Pyspark -从具有最小和最大值范围的数组中获取值

from pyspark.sql import SparkSession
from pyspark.sql.functions import array_min, array_max

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 创建示例数据
data = [(1, [5, 10, 15, 20]), (2, [2, 4, 6, 8]), (3, [1, 3, 5, 7])]
df = spark.createDataFrame(data, ["id", "array"])

# 使用array_min和array_max函数获取最小和最大值
df.withColumn("min_value", array_min(df.array)).withColumn("max_value", array_max(df.array)).show()

+---+---------------+---------+
| id|          array|min_value|max_value|
+---+---------------+---------+
|  1|[5, 10, 15, 20]|        5|       20|
|  2|  [2, 4, 6, 8]|        2|        8|
|  3|  [1, 3, 5, 7]|        1|        7|
+---+---------------+---------+