标识与PySpark数据帧中的当前值不同的最新记录

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

spark = SparkSession.builder.appName("Identify Latest Changed Records").getOrCreate()

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

windowSpec = Window.orderBy("timestamp_column")
df = df.withColumn("previous_value", lag(col("value_column")).over(windowSpec))
df = df.withColumn("is_changed", col("value_column") != col("previous_value"))

latest_changed_records = df.filter(col("is_changed") == True)