python开发sparkSQL应用

cnq

# -*- coding: utf-8 -*-　　
"""
　　
Created on Wed Feb 22 15:07:44 2017
　　
练习SparkSQL
　　
@author: wanghuan
　　
"""
　　
from pyspark.sql import SparkSession
　　

　　
spark = SparkSession.builder.master("spark://cent0s7Master:7077").appName("Python Spark SQL basic example").config("spark.some.config.option", "some-value")
　　
.getOrCreate()
　　
#ssc=SparkContext("local[2]","sparksqltest")
　　
peopleDF = spark.read.json("examples/src/main/resources/people.json")
　　
salaryDF = spark.read.json("examples/src/main/resources/salary.json")
　　
#peopleDF.printSchema()
　　

　　
# Creates a temporary view using the DataFrame
　　
peopleDF.createOrReplaceTempView("people")
　　
salaryDF.createOrReplaceTempView("salary")
　　
# SQL statements can be run by using the sql methods provided by spark
　　
teenagerNamesDF = spark.sql("SELECT a.name,a.age,b.salary FROM people a,salary b where a.name=b.name and a.age <30 and b.salary>5000")
　　
teenagerNamesDF.show()