在Pyspark中将Struct数组重排为带字段的结构数组

from pyspark.sql import SparkSession
from pyspark.sql.functions import explode, struct

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

# 假设有一个DataFrame，包含名为data的Struct数组列
data = [(1, [("A", 10), ("B", 20), ("C", 30)]), (2, [("D", 40), ("E", 50)])]
df = spark.createDataFrame(data, ["id", "data"])

# 将Struct数组重排为带字段的结构数组
df_new = df.select("id", explode("data").alias("data_exp")).select("id", "data_exp._1", "data_exp._2")
df_new = df_new.select("id", struct("data_exp._1", "data_exp._2").alias("data"))

# 打印结果
df_new.show(truncate=False)

+---+----------+
|id |data      |
+---+----------+
|1  |[A, 10]   |
|1  |[B, 20]   |
|1  |[C, 30]   |
|2  |[D, 40]   |
|2  |[E, 50]   |
+---+----------+