真实的国产乱ⅩXXX66竹夫人,五月香六月婷婷激情综合,亚洲日本VA一区二区三区,亚洲精品一区二区三区麻豆

成都創(chuàng)新互聯(lián)網(wǎng)站制作重慶分公司

java中Spark中將對象序列化存儲到hdfs

java 中Spark中將對象序列化存儲到hdfs

創(chuàng)新互聯(lián)長期為千余家客戶提供的網(wǎng)站建設服務,團隊從業(yè)經(jīng)驗10年,關注不同地域、不同群體,并針對不同對象提供差異化的產(chǎn)品和服務;打造開放共贏平臺,與合作伙伴共同營造健康的互聯(lián)網(wǎng)生態(tài)環(huán)境。為酉陽土家族苗族企業(yè)提供專業(yè)的成都網(wǎng)站制作、成都網(wǎng)站建設,酉陽土家族苗族網(wǎng)站改版等技術服務。擁有10多年豐富建站經(jīng)驗和眾多成功案例,為您定制開發(fā)。

摘要: Spark應用中經(jīng)常會遇到這樣一個需求: 需要將JAVA對象序列化并存儲到HDFS, 尤其是利用MLlib計算出來的一些模型, 存儲到hdfs以便模型可以反復利用. 下面的例子演示了Spark環(huán)境下從Hbase讀取數(shù)據(jù), 生成一個word2vec模型, 存儲到hdfs.

廢話不多說, 直接貼代碼了. spark1.4 + hbase0.98

import org.apache.spark.storage.StorageLevel
import scala.collection.JavaConverters._
import java.io.File
import java.io.FileInputStream
import java.io.FileOutputStream
import java.io.ObjectInputStream
import java.io.ObjectOutputStream
import java.net.URI
import java.util.Date
import org.ansj.library.UserDefineLibrary
import org.ansj.splitWord.analysis.NlpAnalysis
import org.ansj.splitWord.analysis.ToAnalysis
import org.apache.hadoop.fs.FSDataInputStream
import org.apache.hadoop.fs.FSDataOutputStream
import org.apache.hadoop.fs.FileSystem
import org.apache.hadoop.fs.FileUtil
import org.apache.hadoop.fs.Path
import org.apache.hadoop.hbase.client._
import org.apache.hadoop.hbase.{HBaseConfiguration, HTableDescriptor, TableName}
import org.apache.hadoop.hbase.filter.FilterList
import org.apache.hadoop.hbase.filter.PageFilter
import org.apache.hadoop.hbase.filter.RegexStringComparator
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter
import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp
import org.apache.hadoop.hbase.mapreduce.TableInputFormat
import org.apache.hadoop.hbase.protobuf.ProtobufUtil
import org.apache.hadoop.hbase.util.{Base64, Bytes}
import com.feheadline.fespark.db.Neo4jManager
import com.feheadline.fespark.util.Env
import org.apache.spark.SparkConf
import org.apache.spark.SparkContext
import org.apache.spark.rdd._
import org.apache.spark.mllib.feature.{Word2Vec, Word2VecModel}
import scala.math.log
import scala.io.Source

object Word2VecDemo {

 def convertScanToString(scan: Scan) = {
  val proto = ProtobufUtil.toScan(scan)
  Base64.encodeBytes(proto.toByteArray)
 }

 def main(args: Array[String]): Unit = {
  val sparkConf = new SparkConf().setAppName("Word2Vec Demo")
  sparkConf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer")
  sparkConf.set("spark.kryoserializer.buffer", "256m")
  sparkConf.set("spark.kryoserializer.buffer.max","2046m")
  sparkConf.set("spark.akka.frameSize", "500")
  sparkConf.set("spark.rpc.askTimeout", "30")
  

  val sc = new SparkContext(sparkConf)
  val hbaseConf = HBaseConfiguration.create()
  hbaseConf.set("hbase.zookeeper.quorum", "myzookeeper")

  hbaseConf.set(TableInputFormat.INPUT_TABLE, "crawled")

  val scan = new Scan()
  val filterList:FilterList = new FilterList(FilterList.Operator.MUST_PASS_ALL)
  
  val comp:RegexStringComparator = new RegexStringComparator(""".{1500,}""")
  
  val articleFilter:SingleColumnValueFilter = new SingleColumnValueFilter(
  "data".getBytes,
  "article".getBytes,
  CompareOp.EQUAL,
  comp
  )
  
  filterList.addFilter(articleFilter)
  filterList.addFilter(new PageFilter(100))
  
  scan.setFilter(filterList)
  scan.setCaching(50)
  scan.setCacheBlocks(false)
  hbaseConf.set(TableInputFormat.SCAN,convertScanToString(scan))

  val crawledRDD = sc.newAPIHadoopRDD(
   hbaseConf,
   classOf[TableInputFormat],
   classOf[org.apache.hadoop.hbase.io.ImmutableBytesWritable],
   classOf[org.apache.hadoop.hbase.client.Result]
  )
 
  val articlesRDD = crawledRDD.filter{
   case (_,result) => {
     val content = Bytes.toString(result.getValue("data".getBytes,"article".getBytes))
     content != null
   }
  }

  val wordsInDoc = articlesRDD.map{
   case (_,result) => {
     val content = Bytes.toString(result.getValue("data".getBytes,"article".getBytes))
     if(content!=null)ToAnalysis.parse(content).asScala.map(_.getName).toSeq
     else Seq("")
   }
  }
  
  val fitleredWordsInDoc = wordsInDoc.filter(_.nonEmpty)
  
  val word2vec = new Word2Vec()
  val model = word2vec.fit(fitleredWordsInDoc)
  
  //---------------------------------------重點看這里-------------------------------------------------------------
  //將上面的模型存儲到hdfs
  val hadoopConf = sc.hadoopConfiguration
  hadoopConf.set("fs.defaultFS", "hdfs://myhadoop:9000/")
  val fileSystem = FileSystem.get(hadoopConf)
  val path = new Path("/user/hadoop/data/mllib/word2vec-object")
  val oos = new ObjectOutputStream(new FSDataOutputStream(fileSystem.create(path)))
  oos.writeObject(model)
  oos.close
  
  //這里示例另外一個程序直接從hdfs讀取序列化對象使用模型
  val ois = new ObjectInputStream(new FSDataInputStream(fileSystem.open(path)))
  val sample_model = ois.readObject.asInstanceOf[Word2VecModel]
  
  /*
  * //你還可以將序列化文件從hdfs放到本地, scala程序使用模型
  * import java.io._
  * import org.apache.spark.mllib.feature.{Word2Vec, Word2VecModel}
  * val ois = new ObjectInputStream(new FileInputStream("/home/cherokee/tmp/word2vec-object"))
  * val sample_model = ois.readObject.asInstanceOf[Word2VecModel]
  * ois.close
  */
  //--------------------------------------------------------------------------------------------------------------
 }
}


感謝閱讀,希望能幫助到大家,謝謝大家對本站的支持!


文章名稱:java中Spark中將對象序列化存儲到hdfs
鏈接分享:http://weahome.cn/article/jpdohh.html

其他資訊

在線咨詢

微信咨詢

電話咨詢

028-86922220(工作日)

18980820575(7×24)

提交需求

返回頂部