Scala Matrix类代码示例

//设置package包名称以及导入依赖的类
package com.ferhtaydn.rater

import org.apache.spark.SparkContext
import org.apache.spark.ml.Pipeline
import org.apache.spark.ml.classification.LogisticRegression
import org.apache.spark.ml.evaluation.BinaryClassificationEvaluator
import org.apache.spark.ml.feature.{ StringIndexerModel, VectorAssembler }
import org.apache.spark.ml.tuning.{ CrossValidator, CrossValidatorModel, ParamGridBuilder }
import org.apache.spark.mllib.linalg.Matrix
import org.apache.spark.sql.{ DataFrame, Row, SQLContext }

class LRCV(sc: SparkContext) {

  implicit val sqlContext = new SQLContext(sc)

  val lr = new LogisticRegression().setMaxIter(10).setFeaturesCol("scaledFeatures")

  val paramGrid = new ParamGridBuilder()
    .addGrid(lr.regParam, Array(0.1, 0.01))
    .build()

  val assembler = new VectorAssembler()
    .setInputCols(Array("gender", "age", "weight", "height", "indexedJob"))
    .setOutputCol("features")

  val pipeline = new Pipeline()
    .setStages(Array(assembler, standardScaler("features"), lr))

  val cv = new CrossValidator()
    .setEstimator(pipeline)
    .setEvaluator(new BinaryClassificationEvaluator)
    .setEstimatorParamMaps(paramGrid)
    .setNumFolds(10)

  def train(df: DataFrame): (StringIndexerModel, CrossValidatorModel, Matrix) = {

    // need to index strings on all data to not missing the job fields.
    // other alternative can be manually assign values for each job like gender.
    val indexerModel = stringIndexer("job").fit(df)
    val indexed = indexerModel.transform(df)

    val splits = indexed.randomSplit(Array(0.8, 0.2))
    val training = splits(0).cache()
    val test = splits(1)

    val cvModel = cv.fit(training)

    val predictionAndLabels = cvModel
      .transform(test)
      .select("label", "prediction").map {
        case Row(label: Double, prediction: Double) ?
          (prediction, label)
      }

    printBinaryMetrics(predictionAndLabels)

    (indexerModel, cvModel, confusionMatrix(predictionAndLabels))

  }

} 

//设置package包名称以及导入依赖的类
package org.broadinstitute.hail.methods

import org.apache.spark.mllib.linalg.{Matrix, DenseMatrix}
import org.apache.spark.rdd.RDD
import org.broadinstitute.hail.variant.Variant
import org.broadinstitute.hail.variant.VariantDataset

class SamplePCA(k: Int, computeLoadings: Boolean, computeEigenvalues: Boolean) {
  def name = "SamplePCA"

  def apply(vds: VariantDataset): (Matrix, Option[RDD[(Variant, Array[Double])]], Option[Array[Double]])  = {

    val (variants, mat) = ToStandardizedIndexedRowMatrix(vds)
    val sc = vds.sparkContext
    val variantsBc = sc.broadcast(variants)

    val svd = mat.computeSVD(k, computeU = computeLoadings)

    val scores =
      svd.V.multiply(DenseMatrix.diag(svd.s))

    val loadings =
      if (computeLoadings)
        Some(svd.U.rows.map(ir =>
          (variantsBc.value(ir.index.toInt), ir.vector.toArray)))
      else
        None

    val eigenvalues =
      if (computeEigenvalues)
        Some(svd.s.toArray.map(x => x * x))
      else
        None

    (scores, loadings, eigenvalues)
  }
} 

//设置package包名称以及导入依赖的类
package graph

import org.apache.spark.SparkContext
import org.apache.spark.graphx.{EdgeDirection, Edge, Graph}
import org.apache.spark.mllib.clustering.KMeans
import org.apache.spark.mllib.linalg.{DenseVector, Vector, Matrix, Vectors}
import org.apache.spark.mllib.linalg.distributed.RowMatrix
import org.apache.spark.rdd.RDD
import scala.collection.mutable


class PCAClustering {
  def matrixToRDD(sc:SparkContext, m: Matrix): RDD[Vector] = {
    val columns = m.toArray.grouped(m.numRows)
    val rows = columns.toSeq.transpose // Skip this if you want a column-major RDD.
    val vectors = rows.map(row => new DenseVector(row.toArray))
    sc.parallelize(vectors)
  }

  def run(inputGraph: Graph[Any, Any], clusterNum: Int, eigsNum: Int,sc:SparkContext ): Graph[Int, Any] = {
    val numNode = inputGraph.numVertices.toInt
    val mapping = new mutable.HashMap[Long,Int]()
    val revMapping = new mutable.HashMap[Int, Long]()

    val verticeIds = inputGraph.vertices.map( u => u._1 ).collect()
    for(i<-0 to numNode - 1) {
      mapping.put(verticeIds.apply(i), i)
      revMapping.put(i, verticeIds.apply(i))
    }

    //reindex the verteces from 0 to the num of nodes
    val nVertices = inputGraph.vertices.map( u=> (mapping.apply(u._1).toLong, u._2))
    val nEdges = inputGraph.edges.map(e=> Edge(mapping.apply(e.srcId).toLong, mapping.apply(e.dstId).toLong, e.attr))
    val ngraph = Graph(nVertices, nEdges)

    val output = ngraph.collectNeighborIds(EdgeDirection.Out)
    val spvec = output.mapValues(r => Vectors.sparse( numNode,  r.map(e=>e.toInt) , r.map(e=> 1.0/r.length )))
    val rows = spvec.map(v=>v._2)
    val order = spvec.map(v=>v._1)
    val mat = new RowMatrix(rows)

    val pc = mat.computePrincipalComponents(eigsNum)


    val pcRDD = matrixToRDD(sc, pc)
    val clusters = KMeans.train(pcRDD, clusterNum, 100)

    val clusterArray = pcRDD.map(p=> clusters.predict(p) ).collect()
    val assignedClusters = order.map( o => (o, clusterArray.apply(o.toInt)))
    val origVerextRDD = assignedClusters.map{case (vid, value)=> (revMapping.apply(vid.toInt), value)}
    Graph(origVerextRDD, inputGraph.edges)

  }

} 

//设置package包名称以及导入依赖的类
package com.ferhtaydn.rater

import akka.actor.ActorSystem
import com.ferhtaydn.models.PatientInfo
import org.apache.spark.ml.feature.StringIndexerModel
import org.apache.spark.ml.tuning.CrossValidatorModel
import org.apache.spark.mllib.linalg.{ Matrix, Vector }
import org.apache.spark.sql.{ Row, SQLContext }

import scala.concurrent.{ ExecutionContextExecutor, Future }

class RatePredictor(system: ActorSystem, sqlContext: SQLContext,
    indexModel: StringIndexerModel, cvModel: CrossValidatorModel,
    confusionMatrix: String) {

  private val decimalFormatter = new java.text.DecimalFormat("##.##")
  private val blockingDispatcher: ExecutionContextExecutor = system.dispatchers.lookup("ml.predictor.dispatcher")

  def confusionMatrixString: Future[String] = {
    Future {
      confusionMatrix
    }(blockingDispatcher)
  }

  def predict(patientInfo: PatientInfo): Future[Either[String, Double]] = {

    Future {

      val df = sqlContext.createDataFrame(Seq(patientInfo.toRecord))
      val indexedJobDF = indexModel.transform(df)

      val result = cvModel
        .transform(indexedJobDF)
        .select("prediction", "probability").map {
          case Row(prediction: Double, probability: Vector) ?
            (probability, prediction)
        }

      result.collect().headOption match {
        case Some((prob, _)) ? Right(decimalFormatter.format(prob(1)).toDouble)
        case None            ? Left(s"No result can be predicted for the patient")
      }

    }(blockingDispatcher)
  }

} 

//设置package包名称以及导入依赖的类
package linalg.svd

import org.apache.spark.{SparkConf, SparkContext}
import org.apache.spark.mllib.linalg.distributed.RowMatrix
import org.apache.spark.mllib.linalg.{Matrix, SingularValueDecomposition, Vector, Vectors}
object SparkSVDExampleOne {

  def main(args: Array[String]) {
    val denseData = Seq(
      Vectors.dense(0.0, 1.0, 2.0, 1.0, 5.0, 3.3, 2.1),
      Vectors.dense(3.0, 4.0, 5.0, 3.1, 4.5, 5.1, 3.3),
      Vectors.dense(6.0, 7.0, 8.0, 2.1, 6.0, 6.7, 6.8),
      Vectors.dense(9.0, 0.0, 1.0, 3.4, 4.3, 1.0, 1.0)
    )
    val spConfig = (new SparkConf).setMaster("local").setAppName("SparkSVDDemo")
    val sc = new SparkContext(spConfig)
    val mat: RowMatrix = new RowMatrix(sc.parallelize(denseData, 2))

    // Compute the top 20 singular values and corresponding singular vectors.
    val svd: SingularValueDecomposition[RowMatrix, Matrix] = mat.computeSVD(7, computeU = true)
    val U: RowMatrix = svd.U // The U factor is a RowMatrix.
    val s: Vector = svd.s // The singular values are stored in a local dense vector.
    val V: Matrix = svd.V // The V factor is a local dense matrix.
    println("U:" + U)
    println("s:" + s)
    println("V:" + V)
    sc.stop()
  }
} 

//设置package包名称以及导入依赖的类
package com.paypal.risk.smunf.math.stats

import org.apache.spark.mllib.linalg.Matrix

import scala.collection.mutable
import java.lang.Double.isNaN

class CorrelationMatrix(val values: Array[Double], val numRows: Int, val numCols: Int) {
  def apply(i: Int, j: Int): Double = values(index(i, j))

  private def index(i: Int, j: Int) = i + numRows * j

  def toString(headers: Map[Int, String]): String = {
    val corrMap = mutable.Map[String, Double]()
    for (row <- 0 until numRows) {
      for (col <- row + 1 until numCols) {
        val name = s"""${headers.getOrElse(row, "")}, ${headers.getOrElse(col, "")}"""
        corrMap(name) = values(index(row, col))
      }
    }
    val sorted = corrMap.toSeq.sortBy(_._2).reverse
    sorted.map(x => s"'${x._1}' : ${x._2}").mkString("\n")
  }

  def toSimilarity: Seq[(Long, Long, Double)] = {
    val items = mutable.ArrayBuffer[(Long, Long, Double)]()
    for (row <- 0 until numRows)
      for (col <- row + 1 until numCols)
        items.append((row, col, math.abs(values(index(row, col)))))
    items.toSeq
  }
}

object CorrelationMatrix {
  def apply(matrix: Matrix): CorrelationMatrix = {
    val array = matrix.toArray.map(x => if (isNaN(x)) -2.0 else x)
    new CorrelationMatrix(array, matrix.numRows, matrix.numCols)
  }
} 

//设置package包名称以及导入依赖的类
//???
val result = h.sql("select max(visit_times) from model_input_active_t")   //??????
val max_visit_times = result.collect()(0).get(0).asInstanceOf[Int].toDouble
val result = h.sql("select min(visit_times) from model_input_active_t")   //??????
val min_visit_times = result.collect()(0).get(0).asInstanceOf[Int].toDouble
val region_visit_times =if(( max_visit_times - min_visit_times) == 0) 1 else ( max_visit_times - min_visit_times)


val result = h.sql("select max(last_online_time) from model_input_active_t")   //??????
val max_last_online_time = result.collect()(0).get(0).asInstanceOf[Int].toDouble
val result = h.sql("select min(last_online_time) from model_input_active_t")   //??????
val min_last_online_time = result.collect()(0).get(0).asInstanceOf[Int].toDouble
val region_last_online_time =if(( max_last_online_time - min_last_online_time ) == 0) 1 else ( max_last_online_time - min_last_online_time)


val result = h.sql("select max(pay_times) from model_input_active_t")   //??????
val max_pay_times = result.collect()(0).get(0).asInstanceOf[Int].toDouble
val result = h.sql("select min(pay_times) from model_input_active_t")   //??????
val min_pay_times = result.collect()(0).get(0).asInstanceOf[Int].toDouble
val region_pay_times =if(( max_pay_times - min_pay_times ) == 0) 1 else (  max_pay_times - min_pay_times)

val result = h.sql("select max(comment_times) from model_input_active_t")   //???????
val max_comment_times = result.collect()(0).get(0).asInstanceOf[Int].toDouble
val result = h.sql("select min(comment_times) from model_input_active_t")   //???????
val min_comment_times = result.collect()(0).get(0).asInstanceOf[Int].toDouble
val region_comment_times =if(( max_comment_times - min_comment_times ) == 0) 1 else (  max_comment_times - min_comment_times)

val result = h.sql("select max(stay_time) from model_input_active_t")   //??????
val max_stay_time = result.collect()(0).get(0).asInstanceOf[Float].toDouble
val result = h.sql("select min(stay_time) from model_input_active_t")   //??????
val min_stay_time = result.collect()(0).get(0).asInstanceOf[Float].toDouble
val region_stay_time =if(( max_stay_time - min_stay_time ) == 0) 1 else (  max_stay_time - min_stay_time)


val result = h.sql("select max(visit_day_times) from model_input_active_t")   //??????
val max_visit_day_times = result.collect()(0).get(0).asInstanceOf[Int].toDouble
val result = h.sql("select min(visit_day_times) from model_input_active_t")   //??????
val min_visit_day_times = result.collect()(0).get(0).asInstanceOf[Int].toDouble
val region_visit_day_times =if(( max_visit_day_times - min_visit_day_times ) == 0) 1 else (   max_visit_day_times - min_visit_day_times)

//???visit_times:0.2,visit_targetpage_percen:0.1,last_online_time:0.1,pay_times:0.2,comment_times:0.2,stay_time:0.1,visit_day_times 0.1
val normalization= h.sql("select t1.cookie , ((t1.visit_times- "+min_visit_times+")*0.2/"+region_visit_times+") as visit_times, t1.visit_targetpage_percen*0.1, ((t1.last_online_time- "+min_last_online_time+")*0.1/"+region_last_online_time+") as last_online_time, ((t1.pay_times- "+min_pay_times+")*0.2/"+region_pay_times+") as pay_times, ((t1.comment_times- "+min_comment_times+")*0.2/"+region_comment_times+") as comment_times, ((t1.stay_time- "+min_stay_time+")*0.1/"+region_stay_time+") as stay_time, ((t1.visit_day_times- "+min_visit_day_times+")*0.1/"+region_visit_day_times+") as visit_day_times from model_input_active_t t1")


import org.apache.spark.mllib.linalg.Matrix
import org.apache.spark.mllib.linalg.Vectors
import org.apache.spark.mllib.linalg.distributed.RowMatrix


//DataFrame???Vectors???????API????Dataframe??rdd??????Vectors.dense????????
val data = normalization.rdd.map(line => Vectors.dense(line.get(1).toString.asInstanceOf[String].toDouble,line.get(2).toString.asInstanceOf[String].toDouble,line.get(3).toString.asInstanceOf[String].toDouble,line.get(4).toString.asInstanceOf[String].toDouble,line.get(5).toString.asInstanceOf[String].toDouble,line.get(6).toString.asInstanceOf[String].toDouble,line.get(7).toString.asInstanceOf[String].toDouble))

val rm = new RowMatrix(data)

val pc = rm.computePrincipalComponents(1)
val mx = rm.multiply(pc)

//???? 

//设置package包名称以及导入依赖的类
import org.apache.spark.mllib.linalg.Matrix

object CsvWriter {
  def writeMatrixToFile(matrix: Matrix, filename : String): Unit = {
    import java.io._

    val localMatrix: List[Array[Double]] = matrix
      .transpose // Transpose since .toArray is column major
      .toArray
      .grouped(matrix.numCols)
      .toList

    val lines: List[String] = localMatrix
      .map(line => line.mkString(","))
      .map(_ + "\n")

    val writer = new PrintWriter(new File(filename))
    lines.foreach(writer.write)
    writer.close()
  }
} 

//设置package包名称以及导入依赖的类
package org.apache.spark.examples.mllib
import org.apache.spark.mllib.linalg.{ Matrix, Matrices, Vectors }
import org.apache.spark.mllib.stat.Statistics
import org.apache.spark.{
  SparkConf,
  SparkContext

}

object ChiSqLearning {
  def main(args: Array[String]) {
    val vd = Vectors.dense(1, 2, 3, 4, 5)
    val vdResult = Statistics.chiSqTest(vd)
    println(vd)
    println(vdResult)
    println("-------------------------------")
    val mtx = Matrices.dense(3, 2, Array(1, 3, 5, 2, 4, 6))
    val mtxResult = Statistics.chiSqTest(mtx)
    println(mtx)
    println(mtxResult)
    
    //print :??????????????p?,???????p
    println("-------------------------------")
    val mtx2 = Matrices.dense(2, 2, Array(19.0, 34, 24, 10.0))
    printChiSqTest(mtx2)
    printChiSqTest(Matrices.dense(2, 2, Array(26.0, 36, 7, 2.0)))
    //    val mtxResult2 = Statistics.chiSqTest(mtx2)
    //    println(mtx2)
    //    println(mtxResult2)
  }

  def printChiSqTest(matrix: Matrix): Unit = {
    println("-------------------------------")
    val mtxResult2 = Statistics.chiSqTest(matrix)
    println(matrix)
    println(mtxResult2)
  }

}