PyCharm远程连接linux中Python运行pyspark

import os
import sys
os.environ['SPARK_HOME'] = '/root/spark-1.4.0-bin-hadoop2.6'
sys.path.append("/root/spark-1.4.0-bin-hadoop2.6/python")

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)

Result:

ssh://hadoop@192.168.1.131:22/usr/bin/python -u /home/hadoop/TestFile/pysparkProgram/Mainprogram.py
Successfully imported Spark Modules

Process finished with exit code 0

import sys
sys.path.append("/root/programs/spark-1.4.0-bin-hadoop2.6/python")

try:
    import numpy as np
    import scipy.sparse as sps
    from pyspark.mllib.linalg import Vectors

    dv1 = np.array([1.0, 0.0, 3.0])
    dv2 = [1.0, 0.0, 3.0]
    sv1 = Vectors.sparse(3, [0, 2], [1.0, 3.0])
    sv2 = sps.csc_matrix((np.array([1.0, 3.0]), np.array([0, 2]), np.array([0, 2])), shape=(3, 1))

    print(sv2)

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

Result

ssh://hadoop@192.168.1.131:22/usr/bin/python -u /home/hadoop/TestFile/pysparkProgram/Mainprogram.py
  (0, 0)    1.0
  (2, 0)    3.0

Process finished with exit code 0