在pyspark数据帧中查找非重叠窗口

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

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

# 创建示例数据帧
data = [("A", 1), ("A", 2), ("A", 3), ("B", 4), ("B", 5), ("B", 6)]
df = spark.createDataFrame(data, ["key", "value"])

# 定义窗口规范
window_spec = Window.partitionBy("key").orderBy("value")

# 添加窗口行号
df_with_row_number = df.withColumn("row_number", row_number().over(window_spec))

# 定义窗口大小
window_size = 2

# 过滤非重叠窗口
result = df_with_row_number.filter((col("row_number") - 1) % window_size == 0)

# 显示结果
result.show()