samples = sc.parallelize([
("abonsanto@fakemail.com", "Alberto", "Bonsanto"),
("mbonsanto@fakemail.com", "Miguel", "Bonsanto"),
("stranger@fakemail.com", "Stranger", "Weirdo"),
("dbonsanto@fakemail.com", "Dakota", "Bonsanto")
])
print samples.collect()
samples.saveAsTextFile("folder/here.txt")
read_rdd = sc.textFile("folder/here.txt")
read_rdd.collect()