spark_home的配置

import sys, os

# Path for spark source folder
os.environ['SPARK_HOME'] = "/opt/spark-2.0.1-bin-hadoop2.7"

# Append pyspark  to Python Path
sys.path.append("/opt/spark-2.0.1-bin-hadoop2.7/python/")
sys.path.append("/opt/spark-2.0.1-bin-hadoop2.7/python/lib/")

try:
    from pyspark import SparkContext
    from pyspark import SparkConf
    from pyspark.sql import SparkSession
    from pyspark.sql import SQLContext

    print("Successfully imported Spark Modules")
except ImportError as e:
    print("Can not import Spark Modules", e)
    sys.exit(1)
from pyspark.sql import Row