Pyspark将包含字符串的列转换为字符串列表，并将其保存到同一列中

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

# 创建SparkSession
spark = SparkSession.builder.appName("StringToList").getOrCreate()

# 创建示例数据集
data = [("Alice", "apple,banana,orange"),
        ("Bob", "grape,kiwi"),
        ("Charlie", "watermelon")]

df = spark.createDataFrame(data, ["Name", "Fruits"])

# 使用split函数将Fruits列转换为字符串列表
df = df.withColumn("Fruits_List", split(df.Fruits, ","))

# 显示结果
df.show(truncate=False)

+-------+-----------------+-------------------+
|Name   |Fruits           |Fruits_List        |
+-------+-----------------+-------------------+
|Alice  |apple,banana,orange|[apple, banana, orange]|
|Bob    |grape,kiwi       |[grape, kiwi]      |
|Charlie|watermelon       |[watermelon]       |
+-------+-----------------+-------------------+