如何在PysPark中将数组结构拆分为csv

from pyspark.sql.functions import explode
import csv

df = spark.createDataFrame([(1, ["a", "b", "c"]), (2, ["d", "e", "f"])], ["id", "array_col"])
df_exploded = df.withColumn("value", explode(df.array_col))

output_path = "/path/to/output.csv"

with open(output_path, mode='w', newline='') as file:
    writer = csv.writer(file)
    writer.writerow(["id", "value"])  # 写入CSV文件的标题行
    for row in df_exploded.collect():
        writer.writerow(row)  # 写入拆分后的DataFrame的每行数据

from pyspark.sql import SparkSession
from pyspark.sql.functions import explode
import csv

# 创建SparkSession
spark = SparkSession.builder.appName("Array to CSV").getOrCreate()

# 创建包含数组的DataFrame
df = spark.createDataFrame([(1, ["a", "b", "c"]), (2, ["d", "e", "f"])], ["id", "array_col"])

# 使用explode函数将数组结构拆分为多行
df_exploded = df.withColumn("value", explode(df.array_col))

# 定义CSV文件的路径和文件名
output_path = "/path/to/output.csv"

# 将拆分后的DataFrame保存为CSV文件
with open(output_path, mode='w', newline='') as file:
    writer = csv.writer(file)
    writer.writerow(["id", "value"])  # 写入CSV文件的标题行
    for row in df_exploded.collect():
        writer.writerow(row)  # 写入拆分后的DataFrame的每行数据

# 关闭SparkSession
spark.stop()