コード例 #1
0
ファイル: GLRMModel.java プロジェクト: vijaykiran/h2o-3
  /**
   * Project each archetype into original feature space
   *
   * @param frame Original training data with m rows and n columns
   * @param destination_key Frame Id for output
   * @return Frame containing k rows and n columns, where each row corresponds to an archetype
   */
  public Frame scoreArchetypes(Frame frame, Key destination_key, boolean reverse_transform) {
    final int ncols = _output._names.length;
    Frame adaptedFr = new Frame(frame);
    adaptTestForTrain(adaptedFr, true, false);
    assert ncols == adaptedFr.numCols();
    String[][] adaptedDomme = adaptedFr.domains();
    double[][] proj = new double[_parms._k][_output._nnums + _output._ncats];

    // Categorical columns
    for (int d = 0; d < _output._ncats; d++) {
      double[][] block = _output._archetypes_raw.getCatBlock(d);
      for (int k = 0; k < _parms._k; k++)
        proj[k][_output._permutation[d]] = _parms.mimpute(block[k], _output._lossFunc[d]);
    }

    // Numeric columns
    for (int d = _output._ncats; d < (_output._ncats + _output._nnums); d++) {
      int ds = d - _output._ncats;
      for (int k = 0; k < _parms._k; k++) {
        double num = _output._archetypes_raw.getNum(ds, k);
        proj[k][_output._permutation[d]] = _parms.impute(num, _output._lossFunc[d]);
        if (reverse_transform)
          proj[k][_output._permutation[d]] =
              proj[k][_output._permutation[d]] / _output._normMul[ds] + _output._normSub[ds];
      }
    }

    // Convert projection of archetypes into a frame with correct domains
    Frame f =
        ArrayUtils.frame(
            (null == destination_key ? Key.make() : destination_key), adaptedFr.names(), proj);
    for (int i = 0; i < ncols; i++) f.vec(i).setDomain(adaptedDomme[i]);
    return f;
  }
コード例 #2
0
ファイル: GLRMModel.java プロジェクト: vijaykiran/h2o-3
 public static int mimpute(double[] u, Loss multi_loss) {
   assert multi_loss.isForCategorical()
       : "Loss function " + multi_loss + " not applicable to categoricals";
   switch (multi_loss) {
     case Categorical:
     case Ordinal:
       double[] cand = new double[u.length];
       for (int a = 0; a < cand.length; a++) cand[a] = mloss(u, a, multi_loss);
       return ArrayUtils.minIndex(cand);
     default:
       throw new RuntimeException("Unknown multidimensional loss function " + multi_loss);
   }
 }
コード例 #3
0
ファイル: GLRMModel.java プロジェクト: vijaykiran/h2o-3
    // public final double[] rproxgrad_x(double[] u, double alpha) { return rproxgrad(u, alpha,
    // _gamma_x, _regularization_x, RandomUtils.getRNG(_seed)); }
    // public final double[] rproxgrad_y(double[] u, double alpha) { return rproxgrad(u, alpha,
    // _gamma_y, _regularization_y, RandomUtils.getRNG(_seed)); }
    static double[] rproxgrad(
        double[] u, double alpha, double gamma, Regularizer regularization, Random rand) {
      if (u == null || alpha == 0 || gamma == 0) return u;
      double[] v = new double[u.length];

      switch (regularization) {
        case None:
          return u;
        case Quadratic:
          for (int i = 0; i < u.length; i++) v[i] = u[i] / (1 + 2 * alpha * gamma);
          return v;
        case L2:
          // Proof uses Moreau decomposition; see section 6.5.1 of Parikh and Boyd
          // https://web.stanford.edu/~boyd/papers/pdf/prox_algs.pdf
          double weight = 1 - alpha * gamma / ArrayUtils.l2norm(u);
          if (weight < 0) return v; // Zero vector
          for (int i = 0; i < u.length; i++) v[i] = weight * u[i];
          return v;
        case L1:
          for (int i = 0; i < u.length; i++)
            v[i] = Math.max(u[i] - alpha * gamma, 0) + Math.min(u[i] + alpha * gamma, 0);
          return v;
        case NonNegative:
          for (int i = 0; i < u.length; i++) v[i] = Math.max(u[i], 0);
          return v;
        case OneSparse:
          int idx = ArrayUtils.maxIndex(u, rand);
          v[idx] = u[idx] > 0 ? u[idx] : 1e-6;
          return v;
        case UnitOneSparse:
          idx = ArrayUtils.maxIndex(u, rand);
          v[idx] = 1;
          return v;
        case Simplex:
          // Proximal gradient algorithm by Chen and Ye in http://arxiv.org/pdf/1101.6081v2.pdf
          // 1) Sort input vector u in ascending order: u[1] <= ... <= u[n]
          int n = u.length;
          int[] idxs = new int[n];
          for (int i = 0; i < n; i++) idxs[i] = i;
          ArrayUtils.sort(idxs, u);

          // 2) Calculate cumulative sum of u in descending order
          // cumsum(u) = (..., u[n-2]+u[n-1]+u[n], u[n-1]+u[n], u[n])
          double[] ucsum = new double[n];
          ucsum[n - 1] = u[idxs[n - 1]];
          for (int i = n - 2; i >= 0; i--) ucsum[i] = ucsum[i + 1] + u[idxs[i]];

          // 3) Let t_i = (\sum_{j=i+1}^n u[j] - 1)/(n - i)
          // For i = n-1,...,1, set optimal t* to first t_i >= u[i]
          double t = (ucsum[0] - 1) / n; // Default t* = (\sum_{j=1}^n u[j] - 1)/n
          for (int i = n - 1; i >= 1; i--) {
            double tmp = (ucsum[i] - 1) / (n - i);
            if (tmp >= u[idxs[i - 1]]) {
              t = tmp;
              break;
            }
          }

          // 4) Return max(u - t*, 0) as projection of u onto simplex
          double[] x = new double[u.length];
          for (int i = 0; i < u.length; i++) x[i] = Math.max(u[i] - t, 0);
          return x;
        default:
          throw new RuntimeException("Unknown regularization function " + regularization);
      }
    }