pyspark-rdd-flatMap.py

# -*- coding: utf-8 -*-
"""
author SparkByExamples.com
"""


from pyspark.sql import SparkSession
spark = SparkSession.builder.appName('SparkByExamples.com').getOrCreate()

data = ["Project Gutenberg’s",
        "Alice’s Adventures in Wonderland",
        "Project Gutenberg’s",
        "Adventures in Wonderland",
        "Project Gutenberg’s"]
rdd=spark.sparkContext.parallelize(data)

for element in rdd.collect():
    print(element)

#Flatmap    
rdd2=rdd.flatMap(lambda x: x.split(" "))
for element in rdd2.collect():
    print(element)