private double calcSTDev(
     HashMap<Integer, String> singleGeneCaseValueMap, String groupType, String profileStableId) {
   switch (groupType) {
     case "altered":
       DescriptiveStatistics stats_altered = new DescriptiveStatistics();
       for (Integer alteredSampleId : alteredSampleIds) {
         if (singleGeneCaseValueMap.containsKey(alteredSampleId)) {
           if (profileStableId.indexOf("rna_seq") != -1) {
             try {
               stats_altered.addValue(
                   Math.log(Double.parseDouble(singleGeneCaseValueMap.get(alteredSampleId)))
                       / Math.log(2));
             } catch (NumberFormatException e) {
               e.getStackTrace();
             }
           } else {
             try {
               stats_altered.addValue(
                   Double.parseDouble(singleGeneCaseValueMap.get(alteredSampleId)));
             } catch (NumberFormatException e) {
               e.getStackTrace();
             }
           }
         }
       }
       return stats_altered.getStandardDeviation();
     case "unaltered":
       DescriptiveStatistics stats_unaltered = new DescriptiveStatistics();
       for (Integer unalteredSampleId : unalteredSampleIds) {
         if (singleGeneCaseValueMap.containsKey(unalteredSampleId)) {
           if (profileStableId.indexOf("rna_seq") != -1) {
             try {
               stats_unaltered.addValue(
                   Math.log(Double.parseDouble(singleGeneCaseValueMap.get(unalteredSampleId)))
                       / Math.log(2));
             } catch (NumberFormatException e) {
               e.getStackTrace();
             }
           } else {
             try {
               stats_unaltered.addValue(
                   Double.parseDouble(singleGeneCaseValueMap.get(unalteredSampleId)));
             } catch (NumberFormatException e) {
               e.getStackTrace();
             }
           }
         }
       }
       return stats_unaltered.getStandardDeviation();
     default:
       return Double.NaN; // error
   }
 }
Esempio n. 2
0
  /**
   * Normalize (standardize) the sample, so it is has a mean of 0 and a standard deviation of 1.
   *
   * @param sample Sample to normalize.
   * @return normalized (standardized) sample.
   * @since 2.2
   */
  public static double[] normalize(final double[] sample) {
    DescriptiveStatistics stats = new DescriptiveStatistics();

    // Add the data from the series to stats
    for (int i = 0; i < sample.length; i++) {
      stats.addValue(sample[i]);
    }

    // Compute mean and standard deviation
    double mean = stats.getMean();
    double standardDeviation = stats.getStandardDeviation();

    // initialize the standardizedSample, which has the same length as the sample
    double[] standardizedSample = new double[sample.length];

    for (int i = 0; i < sample.length; i++) {
      // z = (x- mean)/standardDeviation
      standardizedSample[i] = (sample[i] - mean) / standardDeviation;
    }
    return standardizedSample;
  }
  public Vector<double[]> getMeanSd(svm_node[][] node) {
    // TODO Auto-generated method stub
    DescriptiveStatistics statistics = new DescriptiveStatistics();
    int nAttr = node[0].length;
    int nSample = node.length;
    double[] meanValues = new double[nAttr];
    double[] sdValues = new double[nAttr];

    for (int i = 0; i < nAttr; i++) {
      statistics.clear();
      for (int j = 0; j < nSample; j++) {
        statistics.addValue(node[j][i].value);
      }
      // 获取中值及标准差
      meanValues[i] = statistics.getMean();
      sdValues[i] = statistics.getStandardDeviation();
    }

    Vector<double[]> meanSd = new Vector<double[]>();
    meanSd.add(meanValues);
    meanSd.add(sdValues);
    return meanSd;
  }
Esempio n. 4
0
  public static void main(String[] args) {

    // TEST MEASURE
    //        Point p1 = new Point(-1d, -1d);
    //        Point p2 = new Point(2d, 3d);
    //        System.out.println(measure.d(p1, p2));
    //        System.out.println(measure.s(p1, p2));
    //        return;

    Double[][] data = FileHandler.readFile(fileName);

    // cannot display points if dimension is > 2
    if (data[0].length != 2) canDisplay = false;

    // build graphic points from coords' array
    buildPointsFromData(data);
    Config.computeBoundingRect(points);

    // init display
    if (canDisplay) {
      disp = new Display();
      disp.setVisible(true);
      for (Point p : points) {
        disp.addObject(p);
      }
    }

    testResults = new double[nbTests];

    for (int t = 0; t < nbTests; ++t) {

      // define K clusters and K temporary centres
      clusters = new ArrayList<Cluster>();
      for (int i = 0; i < K; ++i) {
        clusters.add(new Cluster());
      }
      setRandomCenters();
      for (Cluster c : clusters) {
        System.out.println("center for cluster " + c + ": " + c.getCenter());
      }

      if (canDisplay) pause(1000);

      // variables used in for loops
      double minDist, currDist, diff;
      Double[] prevCoords, newCoords;
      Cluster alloc;
      Point newCenter;

      for (int i = 0; i < maxIter; ++i) {

        if (canDisplay) {
          disp.setLabel("[ iteration #" + (i + 1) + " ]");
        } else {
          System.out.println("------> iteration #" + (i + 1));
        }

        // allocate points to group which center is closest
        for (Point p : points) {

          minDist = Config.MAX;
          alloc = clusters.get(0); // default initialization

          for (Cluster c : clusters) {
            currDist = measure.d(p, c.getCenter());
            if (currDist < minDist) {
              minDist = currDist;
              alloc = c;
            }
          }

          alloc.addPoint(p);
        }

        // recenter: calculate gravity centers for formed groups
        diff = 0;
        prevCoords = null;
        for (Cluster c : clusters) {

          // delete previous center if it not a Point of the Cluster
          if (canDisplay && !c.getPoints().contains(c.getCenter())) {
            disp.removeObject(c.getCenter());
          }

          if (stopOnConverge) {
            prevCoords = c.getCenter().getCoords();
          }

          newCenter = c.makeGravityCenter();

          if (stopOnConverge) {
            newCoords = c.getCenter().getCoords();
            for (int k = 0; k < prevCoords.length; ++k) {
              diff += Math.abs(prevCoords[k] - newCoords[k]);
            }
          }

          if (canDisplay) {
            disp.addObject(newCenter);
          } else {
            // System.out.println("\tcenter for " + c + ": " + c.getCenter());
            System.out.println(c.getCenter());
          }
        } // loop over clusters

        if (canDisplay) {
          disp.repaint();
        }

        // if Clusters' centers don't change anymore, then stop (algorithm converged)
        if (diff == 0 && stopOnConverge) {
          testResults[t] = (double) i;
          if (canDisplay) {
            disp.setLabel("[ Converged at iteration #" + (i) + " ]");
            disp.repaint();
          } else {
            System.out.println("[ Converged at iteration #" + (i) + " ]");
          }
          break;
        }

        pause(100);
      } // loop over iterations

      if (testResults[t] == 0) {
        System.out.println("!!!!!!!!!! Test #" + t + " did not converge.");
        if (stopOnConverge) return;
      }

      // reset display
      if (canDisplay && t + 1 < nbTests) {
        for (Point p : points) p.setCluster(null);
        for (Cluster c : clusters) disp.removeObject(c.getCenter());
      }
    } // loop over tests

    // display test results and compute means
    DescriptiveStatistics stats = new DescriptiveStatistics(testResults);
    System.out.println("=========> Results:");
    for (int t = 0; t < nbTests; ++t) {
      System.out.println("--> [ " + testResults[t] + " ]");
    }
    System.out.println("=========> Means: " + stats.getMean());
    System.out.println("=========> Std dev: " + stats.getStandardDeviation());
  }