PySpark:如何获得一列更改值所用的平均时间？

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

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

data = [(1, "2022-01-01 10:00:00", 100),
        (2, "2022-01-01 10:05:00", 150),
        (3, "2022-01-01 10:10:00", 200),
        (4, "2022-01-01 10:15:00", 200),
        (5, "2022-01-01 10:20:00", 250)]

df = spark.createDataFrame(data, ["id", "timestamp", "value"])

df = df.withColumn("timestamp", unix_timestamp(col("timestamp"), "yyyy-MM-dd HH:mm:ss"))

windowSpec = Window.orderBy("timestamp")
df = df.withColumn("prev_timestamp", lag(col("timestamp")).over(windowSpec))

df = df.withColumn("time_diff", col("timestamp") - col("prev_timestamp"))

average_time = df.selectExpr("avg(time_diff) as average_time").collect()[0]["average_time"]

print("平均时间：", average_time)