PYTHON

flatmap python

array = [[1, 2], [3, 4]]

flatArray = [element for element in innerArray for innerArray in array]
# [1, 2, 3, 4]

flatmap in python

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

flatmap in python

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)