提取列值并将其作为Spark dataframe中的数组分配给另一列

from pyspark.sql import SparkSession
from pyspark.sql.functions import split

spark = SparkSession.builder.getOrCreate()

data = [("John,Doe",), ("Jane,Smith",), ("Tom,Hanks",)]
df = spark.createDataFrame(data, ["name"])
df.show()

+----------+
|      name|
+----------+
|  John,Doe|
|Jane,Smith|
| Tom,Hanks|
+----------+

df = df.withColumn("name_array", split(df.name, ","))
df.show()

+----------+-------------+
|      name|   name_array|
+----------+-------------+
|  John,Doe| [John, Doe]|
|Jane,Smith|[Jane, Smith]|
| Tom,Hanks| [Tom, Hanks]|
+----------+-------------+