在pyspark中将对象传递给UDF

from pyspark.sql import SparkSession
from pyspark.sql.functions import udf
from pyspark.sql.types import StringType

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

# 定义一个自定义函数，将对象转换为字符串
def object_to_string(obj):
    return str(obj)

# 注册UDF
object_to_string_udf = udf(object_to_string, StringType())
spark.udf.register("object_to_string", object_to_string_udf)

# 创建一个DataFrame
data = [("Alice", 25, {"city": "New York"}), ("Bob", 30, {"city": "San Francisco"})]
df = spark.createDataFrame(data, ["name", "age", "info"])

# 使用UDF将对象转换为字符串
df = df.withColumn("info_str", object_to_string_udf(df["info"]))

# 显示结果
df.show()