如何统计pyspark中行值的变化

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

spark = SparkSession.builder.appName("RowValueChange").getOrCreate()

data = [(1, "A"), (2, "B"), (3, "B"), (4, "C"), (5, "C")]
df = spark.createDataFrame(data, ["id", "value"])

windowSpec = Window.orderBy("id")

df = df.withColumn("previous_value", lag(col("value")).over(windowSpec))

df = df.withColumn("value_changed", col("value") != col("previous_value"))

df.show()