问如何在PySpark中从单个元素的RDD创建成对RDD？

EN

rdd1 = sc.textFile("sometext.txt")

import re
import string

def Func(lines):
    lines = lines.lower() #make all text lowercase
    lines = re.sub('[%s]' % re.escape(string.punctuation), '', lines) #remove punctuation
    lines = re.sub('\w*\d\w*', '', lines) #remove numeric-containing strings
    lines = lines.split() #split lines
    return lines
rdd2 = rdd1.flatMap(Func)

stopwords = ['list of stopwords goes here'] 
rdd3 = rdd2.filter(lambda x: x not in stopwords) # filter out stopwords
rdd3.take(5) #resulting RDD

Out:['a',
     'b',
     'c',
     'd',
     'e']