pyspark每n行聚合一次

from pyspark.sql import SparkSession
from pyspark.sql.functions import col, row_number
from pyspark.sql.window import Window

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

# 读取数据
data = spark.read.csv("data.csv", header=True)

# 添加行号
data = data.withColumn("row_num", row_number().over(Window.orderBy("id")))

# 定义窗口大小和滑动步长
n = 3
window_spec = Window.orderBy("row_num").rowsBetween(-n, 0)

# 聚合操作
aggregated_data = data.groupBy(col("row_num"), window_spec).agg({"value": "sum"})

# 显示结果
aggregated_data.show()