In [1]:

    

from __future__ import print_function


%pylab inline
from pyspark.sql.types import *


    

    




Populating the interactive namespace from numpy and matplotlib

In [2]:

    

fname = sc.textFile('/Users/omojumiller/mycode/JayZ/JayZ_American Gangster_American Dreamin.txt')


    

In [4]:

    

counts = fname.flatMap(lambda line: line.split(" "))\
            .map(lambda word: (word, 1))\
            .reduceByKey(lambda a, b: a + b)


    

In [5]:

    

counts.saveAsTextFile('word_count_out')


    

In [ ]: