利用jupyter notebook 运行pyspark读取oracle文件 

from pyspark import SparkContext, SparkConf
from pyspark.sql import SQLContext
import numpy as np
import pandas as pd 
conf = SparkConf()
conf.setAppName("appname")
conf.set("spark.jars","E:\\ojdbc6.jar") #开始没有配置这个，一直报错。
conf.setMaster("local[1]")
sc = SparkContext(conf=conf)
sqlContext = SQLContext(sc)
empDF = spark.read \
    .format("jdbc") \
    .option("url", "jdbc:oracle:thin:@//hostname:portnumber/SID") \
    .option("dbtable", "hr.emp") \
    .option("user", "db_user_name") \