In [1]:

    

# Initialization Spark in Python
from pyspark import SparkContext


    

In [2]:

    

# Setting Spark work
sc = SparkContext("local", "Hello World APP")


    

In [3]:

    

# Should be some file on your system
logFile = "/usr/apache/spark-2.0.2-bin-hadoop2.7/README.md"
logData = sc.textFile(logFile).cache()


    

In [4]:

    

numAs = logData.filter(lambda s: 'a' in s).count()
numBs = logData.filter(lambda s: 'b' in s).count()


    

In [5]:

    

print("Lines with a: %i, lines with b: %i" % (numAs, numBs))


    

    




Lines with a: 61, lines with b: 27

In [6]:

    

sc.stop()


    

In [ ]: