/**
   * Process a classifier's prediction for an instance and update a set of plotting instances and
   * additional plotting info. m_PlotShape for nominal class datasets holds shape types (actual data
   * points have automatic shape type assignment; classifier error data points have box shape type).
   * For numeric class datasets, the actual data points are stored in m_PlotInstances and m_PlotSize
   * stores the error (which is later converted to shape size values).
   *
   * @param toPredict the actual data point
   * @param classifier the classifier
   * @param eval the evaluation object to use for evaluating the classifier on the instance to
   *     predict
   * @see #m_PlotShapes
   * @see #m_PlotSizes
   * @see #m_PlotInstances
   */
  public void process(Instance toPredict, Classifier classifier, Evaluation eval) {
    double pred;
    double[] values;
    int i;

    try {
      pred = eval.evaluateModelOnceAndRecordPrediction(classifier, toPredict);

      if (classifier instanceof weka.classifiers.misc.InputMappedClassifier) {
        toPredict =
            ((weka.classifiers.misc.InputMappedClassifier) classifier)
                .constructMappedInstance(toPredict);
      }

      if (!m_SaveForVisualization) return;

      if (m_PlotInstances != null) {
        values = new double[m_PlotInstances.numAttributes()];
        for (i = 0; i < m_PlotInstances.numAttributes(); i++) {
          if (i < toPredict.classIndex()) {
            values[i] = toPredict.value(i);
          } else if (i == toPredict.classIndex()) {
            values[i] = pred;
            values[i + 1] = toPredict.value(i);
            i++;
          } else {
            values[i] = toPredict.value(i - 1);
          }
        }

        m_PlotInstances.add(new DenseInstance(1.0, values));

        if (toPredict.classAttribute().isNominal()) {
          if (toPredict.isMissing(toPredict.classIndex()) || Utils.isMissingValue(pred)) {
            m_PlotShapes.addElement(new Integer(Plot2D.MISSING_SHAPE));
          } else if (pred != toPredict.classValue()) {
            // set to default error point shape
            m_PlotShapes.addElement(new Integer(Plot2D.ERROR_SHAPE));
          } else {
            // otherwise set to constant (automatically assigned) point shape
            m_PlotShapes.addElement(new Integer(Plot2D.CONST_AUTOMATIC_SHAPE));
          }
          m_PlotSizes.addElement(new Integer(Plot2D.DEFAULT_SHAPE_SIZE));
        } else {
          // store the error (to be converted to a point size later)
          Double errd = null;
          if (!toPredict.isMissing(toPredict.classIndex()) && !Utils.isMissingValue(pred)) {
            errd = new Double(pred - toPredict.classValue());
            m_PlotShapes.addElement(new Integer(Plot2D.CONST_AUTOMATIC_SHAPE));
          } else {
            // missing shape if actual class not present or prediction is missing
            m_PlotShapes.addElement(new Integer(Plot2D.MISSING_SHAPE));
          }
          m_PlotSizes.addElement(errd);
        }
      }
    } catch (Exception ex) {
      ex.printStackTrace();
    }
  }
  /**
   * Accepts and processes a classifier encapsulated in an incremental classifier event
   *
   * @param ce an <code>IncrementalClassifierEvent</code> value
   */
  @Override
  public void acceptClassifier(final IncrementalClassifierEvent ce) {
    try {
      if (ce.getStatus() == IncrementalClassifierEvent.NEW_BATCH) {
        m_throughput = new StreamThroughput(statusMessagePrefix());
        m_throughput.setSamplePeriod(m_statusFrequency);

        // m_eval = new Evaluation(ce.getCurrentInstance().dataset());
        m_eval = new Evaluation(ce.getStructure());
        m_eval.useNoPriors();

        m_dataLegend = new Vector();
        m_reset = true;
        m_dataPoint = new double[0];
        Instances inst = ce.getStructure();
        System.err.println("NEW BATCH");
        m_instanceCount = 0;

        if (m_windowSize > 0) {
          m_window = new LinkedList<Instance>();
          m_windowEval = new Evaluation(ce.getStructure());
          m_windowEval.useNoPriors();
          m_windowedPreds = new LinkedList<double[]>();

          if (m_logger != null) {
            m_logger.logMessage(
                statusMessagePrefix()
                    + "[IncrementalClassifierEvaluator] Chart output using windowed "
                    + "evaluation over "
                    + m_windowSize
                    + " instances");
          }
        }

        /*
         * if (m_logger != null) { m_logger.statusMessage(statusMessagePrefix()
         * + "IncrementalClassifierEvaluator: started processing...");
         * m_logger.logMessage(statusMessagePrefix() +
         * " [IncrementalClassifierEvaluator]" + statusMessagePrefix() +
         * " started processing..."); }
         */
      } else {
        Instance inst = ce.getCurrentInstance();
        if (inst != null) {
          m_throughput.updateStart();
          m_instanceCount++;
          // if (inst.attribute(inst.classIndex()).isNominal()) {
          double[] dist = ce.getClassifier().distributionForInstance(inst);
          double pred = 0;
          if (!inst.isMissing(inst.classIndex())) {
            if (m_outputInfoRetrievalStats) {
              // store predictions so AUC etc can be output.
              m_eval.evaluateModelOnceAndRecordPrediction(dist, inst);
            } else {
              m_eval.evaluateModelOnce(dist, inst);
            }

            if (m_windowSize > 0) {

              m_windowEval.evaluateModelOnce(dist, inst);
              m_window.addFirst(inst);
              m_windowedPreds.addFirst(dist);

              if (m_instanceCount > m_windowSize) {
                // "forget" the oldest prediction
                Instance oldest = m_window.removeLast();

                double[] oldDist = m_windowedPreds.removeLast();
                oldest.setWeight(-oldest.weight());
                m_windowEval.evaluateModelOnce(oldDist, oldest);
                oldest.setWeight(-oldest.weight());
              }
            }
          } else {
            pred = ce.getClassifier().classifyInstance(inst);
          }
          if (inst.classIndex() >= 0) {
            // need to check that the class is not missing
            if (inst.attribute(inst.classIndex()).isNominal()) {
              if (!inst.isMissing(inst.classIndex())) {
                if (m_dataPoint.length < 2) {
                  m_dataPoint = new double[3];
                  m_dataLegend.addElement("Accuracy");
                  m_dataLegend.addElement("RMSE (prob)");
                  m_dataLegend.addElement("Kappa");
                }
                // int classV = (int) inst.value(inst.classIndex());

                if (m_windowSize > 0) {
                  m_dataPoint[1] = m_windowEval.rootMeanSquaredError();
                  m_dataPoint[2] = m_windowEval.kappa();
                } else {
                  m_dataPoint[1] = m_eval.rootMeanSquaredError();
                  m_dataPoint[2] = m_eval.kappa();
                }
                // int maxO = Utils.maxIndex(dist);
                // if (maxO == classV) {
                // dist[classV] = -1;
                // maxO = Utils.maxIndex(dist);
                // }
                // m_dataPoint[1] -= dist[maxO];
              } else {
                if (m_dataPoint.length < 1) {
                  m_dataPoint = new double[1];
                  m_dataLegend.addElement("Confidence");
                }
              }
              double primaryMeasure = 0;
              if (!inst.isMissing(inst.classIndex())) {
                if (m_windowSize > 0) {
                  primaryMeasure = 1.0 - m_windowEval.errorRate();
                } else {
                  primaryMeasure = 1.0 - m_eval.errorRate();
                }
              } else {
                // record confidence as the primary measure
                // (another possibility would be entropy of
                // the distribution, or perhaps average
                // confidence)
                primaryMeasure = dist[Utils.maxIndex(dist)];
              }
              // double [] dataPoint = new double[1];
              m_dataPoint[0] = primaryMeasure;
              // double min = 0; double max = 100;
              /*
               * ChartEvent e = new
               * ChartEvent(IncrementalClassifierEvaluator.this, m_dataLegend,
               * min, max, dataPoint);
               */

              m_ce.setLegendText(m_dataLegend);
              m_ce.setMin(0);
              m_ce.setMax(1);
              m_ce.setDataPoint(m_dataPoint);
              m_ce.setReset(m_reset);
              m_reset = false;
            } else {
              // numeric class
              if (m_dataPoint.length < 1) {
                m_dataPoint = new double[1];
                if (inst.isMissing(inst.classIndex())) {
                  m_dataLegend.addElement("Prediction");
                } else {
                  m_dataLegend.addElement("RMSE");
                }
              }
              if (!inst.isMissing(inst.classIndex())) {
                double update;
                if (!inst.isMissing(inst.classIndex())) {
                  if (m_windowSize > 0) {
                    update = m_windowEval.rootMeanSquaredError();
                  } else {
                    update = m_eval.rootMeanSquaredError();
                  }
                } else {
                  update = pred;
                }
                m_dataPoint[0] = update;
                if (update > m_max) {
                  m_max = update;
                }
                if (update < m_min) {
                  m_min = update;
                }
              }

              m_ce.setLegendText(m_dataLegend);
              m_ce.setMin((inst.isMissing(inst.classIndex()) ? m_min : 0));
              m_ce.setMax(m_max);
              m_ce.setDataPoint(m_dataPoint);
              m_ce.setReset(m_reset);
              m_reset = false;
            }
            notifyChartListeners(m_ce);
          }
          m_throughput.updateEnd(m_logger);
        }

        if (ce.getStatus() == IncrementalClassifierEvent.BATCH_FINISHED || inst == null) {
          if (m_logger != null) {
            m_logger.logMessage(
                "[IncrementalClassifierEvaluator]"
                    + statusMessagePrefix()
                    + " Finished processing.");
          }
          m_throughput.finished(m_logger);

          // save memory if using windowed evaluation for charting
          m_windowEval = null;
          m_window = null;
          m_windowedPreds = null;

          if (m_textListeners.size() > 0) {
            String textTitle = ce.getClassifier().getClass().getName();
            textTitle = textTitle.substring(textTitle.lastIndexOf('.') + 1, textTitle.length());
            String results =
                "=== Performance information ===\n\n"
                    + "Scheme:   "
                    + textTitle
                    + "\n"
                    + "Relation: "
                    + m_eval.getHeader().relationName()
                    + "\n\n"
                    + m_eval.toSummaryString();
            if (m_eval.getHeader().classIndex() >= 0
                && m_eval.getHeader().classAttribute().isNominal()
                && (m_outputInfoRetrievalStats)) {
              results += "\n" + m_eval.toClassDetailsString();
            }

            if (m_eval.getHeader().classIndex() >= 0
                && m_eval.getHeader().classAttribute().isNominal()) {
              results += "\n" + m_eval.toMatrixString();
            }
            textTitle = "Results: " + textTitle;
            TextEvent te = new TextEvent(this, results, textTitle);
            notifyTextListeners(te);
          }
        }
      }
    } catch (Exception ex) {
      if (m_logger != null) {
        m_logger.logMessage(
            "[IncrementalClassifierEvaluator]"
                + statusMessagePrefix()
                + " Error processing prediction "
                + ex.getMessage());
        m_logger.statusMessage(
            statusMessagePrefix() + "ERROR: problem processing prediction (see log for details)");
      }
      ex.printStackTrace();
      stop();
    }
  }
Ejemplo n.º 3
0
  /**
   * Calculates the accuracy on a test fold for internal cross validation of feature sets
   *
   * @param fold set of instances to be "left out" and classified
   * @param fs currently selected feature set
   * @return the accuracy for the fold
   * @throws Exception if something goes wrong
   */
  double evaluateFoldCV(Instances fold, int[] fs) throws Exception {

    int i;
    int ruleCount = 0;
    int numFold = fold.numInstances();
    int numCl = m_theInstances.classAttribute().numValues();
    double[][] class_distribs = new double[numFold][numCl];
    double[] instA = new double[fs.length];
    double[] normDist;
    DecisionTableHashKey thekey;
    double acc = 0.0;
    int classI = m_theInstances.classIndex();
    Instance inst;

    if (m_classIsNominal) {
      normDist = new double[numCl];
    } else {
      normDist = new double[2];
    }

    // first *remove* instances
    for (i = 0; i < numFold; i++) {
      inst = fold.instance(i);
      for (int j = 0; j < fs.length; j++) {
        if (fs[j] == classI) {
          instA[j] = Double.MAX_VALUE; // missing for the class
        } else if (inst.isMissing(fs[j])) {
          instA[j] = Double.MAX_VALUE;
        } else {
          instA[j] = inst.value(fs[j]);
        }
      }
      thekey = new DecisionTableHashKey(instA);
      if ((class_distribs[i] = (double[]) m_entries.get(thekey)) == null) {
        throw new Error("This should never happen!");
      } else {
        if (m_classIsNominal) {
          class_distribs[i][(int) inst.classValue()] -= inst.weight();
        } else {
          class_distribs[i][0] -= (inst.classValue() * inst.weight());
          class_distribs[i][1] -= inst.weight();
        }
        ruleCount++;
      }
      m_classPriorCounts[(int) inst.classValue()] -= inst.weight();
    }
    double[] classPriors = m_classPriorCounts.clone();
    Utils.normalize(classPriors);

    // now classify instances
    for (i = 0; i < numFold; i++) {
      inst = fold.instance(i);
      System.arraycopy(class_distribs[i], 0, normDist, 0, normDist.length);
      if (m_classIsNominal) {
        boolean ok = false;
        for (int j = 0; j < normDist.length; j++) {
          if (Utils.gr(normDist[j], 1.0)) {
            ok = true;
            break;
          }
        }

        if (!ok) { // majority class
          normDist = classPriors.clone();
        }

        //	if (ok) {
        Utils.normalize(normDist);
        if (m_evaluationMeasure == EVAL_AUC) {
          m_evaluation.evaluateModelOnceAndRecordPrediction(normDist, inst);
        } else {
          m_evaluation.evaluateModelOnce(normDist, inst);
        }
        /*	} else {
          normDist[(int)m_majority] = 1.0;
          if (m_evaluationMeasure == EVAL_AUC) {
            m_evaluation.evaluateModelOnceAndRecordPrediction(normDist, inst);
          } else {
            m_evaluation.evaluateModelOnce(normDist, inst);
          }
        } */
      } else {
        if (Utils.eq(normDist[1], 0.0)) {
          double[] temp = new double[1];
          temp[0] = m_majority;
          m_evaluation.evaluateModelOnce(temp, inst);
        } else {
          double[] temp = new double[1];
          temp[0] = normDist[0] / normDist[1];
          m_evaluation.evaluateModelOnce(temp, inst);
        }
      }
    }

    // now re-insert instances
    for (i = 0; i < numFold; i++) {
      inst = fold.instance(i);

      m_classPriorCounts[(int) inst.classValue()] += inst.weight();

      if (m_classIsNominal) {
        class_distribs[i][(int) inst.classValue()] += inst.weight();
      } else {
        class_distribs[i][0] += (inst.classValue() * inst.weight());
        class_distribs[i][1] += inst.weight();
      }
    }
    return acc;
  }
Ejemplo n.º 4
0
  /**
   * Classifies an instance for internal leave one out cross validation of feature sets
   *
   * @param instance instance to be "left out" and classified
   * @param instA feature values of the selected features for the instance
   * @return the classification of the instance
   * @throws Exception if something goes wrong
   */
  double evaluateInstanceLeaveOneOut(Instance instance, double[] instA) throws Exception {

    DecisionTableHashKey thekey;
    double[] tempDist;
    double[] normDist;

    thekey = new DecisionTableHashKey(instA);
    if (m_classIsNominal) {

      // if this one is not in the table
      if ((tempDist = (double[]) m_entries.get(thekey)) == null) {
        throw new Error("This should never happen!");
      } else {
        normDist = new double[tempDist.length];
        System.arraycopy(tempDist, 0, normDist, 0, tempDist.length);
        normDist[(int) instance.classValue()] -= instance.weight();

        // update the table
        // first check to see if the class counts are all zero now
        boolean ok = false;
        for (int i = 0; i < normDist.length; i++) {
          if (Utils.gr(normDist[i], 1.0)) {
            ok = true;
            break;
          }
        }

        //	downdate the class prior counts
        m_classPriorCounts[(int) instance.classValue()] -= instance.weight();
        double[] classPriors = m_classPriorCounts.clone();
        Utils.normalize(classPriors);
        if (!ok) { // majority class
          normDist = classPriors;
        }

        m_classPriorCounts[(int) instance.classValue()] += instance.weight();

        // if (ok) {
        Utils.normalize(normDist);
        if (m_evaluationMeasure == EVAL_AUC) {
          m_evaluation.evaluateModelOnceAndRecordPrediction(normDist, instance);
        } else {
          m_evaluation.evaluateModelOnce(normDist, instance);
        }
        return Utils.maxIndex(normDist);
        /*} else {
          normDist = new double [normDist.length];
          normDist[(int)m_majority] = 1.0;
          if (m_evaluationMeasure == EVAL_AUC) {
            m_evaluation.evaluateModelOnceAndRecordPrediction(normDist, instance);
          } else {
            m_evaluation.evaluateModelOnce(normDist, instance);
          }
          return m_majority;
        } */
      }
      //      return Utils.maxIndex(tempDist);
    } else {

      // see if this one is already in the table
      if ((tempDist = (double[]) m_entries.get(thekey)) != null) {
        normDist = new double[tempDist.length];
        System.arraycopy(tempDist, 0, normDist, 0, tempDist.length);
        normDist[0] -= (instance.classValue() * instance.weight());
        normDist[1] -= instance.weight();
        if (Utils.eq(normDist[1], 0.0)) {
          double[] temp = new double[1];
          temp[0] = m_majority;
          m_evaluation.evaluateModelOnce(temp, instance);
          return m_majority;
        } else {
          double[] temp = new double[1];
          temp[0] = normDist[0] / normDist[1];
          m_evaluation.evaluateModelOnce(temp, instance);
          return temp[0];
        }
      } else {
        throw new Error("This should never happen!");
      }
    }

    // shouldn't get here
    // return 0.0;
  }