如何在Pyspark中从十亿行数据集中随机抽取行

from pyspark.sql import SparkSession
from pyspark.sql.functions import rand

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

data = spark.read.format("csv").option("header", "true").load("数据集路径")

row_count = data.count()

sample_ratio = 0.01  # 抽样比例为1%
random_seed = 42  # 随机种子，可选

sampled_data = data.sample(withReplacement=False, fraction=sample_ratio, seed=random_seed)

sampled_data.show()