如何在分组的值上将一行的值与PySpark中的所有其他行进行比较

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

# 初始化SparkSession
spark = SparkSession.builder.appName("GroupComparison").getOrCreate()

# 创建一个示例DataFrame
data = [
    ("group1", 10),
    ("group1", 20),
    ("group1", 30),
    ("group2", 15),
    ("group2", 25)
]
columns = ["group", "value"]
df = spark.createDataFrame(data, columns)

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

# 添加行号列，用于比较
df = df.withColumn("row_num", row_number().over(window_spec))

# 将当前行的值与其他所有行的值进行比较
df = df.withColumn("comparison", lit(1) - (col("row_num") == 1).cast("int"))

# 显示结果
df.show()