基于Spark Streaming预测股票走势的例子(一)

  最近学习Spark Streaming,不知道是不是我搜索的姿势不对,总找不到具体的、完整的例子,一怒之下就决定自己写一个出来。下面以预测股票走势为例,总结了用Spark Streaming开发的具体步骤以及方法。

  一、数据源。

  既然预测股票走势,当然要从网上找一下股票数据的接口,具体可以参考 http://blog.sina.com.cn/s/blog_540f22560100ba2k.htmlhttp://apistore.baidu.com/apiworks/servicedetail/115.html 。下面简单分析一下各种数据接口的优劣以抛砖引玉:

  1、Sina股票数据接口。以字符串数据的形式范围,简单易用且直观。

  2、百度数据接口。以API集市形式提供json形式的数据,比较规范,但使用起来比较繁琐。

  简单起见,作者使用新浪的数据接口。

  二、测试数据源

  有了股票的数据接口,以下代码提供简单的测试,以解析返回的数据。

 

/**
  * Created by gabry.wu on 2016/2/18.
  */
package com.gabry.stock

import scala.io.Source
/** 其实这个类应该更通用一点,但目前一切以简单为主,后期在进行重构 **/
class SinaStock
{
  var code:String="" //“sh601006”,股票代码
  var name :String =""  //”大秦铁路”,股票名字
  var curOpenPrice :Float =0 //”27.55″,今日开盘价
  var lstOpenPrice:Float =0 //”27.25″,昨日收盘价
  var curPrice :Float =0 //”26.91″,当前价格
  var highestPrice  :Float =0 //”27.55″,今日最高价
  var lowestPrice :Float=0 //”26.20″,今日最低价
  var bidBuyPrice:Float=0 //”26.91″,竞买价,即“买一”报价
  var bidSalePrice:Float=0 //”26.92″,竞卖价,即“卖一”报价
  var dealNum :Long=0 //8:”22114263″,成交的股票数,由于股票交易以一百股为基本单位,所以在使用时,通常把该值除以一百
  var dealAmount  :Float=0 //9:”589824680″,成交金额,单位为“元”,为了一目了然,通常以“万元”为成交金额的单位,所以通常把该值除以一万
  var bidBuy1Num :Long=0 //10:”4695″,“买一”申请4695股,即47手
  var bidBuy1Amount :Float=0 //11:”26.91″,“买一”报价
  var bidBuy2Num :Long=0
  var bidBuy2Amount :Float=0
  var bidBuy3Num :Long=0
  var bidBuy3Amount :Float=0
  var bidBuy4Num :Long=0
  var bidBuy4Amount :Float=0
  var bidBuy5Num :Long=0
  var bidBuy5Amount :Float=0
  var bidSale1Num :Long=0 //“卖一”申报3100股,即31手
  var bidSale1Amount :Float=0 //“卖一”报价
  var bidSale2Num :Long=0
  var bidSale2Amount :Float=0
  var bidSale3Num :Long=0
  var bidSale3Amount :Float=0
  var bidSale4Num :Long=0
  var bidSale4Amount :Float=0
  var bidSale5Num :Long=0
  var bidSale5Amount :Float=0
  var date:String ="" //”2008-01-11″,日期
  var time:String="" //”15:05:32″,时间
  def toDebugString =  "code[%s],name[%s],curOpenPrice [%f],lstOpenPrice[%f],curPrice [%f],highestPrice  [%f],lowestPrice [%f],bidBuyPrice[%f],bidSalePrice[%f],dealNum [%d],dealAmount  [%f],bidBuy1Num [%d],bidBuy1Amount [%f],,bidBuy2Num [%d],bidBuy2Amount [%f],bidBuy3Num [%d],bidBuy3Amount [%f],bidBuy4Num [%d],bidBuy4Amount [%f],bidBuy5Num [%d],bidBuy5Amount [%f],bidSale1Num [%d],bidSale1Amount [%f],bidSale2Num [%d],bidSale2Amount [%f],bidSale3Num [%d],bidSale3Amount [%f],bidSale4Num [%d],bidSale4Amount [%f],bidSale5Num [%d],bidSale5Amount [%f],date [%s],time [%s]" .format( this.code,    this.name,    this.curOpenPrice ,    this.lstOpenPrice,    this.curPrice ,    this.highestPrice  ,    this.lowestPrice ,    this.bidBuyPrice,    this.bidSalePrice,    this.dealNum ,    this.dealAmount  ,    this.bidBuy1Num ,    this.bidBuy1Amount ,    this.bidBuy2Num ,    this.bidBuy2Amount ,    this.bidBuy3Num ,    this.bidBuy3Amount ,    this.bidBuy4Num ,    this.bidBuy4Amount ,    this.bidBuy5Num ,    this.bidBuy5Amount ,    this.bidSale1Num ,    this.bidSale1Amount ,    this.bidSale2Num ,    this.bidSale2Amount ,    this.bidSale3Num ,    this.bidSale3Amount ,    this.bidSale4Num ,    this.bidSale4Amount ,    this.bidSale5Num ,    this.bidSale5Amount ,    this.date ,    this.time  )
  override def toString =  Array(this.code,this.name,this.curOpenPrice,this.lstOpenPrice,this.curPrice,this.highestPrice,this.lowestPrice,this.bidBuyPrice,this.bidSalePrice,this.dealNum,this.dealAmount,this.bidBuy1Num,this.bidBuy1Amount,this.bidBuy2Num,this.bidBuy2Amount,this.bidBuy3Num,this.bidBuy3Amount,this.bidBuy4Num,this.bidBuy4Amount,this.bidBuy5Num,this.bidBuy5Amount,this.bidSale1Num,this.bidSale1Amount,this.bidSale2Num,this.bidSale2Amount,this.bidSale3Num,this.bidSale3Amount,this.bidSale4Num,this.bidSale4Amount,this.bidSale5Num,this.bidSale5Amount,this.date,this.time).mkString(",")
  private var stockInfo :String =""
  def getStockInfo = stockInfo
  def this(stockInfo:String)
  {
    this()
    this.stockInfo=stockInfo
/** 根据新浪的数据接口解析数据 **/ val stockDetail=stockInfo.split(Array(' ','_','=',',','"')) if (stockDetail.length>36){ this.code=stockDetail(3) this.name=stockDetail(5) this.curOpenPrice =stockDetail(6).toFloat this.lstOpenPrice=stockDetail(7).toFloat this.curPrice =stockDetail(8).toFloat this.highestPrice =stockDetail(9).toFloat this.lowestPrice =stockDetail(10).toFloat this.bidBuyPrice=stockDetail(11).toFloat this.bidSalePrice=stockDetail(12).toFloat this.dealNum =stockDetail(13).toLong this.dealAmount =stockDetail(14).toFloat this.bidBuy1Num =stockDetail(15).toLong this.bidBuy1Amount =stockDetail(16).toFloat this.bidBuy2Num =stockDetail(17).toLong this.bidBuy2Amount =stockDetail(18).toFloat this.bidBuy3Num =stockDetail(19).toLong this.bidBuy3Amount =stockDetail(20).toFloat this.bidBuy4Num =stockDetail(21).toLong this.bidBuy4Amount =stockDetail(22).toFloat this.bidBuy5Num =stockDetail(23).toLong this.bidBuy5Amount =stockDetail(24).toFloat this.bidSale1Num =stockDetail(25).toLong this.bidSale1Amount =stockDetail(26).toFloat this.bidSale2Num =stockDetail(27).toLong this.bidSale2Amount =stockDetail(28).toFloat this.bidSale3Num =stockDetail(29).toLong this.bidSale3Amount =stockDetail(30).toFloat this.bidSale4Num =stockDetail(31).toLong this.bidSale4Amount =stockDetail(32).toFloat this.bidSale5Num =stockDetail(33).toLong this.bidSale5Amount =stockDetail(34).toFloat this.date =stockDetail(35) this.time =stockDetail(36) } } }
/** SinaStock的伴生对象,此处用来替代new **/ object SinaStock { def apply(stockInfo:String) :SinaStock = { new SinaStock(stockInfo) } } object StockRetrivor { def main(args: Array[String]): Unit = { println("查询新浪股票(每小时更新) http://hq.sinajs.cn/list=sh601006,sh601007")
/** 查询sh601006,sh601007两只股票 **/ val sinaStockStream = Source.fromURL("http://hq.sinajs.cn/list=sh601006,sh601007","gbk") val sinaLines=sinaStockStream.getLines for(line <- sinaLines) {
/** 将每行数据解析成SinaStock对象,并答应对应的股票信息 **/ println(SinaStock(line).toString) } sinaStockStream.close() } }

   三、Spark Streaming编程

   数据接口调试完毕,股票数据也解析好了,下面就开始Streaming。Spark Streaming一定会涉及数据源,且该数据源是一个主动推送的过程,即spark被动接受该数据源的数据进行分析。但Sina的接口是一个很简单的HttpResponse,无法主动推送数据,所以我们需要实现一个Custom Receiver,可参考 http://spark.apache.org/docs/latest/streaming-custom-receivers.html 

   下面是具体的代码,其实定制化一个Receiver简单来说就是实现onStart/onStop。onStart用来初始化资源,给获取数据做准备,获取到的数据用store发送给SparkStreaming即可;onStop用来释放资源

package com.gabry.stock

import org.apache.spark.Logging
import org.apache.spark.storage.StorageLevel
import org.apache.spark.streaming.receiver.Receiver

import scala.io.Source

/**
  * Created by gabry.wu on 2016/2/19.
  * 简单起见,只获取新浪股票数据,后续再进行重构
  */
class SinaStockReceiver extends Receiver[String](StorageLevel.MEMORY_AND_DISK_2) with Logging{
  def onStart() {
    /* 创建一个线程用来查询新浪股票数据,并将数据发送给Spark Streaming */
    new Thread("Socket Receiver") {
      override def run() { receive() }
    }.start()
  }

  def onStop() {
    // There is nothing much to do as the thread calling receive()
    // is designed to stop by itself isStopped() returns false
  }
  private def receive(): Unit = {
      try{
        while(!isStopped ) {
          var stockIndex = 1
          while(stockIndex!=0){
            val stockCode = 601000+stockIndex
            val url="http://hq.sinajs.cn/list=sh%d".format(stockCode)
            logInfo(url)
            val sinaStockStream = Source.fromURL(url,"gbk")
            val sinaLines=sinaStockStream.getLines
            for(line <- sinaLines) {
              logInfo(line)
              store(line)
            }
            sinaStockStream.close()
            stockIndex= (stockIndex+1)%1
          }
       
        }

        logInfo("Stopped receiving")
        restart("Trying to connect again")
      } catch {
        case e: java.net.ConnectException =>
          restart("Error connecting to", e)
        case t: Throwable =>
          restart("Error receiving data", t)
      }
    }
}

   Receiver搞定之后就可以开始编写股票预测的main函数了,贴代码之前说明一下,股票预测的方法之一,就是统计一段时间内股票上涨的次数,并展示上涨次数TopN的股票信息,但本文一切从简,并没有实现全部的功能,只是统计了股票上涨的次数,也就是对上涨与否进行WordCount。

 

/**
  * Created by gabry.wu on 2016/2/19.
  */
package com.gabry.stock

import org.apache.log4j.{Level, Logger}
import org.apache.spark.{HashPartitioner, SparkConf}
import org.apache.spark.streaming.{Seconds, StreamingContext}

object StockTrend {
  def updatePriceTrend( newValue:Seq[(Float,Int)],preValue :Option[(Float,Int)]):Option[(Float,Int)] = {
    if (newValue.length>0){
      val priceDiff=newValue(0)._1 - preValue.getOrElse((newValue(0)._1 ,0))._1
      // ("update state: new Value "+newValue(0) + ",pre Value " + preValue.getOrElse((newValue(0)._1 ,0)))
      Some((newValue(0)._1,priceDiff.compareTo(0.0f)))
    }else preValue
  }

  def main(args: Array[String]): Unit = {
    val sparkConf = new SparkConf().setAppName("CustomReceiver").setMaster("local[4]")
    val ssc = new StreamingContext(sparkConf, Seconds(1))
    Logger.getRootLogger.setLevel(Level.WARN)
    ssc.checkpoint("./tmp")
    /* 创建股票的输入流,该输入流是自定义的 */
    val lines = ssc.receiverStream(new SinaStockReceiver())
/** 将数据的每一行映射成一个SinaStock对象。注意此处的每一行数据都是SinaStockReceiver对象调用store传过来的 **/ val words = lines.map(SinaStock(_)) import scala.util.Random /* reduce从左到右进行折叠。其实就是先处理t-6,t-5的RDD,将结果与t-4的RDD再次调用reduceFunc,依次类推直到当前RDD */ def reduceFunc( left :(Float,Int),right:(Float,Int)):(Float,Int) = { println("left "+left+"right "+right) (right._1,left._2+right._2) } /* 3点之后股票价格不在变化,故为了测试,此处使用随机数修改股票当前价格 */ /* 根据上一次股票价格更新股票的变化方向 */
/** 由于股票信息只有当前价格,如果要判断股票上涨与否就要记录上一次的股票价格,所以此处使用updateStateByKey更新当前股票价格是否上涨。
    若上涨则记为1,不变记为0,否则记为1
**/ val stockState = words.map(sinaStock => (sinaStock.name, (sinaStock.curPrice+Random.nextFloat,-1))).filter(stock=>stock._1.isEmpty==false)
.updateStateByKey(updatePriceTrend) /* 每3秒,处理过去6秒的数据,对数据进行变化的累加 */ val stockTrend=stockState.reduceByKeyAndWindow(reduceFunc(_,_),Seconds(6),Seconds(3)) /* 每3秒,处理过去6秒的数据,对数据进行正向变化的累加 */ //val stockPosTrend=stockState.filter(x=>x._2._2>=0).reduceByKeyAndWindow(reduceFunc(_,_),Seconds(6),Seconds(3)) stockState.print() stockTrend.print() //stockPosTrend.print() ssc.start() ssc.awaitTermination() println("StockTrend") } }

   四、运行结果分析

  下面是某次运行的打印结果,对其进行简单的分析。

  由于ssc的时间间隔为1,所以每秒都会查询大同煤业的股票数据,这就是下面每个Time打印的第一行数据(因为stockState先进行print,所以每次查询的股票数据是第一行);又因为slide设置为3,所以每隔3秒会进行reduceFunc计算,该函数处理windowsize个RDD(此处设置为6),对这6个RDD按照时间先后顺序进行reduce。

  需要特别说明的是spark的reduce默认从左到右进行fold(折叠),从最左边取两个数进行reduce计算产生临时结果,再与后面的数据进行reduce,以此类推进行计算,其实就是foldLeft。

  下面标红色的数据,其实就是对(5.387682,0),(5.9087195,1),(5.7605586,-1),(5.278526,-1),(5.4471517,1),(5.749305,1)进行reduce的过程。

-------------------------------------------

Time: 1455888254000 ms

-------------------------------------------

(大同煤业,(5.387682,0))

-------------------------------------------

Time: 1455888255000 ms

-------------------------------------------

(大同煤业,(5.9087195,1))

-------------------------------------------

Time: 1455888256000 ms

-------------------------------------------

(大同煤业,(5.7605586,-1))

 

left (5.387682,0)right (5.9087195,1)

left (5.9087195,1)right (5.7605586,-1)

-------------------------------------------

Time: 1455888256000 ms

-------------------------------------------

(大同煤业,(5.7605586,0))

-------------------------------------------

Time: 1455888257000 ms

-------------------------------------------

(大同煤业,(5.278526,-1))

-------------------------------------------

Time: 1455888258000 ms

-------------------------------------------

(大同煤业,(5.4471517,1))

-------------------------------------------

Time: 1455888259000 ms

-------------------------------------------

(大同煤业,(5.749305,1))

 

left (5.387682,0)right (5.9087195,1)

left (5.9087195,1)right (5.7605586,-1)

left (5.7605586,0)right (5.278526,-1)

left (5.278526,-1)right (5.4471517,1)

left (5.4471517,0)right (5.749305,1)

-------------------------------------------

Time: 1455888259000 ms

-------------------------------------------

(大同煤业,(5.749305,1))

-------------------------------------------

Time: 1455888260000 ms

-------------------------------------------

(大同煤业,(5.749305,1))

-------------------------------------------

Time: 1455888261000 ms

-------------------------------------------

(大同煤业,(5.748391,-1))

-------------------------------------------

Time: 1455888262000 ms

-------------------------------------------

(大同煤业,(5.395269,-1))

 

left (5.278526,-1)right (5.4471517,1)

left (5.4471517,0)right (5.749305,1)

left (5.749305,1)right (5.749305,1)

left (5.749305,2)right (5.748391,-1)

left (5.748391,1)right (5.395269,-1)

-------------------------------------------

Time: 1455888262000 ms

-------------------------------------------

(大同煤业,(5.395269,0))

-------------------------------------------

Time: 1455888263000 ms

-------------------------------------------

(大同煤业,(5.5215807,1))

-------------------------------------------

Time: 1455888264000 ms

-------------------------------------------

(大同煤业,(5.945005,1))

-------------------------------------------

Time: 1455888265000 ms

-------------------------------------------

(大同煤业,(5.2400274,-1))

 

left (5.749305,1)right (5.748391,-1)

left (5.748391,0)right (5.395269,-1)

left (5.395269,-1)right (5.5215807,1)

left (5.5215807,0)right (5.945005,1)

left (5.945005,1)right (5.2400274,-1)

-------------------------------------------

Time: 1455888265000 ms

-------------------------------------------

(大同煤业,(5.2400274,0))

-------------------------------------------

Time: 1455888266000 ms

-------------------------------------------

(大同煤业,(5.1895638,-1))

-------------------------------------------

Time: 1455888267000 ms

-------------------------------------------

(大同煤业,(5.1885605,-1))

-------------------------------------------

Time: 1455888268000 ms

-------------------------------------------

(大同煤业,(5.9881735,1)) 

Process finished with exit code -1

   五、总结

  本文以股票预测为例简单描述了SparkStreaming编程的步骤及其注意点,希望抛砖引玉,也算弥补了网上没有完整例子的遗憾。但由于作者重代码、轻描述,估计会有一些不易理解的地方,还望各位读者留言讨论。最后附上源码的git地址:http://git.oschina.net/gabry_wu/BigDataPractice

 

PS:未经允许,禁止转载,否则将追究法律责任!

 

评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值