使用pySpark对RDD中数组类型的值进行排序

from pyspark.sql import SparkSession
from pyspark.sql.functions import sort_array

spark = SparkSession.builder.appName("Array Sorting").getOrCreate()

data = [("Alice", [3, 2, 1]),
        ("Bob", [6, 5, 4]),
        ("Charlie", [9, 8, 7])]
rdd = spark.sparkContext.parallelize(data)

df = rdd.toDF(["Name", "Array"])

sorted_df = df.select("Name", sort_array("Array").alias("SortedArray"))

sorted_df.show()