetes_train_spark_df)
 
-transformed_diabetes_test_spark_df = xgb_regressor_model.transform(diabetes_test_spark_df)
+transformed_diabetes_test_spark_df = xgb_regressor_model.transform(
+    diabetes_test_spark_df
+)
 regressor_evaluator = RegressionEvaluator(metricName="rmse")
-print(f"regressor rmse={regressor_evaluator.evaluate(transformed_diabetes_test_spark_df)}")
+print(
+    f"regressor rmse={regressor_evaluator.evaluate(transformed_diabetes_test_spark_df)}"
+)
 
 diabetes_train_spark_df2 = diabetes_train_spark_df.withColumn(
     "validationIndicatorCol", rand(1) > 0.7
 )
 
 # train xgboost regressor model with validation dataset
-xgb_regressor2 = SparkXGBRegressor(max_depth=5, validation_indicator_col="validationIndicatorCol")
+xgb_regressor2 = SparkXGBRegressor(
+    max_depth=5, validation_indicator_col="validationIndicatorCol"
+)
 xgb_regressor_model2 = xgb_regressor2.fit(diabetes_train_spark_df2)
-transformed_diabetes_test_spark_df2 = xgb_regressor_model2.transform(diabetes_test_spark_df)
-print(f"regressor2 rmse={regressor_evaluator.evaluate(transformed_diabetes_test_spark_df2)}")
+transformed_diabetes_test_spark_df2 = xgb_regressor_model2.transform(
+    diabetes_test_spark_df
+)
+print(
+    f"regressor2 rmse={regressor_evaluator.evaluate(transformed_diabetes_test_spark_df2)}"
+)
 
 
 # load iris dataset (classification dataset)
 iris_X, iris_y = sklearn.datasets.load_iris(return_X_y=True)
-iris_X_train, iris_X_test, iris_y_train, iris_y_test = \
-    train_test_split(iris_X, iris_y, test_size=0.3, shuffle=True)
+iris_X_train, iris_X_test, iris_y_train, iris_y_test = train_test_split(
+    iris_X, iris_y, test_size=0.3, shuffle=True
+)
 
 iris_train_spark_df = create_spark_df(iris_X_train, iris_y_train)
 iris_test_spark_df = create_spark_df(iris_X_test, iris_y_test)
@@ -74,9 +84,13 @@ iris_train_spark_df2 = iris_train_spark_df.withColumn(
 )
 
 # train xgboost classifier model with validation dataset
-xgb_classifier2 = SparkXGBClassifier(max_depth=5, validation_indicator_col="validationIndicatorCol")
+xgb_classifier2 = SparkXGBClassifier(
+    max_depth=5, validation_indicator_col="validationIndicatorCol"
+)
 xgb_classifier_model2 = xgb_classifier2.fit(iris_train_spark_df2)
 transformed_iris_test_spark_df2 = xgb_classifier_model2.transform(iris_test_spark_df)
-print(f"classifier2 f1={classifier_evaluator.evaluate(transformed_iris_test_spark_df2)}")
+print(
+    f"classifier2 f1={classifier_evaluator.evaluate(transformed_iris_test_spark_df2)}"
+)
 
 spark.stop()