如何删除在特定列上具有相同值的重复记录，并使用pyspark保留时间戳最高的记录

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

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

data = [("A", "2022-01-01 10:00:00"),
        ("B", "2022-01-01 11:00:00"),
        ("A", "2022-01-01 12:00:00"),
        ("C", "2022-01-01 13:00:00"),
        ("B", "2022-01-01 14:00:00")]

df = spark.createDataFrame(data, ["col1", "timestamp"])

windowSpec = Window.partitionBy("col1").orderBy(col("timestamp").desc())

df = df.withColumn("row_number", row_number().over(windowSpec)) \
       .filter(col("row_number") == 1) \
       .drop("row_number")

df.show()