如何在spark中展平具有相同键的列表

# 导入必要的模块
from pyspark import SparkContext

# 创建SparkContext对象
sc = SparkContext("local", "FlatMapExample")

# 创建包含具有相同键的列表的键值对RDD
data = [("key1", [1, 2, 3]), ("key2", [4, 5]), ("key1", [6, 7])]

# 将数据转换为RDD
rdd = sc.parallelize(data)

# 使用flatMap函数展平具有相同键的列表
flattened_rdd = rdd.flatMap(lambda x: [(x[0], i) for i in x[1]])

# 打印展平后的结果
print(flattened_rdd.collect())

[('key1', 1), ('key1', 2), ('key1', 3), ('key2', 4), ('key2', 5), ('key1', 6), ('key1', 7)]