如何在PySpark中使用时间戳和userid创建“sessionId”列？

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

spark = SparkSession.builder.getOrCreate()

data = spark.read.csv("data.csv", header=True)  # 假设数据集为CSV格式，包含时间戳和userid列
df = data.withColumn("timestamp", unix_timestamp(col("timestamp"), "yyyy-MM-dd HH:mm:ss").cast("timestamp"))

windowSpec = Window.partitionBy("userid").orderBy("timestamp")
df = df.withColumn("sessionId", F.sum((col("timestamp").cast("long") - F.lag(col("timestamp").cast("long")).over(windowSpec)) > 1800).cast("int"))

df.show()