Pyspark:如何从spark数据帧中过滤10000个随机元素

from pyspark.sql import SparkSession
from pyspark.sql.functions import col
from pyspark.sql.types import ArrayType, IntegerType
import random

spark = SparkSession.builder.appName("Filter Random Elements").getOrCreate()

df = spark.createDataFrame([(i,) for i in range(100000)], ["value"])

random_elements = random.sample(range(100000), 10000)

random_elements_df = spark.createDataFrame([(i,) for i in random_elements], ["value"])

filtered_df = df.join(random_elements_df, on=["value"], how="inner")