每个分区中增量值基于pyspark中一列的变化

from pyspark.sql import SparkSession

spark = SparkSession.builder.appName("Incremental Calculation").getOrCreate()

df = spark.read.format("csv").option("header", "true").load("data.csv")

from pyspark.sql.window import Window
from pyspark.sql.functions import lag, col

windowSpec = Window.partitionBy().orderBy("column_name")

df = df.withColumn("incremental_value", col("column_name") - lag(col("column_name")).over(windowSpec))

result_df = df.select("column_name", "incremental_value")
result_df.show()