LocalLR

1. 生成Array,由N个 DataPoint(Vector, Double), DataPoint 由 rand 随机生成D个元素组成Vector

def generateData = {
    def generatePoint(i: Int) = {
      val y = if(i % 2 == 0) -1 else 1
      val x = DenseVector.fill(D){rand.nextGaussian + y * R}
      DataPoint(x, y)
    }
    Array.tabulate(N)(generatePoint)
  }

2. 定义 DataPoint

case class DataPoint(x: Vector[Double], y: Double)

3.随机初始化 系数 w (和vector维数一样D) 

var w = DenseVector.fill(D){2 * rand.nextDouble - 1}

4. 跌代 ITERATIONS次， 计算 gradient, 逻辑回归 (1/ 1+ e(-y * (w 点乘 vector(x))) - 1) * p.y 不断调节权重

 for (i <- 1 to ITERATIONS) {
      println("On iteration " + i)
      var gradient = DenseVector.zeros[Double](D)
      for (p <- data) {
        val scale = (1 / (1 + math.exp(-p.y * (w.dot(p.x)))) - 1) * p.y
        gradient +=  p.x * scale
      }
      w -= gradient
    }

5. 并行化

 val sparkConf = new SparkConf().setAppName("SparkLR")
    val sc = new SparkContext(sparkConf)
    val numSlices = if (args.length > 0) args(0).toInt else 2
    val points = sc.parallelize(generateData, numSlices).cache()

    // Initialize w to a random value
    var w = DenseVector.fill(D){2 * rand.nextDouble - 1}
    println("Initial w: " + w)

    for (i <- 1 to ITERATIONS) {
      println("On iteration " + i)
      val gradient = points.map { p =>
        p.x * (1 / (1 + exp(-p.y * (w.dot(p.x)))) - 1) * p.y
      }.reduce(_ + _)
      w -= gradient
    }

    println("Final w: " + w)
    sc.stop()