1. 程式人生 > >pycharm配置spark

pycharm配置spark

pycharm 配置spark

在Run->Configuration->Defaults->Python->Environment variables下,配置:

PYTHONPATH /home/xxx/software/spark-2.1.0-bin-hadoop2.7/python:/home/xxx/software/spark-2.1.0-bin-hadoop2.7/python/lib/py4j-0.10.4-src.zip

SPARK_HOME /home/xxx/software/spark-2.1.0-bin-hadoop2.7

sudo vi /etc/hosts

127.0.0.1 [email protected]

test.py

import os
import sys

# Path for spark source folder
os.environ['SPARK_HOME'] = "/home/xxx/software/spark-2.1.0-bin-hadoop2.7"

# You might need to enter your local IP
# os.environ['SPARK_LOCAL_IP']="192.168.2.138"


# Path for pyspark and py4j
sys.path.append("/home/xxx/software/spark-2.1.0-bin-hadoop2.7/python")
sys.path.append("/home/xxx/software/spark-2.1.0-bin-hadoop2.7/python/lib/py4j-0.10.4-src.zip")

try:
    from pyspark import SparkContext
    from pyspark import SparkConf

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

logFile = "/home/xxx/software/spark-2.1.0-bin-hadoop2.7/README.md"
sc = SparkContext("local", "Simple App")
logData = sc .textFile(logFile).cache()

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

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