过滤DF中最新记录的row_number排名函数

from pyspark.sql import SparkSession
from pyspark.sql.functions import row_number
from pyspark.sql.window import Window

# 创建SparkSession
spark = SparkSession.builder.getOrCreate()

# 假设有一个名为df的数据框，包含字段id和timestamp，表示记录的唯一标识和时间戳
df = spark.createDataFrame([(1, '2022-01-01'), (2, '2022-01-02'), (3, '2022-01-03')], ['id', 'timestamp'])

# 使用row_number函数为每一行分配排名
window = Window.orderBy(df['timestamp'].desc())
df_with_rank = df.withColumn('rank', row_number().over(window))

# 筛选出row_number为1的记录，即最新记录
filtered_df = df_with_rank.where(df_with_rank['rank'] == 1)

# 打印筛选结果
filtered_df.show()