map_flatMap.py

from pyspark import SparkConf, SparkContext
conf = SparkConf().setMaster("local").setAppName("Filter")
sc = SparkContext(conf = conf)
lines = sc.textFile("hdfs://localhost:54310/numeric_input.txt")
input_strings = sc.parallelize(["Hello World", "Hi"])
splitted_strings = input_strings.map(lambda line:line.split(" ")).collect()
for str in splitted_strings:
	print "----------" 
	print str
	print "----------"
splitted_strings = input_strings.flatMap(lambda line:line.split(" ")).collect()
for str in splitted_strings:
	print "----------" 
	print str 
	print "----------"

This python file demonstrates the difference between map() and flatMap()