如何在Pyspark中创建按列拆分的RDD子集？

# 导入必要的模块
from pyspark import SparkContext

# 创建SparkContext对象
sc = SparkContext("local", "Column Split RDD Subset")

# 创建原始RDD
data = [("John", 25, "USA"), ("Alice", 30, "Canada"), ("Bob", 35, "UK")]
rdd = sc.parallelize(data)

# 定义按列拆分的函数
def split_columns(row):
    name = row[0]
    age = row[1]
    country = row[2]
    return name, age

# 使用map函数和lambda表达式创建按列拆分的RDD子集
subset_rdd = rdd.map(lambda row: split_columns(row))

# 打印结果
print(subset_rdd.collect())

# 停止SparkContext对象
sc.stop()