In [ ]:
import os
import sys

print ("start")
os.environ['SPARK_HOME'] = "/Users/chanjinpark/dev/spark-1.6.2/"
sys.path.append("/Users/chanjinpark/dev/spark-1.6.2/python")

try:
    from pyspark import SparkContext
    from pyspark import SparkConf
except ImportError as e:
    print("Can't import pyspark ", e)
    sys.exit(1)

In [ ]:
import matplotlib.pyplot as plt
sc = SparkContext('local')
workspace ='/Users/chanjinpark/data/NRF2015/'
contdir = workspace + 'content-sample/'
metafile = workspace + 'NRF2015Meta.csv'
contfile = workspace + 'contents.csv/part*'
sc.textFile(contfile).take(5)

In [ ]: