1samples = sc.parallelize([
2 ("abonsanto@fakemail.com", "Alberto", "Bonsanto"),
3 ("mbonsanto@fakemail.com", "Miguel", "Bonsanto"),
4 ("stranger@fakemail.com", "Stranger", "Weirdo"),
5 ("dbonsanto@fakemail.com", "Dakota", "Bonsanto")
6])
7
8print samples.collect()
9
10samples.saveAsTextFile("folder/here.txt")
11read_rdd = sc.textFile("folder/here.txt")
12
13read_rdd.collect()