写给开发者的机器学习指南（十一）

object PCA extends SimpleSwingApplication{
  def top = newMainFrame {
    title ="PCA Example"
    //Get theexample data
    val basePath ="/users/.../Example Data/"
    valexampleDataPath = basePath + "PCA_Example_1.csv"
    val trainData =getStockDataFromCSV(new File(exampleDataPath))
    }
  defgetStockDataFromCSV(file: File): (Array[Date],Array[Array[Double]]) = {
    val source =scala.io.Source.fromFile(file)
    //Get all therecords (minus the header)
    val data =source
        .getLines()
        .drop(1)
        .map(x=> getStockDataFromString(x))
        .toArray
    source.close()
    //group allrecords by date, and sort the groups on date ascending
    valgroupedByDate = data.groupBy(x => x._1).toArray.sortBy(x => x._1)
    //extract thevalues from the 3-tuple and turn them into
    // an array oftuples: Array[(Date, Array[Double)]
    valdateArrayTuples = groupedByDate
        .map(x=> (x._1, x
                       ._2
                       .sortBy(x => x._2)
                       .map(y => y._3)
                   )
            )
    //turn thetuples into two separate arrays for easier use later on
    val dateArray =dateArrayTuples.map(x => x._1).toArray
    val doubleArray= dateArrayTuples.map(x => x._2).toArray
   (dateArray,doubleArray)
  }
  defgetStockDataFromString(dataString: String): (Date,String,Double) = {
    //Split thecomma separated value string into an array of strings
    val dataArray:Array[String] = dataString.split(',')
    val format =new SimpleDateFormat("yyyy-MM-dd")
    //Extract thevalues from the strings
    val date =format.parse(dataArray(0))
    val stock:String = dataArray(1)
    val close:Double = dataArray(2).toDouble
    //And returnthe result in a format that can later 
    //easily beused to feed to Smile
   (date,stock,close)
  }
}
With this training data, and the fact that we already know that we want tomerge the 24 features into 1 single feature, we can do the PCA and retrieve thevalues for the datapoints as follows.
//Add to `def top`
val pca = new PCA(trainData._2)
pca.setProjection(1)
val points = pca.project(trainData._2)
val plotData = points
    .zipWithIndex
    .map(x =>Array(x._2.toDouble, -x._1(0) ))
val canvas: PlotCanvas = LinePlot.plot("MergedFeatures Index",
                                        plotData, 
                                        Line.Style.DASH,
                                        Color.RED);
peer.setContentPane(canvas)
size = new Dimension(400, 400)