PySpark -将数组结构转换为列名为我的结构

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

spark = SparkSession.builder.appName("Array to Columns").getOrCreate()

data = [(1, ["A", "B", "C"]), (2, ["D", "E"]), (3, ["F"])]
df = spark.createDataFrame(data, ["id", "my_array"])
df.show()

+---+---------+
| id|my_array |
+---+---------+
|  1|[A, B, C]|
|  2|   [D, E]|
|  3|      [F]|
+---+---------+

df_exploded = df.select("id", explode("my_array").alias("my_struct"))
df_exploded.show()

+---+---------+
| id|my_struct|
+---+---------+
|  1|        A|
|  1|        B|
|  1|        C|
|  2|        D|
|  2|        E|
|  3|        F|
+---+---------+

df_pivoted = df_exploded.groupBy("id").pivot("my_struct").count()
df_pivoted.show()

+---+---+---+---+---+---+---+
| id|  A|  B|  C|  D|  E|  F|
+---+---+---+---+---+---+---+
|  1|  1|  1|  1|  0|  0|  0|
|  2|  0|  0|  0|  1|  1|  0|
|  3|  0|  0|  0|  0|  0|  1|
+---+---+---+---+---+---+---+