private double multiLL(DoubleMatrix2D coeffs, Node dep, List<Node> indep) {

    DoubleMatrix2D indepData =
        factory2D.make(internalData.subsetColumns(indep).getDoubleData().toArray());
    List<Node> depList = new ArrayList<>();
    depList.add(dep);
    DoubleMatrix2D depData =
        factory2D.make(internalData.subsetColumns(depList).getDoubleData().toArray());

    int N = indepData.rows();
    DoubleMatrix2D probs =
        Algebra.DEFAULT.mult(factory2D.appendColumns(factory2D.make(N, 1, 1.0), indepData), coeffs);

    probs =
        factory2D
            .appendColumns(factory2D.make(indepData.rows(), 1, 1.0), probs)
            .assign(Functions.exp);
    double ll = 0;
    for (int i = 0; i < N; i++) {
      DoubleMatrix1D curRow = probs.viewRow(i);
      curRow.assign(Functions.div(curRow.zSum()));
      ll += Math.log(curRow.get((int) depData.get(i, 0)));
    }
    return ll;
  }
Esempio n. 2
0
  public void compute() {

    alpha_Y.assign(1);
    initMDone = false;
    boolean doScaling = params.doScaling;

    if ((beta_Y == null) || (beta_Y.length < dataSeq.length())) {
      beta_Y = new DenseDoubleMatrix1D[2 * dataSeq.length()];
      for (int i = 0; i < beta_Y.length; i++) beta_Y[i] = new DenseDoubleMatrix1D(numY);

      scale = new double[2 * dataSeq.length()];
      scale[dataSeq.length() - 1] = (doScaling) ? numY : 1;
      beta_Y[dataSeq.length() - 1].assign(1.0 / scale[dataSeq.length() - 1]);
    }
    beta.add(beta_Y[dataSeq.length() - 1]);
    // System.out.println("Beta "+beta_Y[3].toString());
    for (int i = dataSeq.length() - 1; i > 0; i--) {
      if (params.debugLvl > 2) {
        Util.printDbg("Features fired");
        // featureGenerator.startScanFeaturesAt(dataSeq, i);
        // while (featureGenerator.hasNext()) {
        // Feature feature = featureGenerator.next();
        // Util.printDbg(feature.toString());
        // }
      }

      // compute the Mi matrix
      // System.out.println("MI previous" +Mi_YY.toString());
      initMDone =
          Trainer.computeLogMi(
              featureGenerator, lambda, dataSeq, i, Mi_YY, Ri_Y, true, reuseM, initMDone);
      // System.out.println("MI "+Mi_YY.toString());
      tmp_Y.assign(beta_Y[i]);
      tmp_Y.assign(Ri_Y, multFunc);
      RobustMath.Mult(Mi_YY, tmp_Y, beta_Y[i - 1], 1, 0, false, edgeGen);

      // need to scale the beta-s to avoid overflow
      scale[i - 1] = doScaling ? beta_Y[i - 1].zSum() : 1;
      if ((scale[i - 1] < 1) && (scale[i - 1] > -1)) scale[i - 1] = 1;
      constMultiplier.multiplicator = 1.0 / scale[i - 1];
      beta_Y[i - 1].assign(constMultiplier);
      // System.out.println("Beta "+beta_Y[i - 1].toString() + " ");
      beta.add(beta_Y[i - 1]);
    }

    double thisSeqLogli = 0;
    System.out.println("\n");
    // Mi_YY.assign(0);
    alpha_temp = new DenseDoubleMatrix1D[2 * dataSeq.length()];
    for (int i = 0; i < dataSeq.length(); i++) alpha_temp[i] = new DenseDoubleMatrix1D(numY);

    for (int i = 0; i < dataSeq.length(); i++) {
      // compute the Mi matrix
      //
      initMDone =
          Trainer.computeLogMi(
              featureGenerator, lambda, dataSeq, i, Mi_YY, Ri_Y, true, reuseM, initMDone);
      // System.out.println("MI: " + Mi_YY.toString());
      // find features that fire at this position..
      featureGenerator.startScanFeaturesAt(dataSeq, i);

      if (i > 0) {
        tmp_Y.assign(alpha_Y);
        RobustMath.Mult(Mi_YY, tmp_Y, newAlpha_Y, 1, 0, true, edgeGen);
        // Mi_YY.zMult(tmp_Y, newAlpha_Y,1,0,true);
        newAlpha_Y.assign(Ri_Y, multFunc);
      } else {
        newAlpha_Y.assign(Ri_Y);
      }
      while (featureGenerator.hasNext()) {
        Feature feature = featureGenerator.next();
        int f = feature.index();

        int yp = feature.y();
        int yprev = feature.yprev();
        float val = feature.value();
        if ((dataSeq.y(i) == yp)
            && (((i - 1 >= 0) && (yprev == dataSeq.y(i - 1))) || (yprev < 0))) {

          thisSeqLogli += val * lambda[f];
        }
      }

      alpha_Y.assign(newAlpha_Y);
      // now scale the alpha-s to avoid overflow problems.
      constMultiplier.multiplicator = 1.0 / scale[i];
      alpha_Y.assign(constMultiplier);
      alpha_temp[i].assign(newAlpha_Y);
      alpha_temp[i].assign(constMultiplier);
      // System.out.println("ALpha "+alpha_Y.toString());
      alpha.add(alpha_temp[i]);
      if (params.debugLvl > 2) {
        System.out.println("Alpha-i " + alpha_Y.toString());
        System.out.println("Ri " + Ri_Y.toString());
        System.out.println("Mi " + Mi_YY.toString());
        System.out.println("Beta-i " + beta_Y[i].toString());
      }
    }

    Zx = alpha_Y.zSum();
    System.out.println("Zx: " + Zx);
  } /* end of computeBeta */
Esempio n. 3
0
  protected double computeFunctionGradient(double lambda[], double grad[]) {
    initMDone = false;

    if (params.trainerType.equals("ll")) return computeFunctionGradientLL(lambda, grad);
    double logli = 0;
    try {
      for (int f = 0; f < lambda.length; f++) {
        grad[f] = -1 * lambda[f] * params.invSigmaSquare;
        logli -= ((lambda[f] * lambda[f]) * params.invSigmaSquare) / 2;
      }
      boolean doScaling = params.doScaling;

      diter.startScan();
      if (featureGenCache != null) featureGenCache.startDataScan();
      int numRecord = 0;
      for (numRecord = 0; diter.hasNext(); numRecord++) {
        DataSequence dataSeq = (DataSequence) diter.next();
        if (featureGenCache != null) featureGenCache.nextDataIndex();
        if (params.debugLvl > 1) {
          Util.printDbg("Read next seq: " + numRecord + " logli " + logli);
        }
        alpha_Y.assign(1);
        for (int f = 0; f < lambda.length; f++) ExpF[f] = 0;

        if ((beta_Y == null) || (beta_Y.length < dataSeq.length())) {
          beta_Y = new DenseDoubleMatrix1D[2 * dataSeq.length()];
          for (int i = 0; i < beta_Y.length; i++) beta_Y[i] = new DenseDoubleMatrix1D(numY);

          scale = new double[2 * dataSeq.length()];
        }
        // compute beta values in a backward scan.
        // also scale beta-values to 1 to avoid numerical problems.
        scale[dataSeq.length() - 1] = (doScaling) ? numY : 1;
        beta_Y[dataSeq.length() - 1].assign(1.0 / scale[dataSeq.length() - 1]);
        for (int i = dataSeq.length() - 1; i > 0; i--) {
          if (params.debugLvl > 2) {
            Util.printDbg("Features fired");
            // featureGenerator.startScanFeaturesAt(dataSeq, i);
            // while (featureGenerator.hasNext()) {
            // Feature feature = featureGenerator.next();
            // Util.printDbg(feature.toString());
            // }
          }

          // compute the Mi matrix
          initMDone =
              computeLogMi(
                  featureGenerator, lambda, dataSeq, i, Mi_YY, Ri_Y, true, reuseM, initMDone);
          tmp_Y.assign(beta_Y[i]);
          tmp_Y.assign(Ri_Y, multFunc);
          RobustMath.Mult(Mi_YY, tmp_Y, beta_Y[i - 1], 1, 0, false, edgeGen);
          //		Mi_YY.zMult(tmp_Y, beta_Y[i-1]);

          // need to scale the beta-s to avoid overflow
          scale[i - 1] = doScaling ? beta_Y[i - 1].zSum() : 1;
          if ((scale[i - 1] < 1) && (scale[i - 1] > -1)) scale[i - 1] = 1;
          constMultiplier.multiplicator = 1.0 / scale[i - 1];
          beta_Y[i - 1].assign(constMultiplier);
        }

        double thisSeqLogli = 0;
        for (int i = 0; i < dataSeq.length(); i++) {
          // compute the Mi matrix
          initMDone =
              computeLogMi(
                  featureGenerator, lambda, dataSeq, i, Mi_YY, Ri_Y, true, reuseM, initMDone);
          // find features that fire at this position..
          featureGenerator.startScanFeaturesAt(dataSeq, i);

          if (i > 0) {
            tmp_Y.assign(alpha_Y);
            RobustMath.Mult(Mi_YY, tmp_Y, newAlpha_Y, 1, 0, true, edgeGen);
            //		Mi_YY.zMult(tmp_Y, newAlpha_Y,1,0,true);
            newAlpha_Y.assign(Ri_Y, multFunc);
          } else {
            newAlpha_Y.assign(Ri_Y);
          }
          while (featureGenerator.hasNext()) {
            Feature feature = featureGenerator.next();
            int f = feature.index();

            int yp = feature.y();
            int yprev = feature.yprev();
            float val = feature.value();
            if ((dataSeq.y(i) == yp)
                && (((i - 1 >= 0) && (yprev == dataSeq.y(i - 1))) || (yprev < 0))) {
              grad[f] += val;
              thisSeqLogli += val * lambda[f];
            }
            if (yprev < 0) {
              ExpF[f] += newAlpha_Y.get(yp) * val * beta_Y[i].get(yp);
            } else {
              ExpF[f] +=
                  alpha_Y.get(yprev)
                      * Ri_Y.get(yp)
                      * Mi_YY.get(yprev, yp)
                      * val
                      * beta_Y[i].get(yp);
            }
          }

          alpha_Y.assign(newAlpha_Y);
          // now scale the alpha-s to avoid overflow problems.
          constMultiplier.multiplicator = 1.0 / scale[i];
          alpha_Y.assign(constMultiplier);

          if (params.debugLvl > 2) {
            System.out.println("Alpha-i " + alpha_Y.toString());
            System.out.println("Ri " + Ri_Y.toString());
            System.out.println("Mi " + Mi_YY.toString());
            System.out.println("Beta-i " + beta_Y[i].toString());
          }
        }
        double Zx = alpha_Y.zSum();
        thisSeqLogli -= log(Zx);
        // correct for the fact that alpha-s were scaled.
        for (int i = 0; i < dataSeq.length(); i++) {
          thisSeqLogli -= log(scale[i]);
        }

        logli += thisSeqLogli;
        // update grad.
        for (int f = 0; f < grad.length; f++) grad[f] -= ExpF[f] / Zx;

        if (params.debugLvl > 1) {
          System.out.println(
              "Sequence "
                  + thisSeqLogli
                  + " logli "
                  + logli
                  + " log(Zx) "
                  + Math.log(Zx)
                  + " Zx "
                  + Zx);
        }
      }
      if (params.debugLvl > 2) {
        for (int f = 0; f < lambda.length; f++) System.out.print(lambda[f] + " ");
        System.out.println(" :x");
        for (int f = 0; f < lambda.length; f++)
          System.out.println(featureGenerator.featureName(f) + " " + grad[f] + " ");
        System.out.println(" :g");
      }

      if (params.debugLvl > 0)
        Util.printDbg(
            "Iter "
                + icall
                + " log likelihood "
                + logli
                + " norm(grad logli) "
                + norm(grad)
                + " norm(x) "
                + norm(lambda));
      if (icall == 0) {
        System.out.println("Number of training records" + numRecord);
      }
    } catch (Exception e) {
      System.out.println("Alpha-i " + alpha_Y.toString());
      System.out.println("Ri " + Ri_Y.toString());
      System.out.println("Mi " + Mi_YY.toString());

      e.printStackTrace();
      System.exit(0);
    }
    return logli;
  }