如何使用pyspark按小时获取x最频繁的位置？

from pyspark.sql import SparkSession
from pyspark.sql.functions import hour, count, desc

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

data = spark.read.csv("data.csv", header=True, inferSchema=True)

data = data.select("timestamp", "location")

data = data.withColumn("hour", hour(data.timestamp))

grouped_data = data.groupBy("hour", "location").agg(count("*").alias("count"))

result = grouped_data.orderBy("hour", desc("count")).groupBy("hour").agg(
    collect_list("location").alias("frequent_locations")
).select("hour", "frequent_locations")

result.show()