kmeans

 def train(
      data: RDD[Vector],
      k: Int,
      maxIterations: Int,
      runs: Int,
      initializationMode: String): KMeansModel = {
    new KMeans().setK(k)
      .setMaxIterations(maxIterations)
      .setRuns(runs)
      .setInitializationMode(initializationMode)
      .run(data)
  }

 def run(data: RDD[Vector]): KMeansModel = {
    if (data.getStorageLevel == StorageLevel.NONE) {
      logWarning("The input data is not directly cached, which may hurt performance if its"
        + " parent RDDs are also uncached.")
    }
    // Compute squared norms and cache them.
//求2范数
    val norms = data.map(Vectors.norm(_, 2.0))
    norms.persist()
//将向量和平方和zip起来
    val zippedData = data.zip(norms).map { case (v, norm) =>
      new VectorWithNorm(v, norm)
    }
//这个是大头
    val model = runAlgorithm(zippedData)
//原来还能主动unpersist的，涨姿势了
    norms.unpersist()
    // Warn at the end of the run as well, for increased visibility.
    if (data.getStorageLevel == StorageLevel.NONE) {
      logWarning("The input data was not directly cached, which may hurt performance if its"
        + " parent RDDs are also uncached.")
    }
    model
  }

  def norm(vector: Vector, p: Double): Double = {
    require(p >= 1.0, "To compute the p-norm of the vector, we require that you specify a p>=1. " +
      s"You specified p=$p.")
    val values = vector match {
      case DenseVector(vs) => vs
      case SparseVector(n, ids, vs) => vs
      case v => throw new IllegalArgumentException("Do not support vector type " + v.getClass)
    }
    val size = values.length
    if (p == 1) {
      var sum = 0.0
      var i = 0
      while (i < size) {
        sum += math.abs(values(i))
        i += 1
      }
      sum
    } else if (p == 2) {
      var sum = 0.0
      var i = 0
      while (i < size) {
        sum += values(i) * values(i)
        i += 1
      }
      math.sqrt(sum)
    } else if (p == Double.PositiveInfinity) {
      var max = 0.0
      var i = 0
      while (i < size) {
        val value = math.abs(values(i))
        if (value > max) max = value
        i += 1
      }
      max
    } else {
      var sum = 0.0
      var i = 0
      while (i < size) {
        sum += math.pow(math.abs(values(i)), p)
        i += 1
      }
      math.pow(sum, 1.0 / p)
    }
  }