将带有int标志的列转换为pyspark中的字符串数组

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

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

# 创建示例数据
data = [(1, "apple,banana,orange"), (2, "grape,kiwi"), (3, "watermelon")]

# 创建DataFrame
df = spark.createDataFrame(data, ["id", "fruits"])

# 将带有int标志的列转换为字符串数组
df = df.withColumn("fruits_array", split(df.fruits, ","))

# 显示转换后的结果
df.show(truncate=False)

+---+-----------------+-------------------+
|id |fruits           |fruits_array       |
+---+-----------------+-------------------+
|1  |apple,banana,orange|[apple, banana, orange]|
|2  |grape,kiwi       |[grape, kiwi]      |
|3  |watermelon       |[watermelon]       |
+---+-----------------+-------------------+