从包含CSV值的spark数据框列中创建单个CSV字符串

from pyspark.sql import SparkSession
from pyspark.sql.functions import concat_ws, collect_list

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

# 创建示例数据框
data = [("John", "Doe", 25), ("Jane", "Smith", 30), ("Tom", "Brown", 35)]
df = spark.createDataFrame(data, ["First Name", "Last Name", "Age"])

# 将CSV值收集到列表中
csv_list = df.select(collect_list(concat_ws(",", "First Name", "Last Name", "Age"))).first()[0]

# 将列表中的值连接成CSV字符串
csv_string = ",".join(csv_list)

print(csv_string)

John,Doe,25,Jane,Smith,30,Tom,Brown,35