Changeset 64

Timestamp:

04/28/16 16:51:59 (9 years ago)

Author:

sherbold

Message:

• added some new approaches

Location:

trunk/CrossPare/src/de/ugoe/cs/cpdp

Files:

• dataprocessing/SynonymAttributePruning.java (added)
• dataprocessing/TCAPlusNormalization.java (modified) (4 diffs)
• dataprocessing/TopMetricFilter.java (added)
• dataprocessing/TransferComponentAnalysis.java (modified) (4 diffs)
• dataselection/DBSCANFilter.java (added)
• dataselection/MahalanobisOutlierRemoval.java (added)
• dataselection/NeighborhoodFilter.java (added)
• dataselection/SynonymOutlierRemoval.java (added)
• training/WekaLASERTraining.java (added)
• wekaclassifier/AbstractCODEP.java (modified) (4 diffs)

trunk/CrossPare/src/de/ugoe/cs/cpdp/dataprocessing/TCAPlusNormalization.java

@@ -15 +15 @@
 package de.ugoe.cs.cpdp.dataprocessing;
 
-import org.apache.commons.math3.ml.distance.EuclideanDistance;
-
+import de.ugoe.cs.cpdp.util.WekaUtils;
+import de.ugoe.cs.cpdp.util.WekaUtils.DistChar;
 import weka.core.Instances;
 
@@ -22 +22 @@
 public class TCAPlusNormalization implements IProcessesingStrategy {
 
-    private class DistChar {
-        private final double mean;
-        private final double std;
-        private final double min;
-        private final double max;
-        private int num;
-        private DistChar(double mean, double std, double min, double max, int num) {
-            this.mean = mean;
-            this.std = std;
-            this.min = min;
-            this.max = max;
-            this.num = num;
-        }
-    }
-    
     /**
      * Does not have parameters. String is ignored.
@@ -55 +40 @@
     
     private void applyTCAPlus(Instances testdata, Instances traindata) {
-        DistChar dcTest = datasetDistance(testdata);
-        DistChar dcTrain = datasetDistance(traindata);
+        DistChar dcTest = WekaUtils.datasetDistance(testdata);
+        DistChar dcTrain = WekaUtils.datasetDistance(traindata);
         
         // RULE 1:
@@ -86 +71 @@
         }
     }
-    
-    private DistChar datasetDistance(Instances data) {
-        double distance;
-        double sumAll = 0.0;
-        double sumAllQ = 0.0;
-        double min = Double.MAX_VALUE;
-        double max = Double.MIN_VALUE;
-        int numCmp = 0;
-        int l = 0;
-        double[] inst1 = new double[data.numAttributes()-1];
-        double[] inst2 = new double[data.numAttributes()-1];
-        EuclideanDistance euclideanDistance = new EuclideanDistance();
-        for( int i=0; i<data.numInstances(); i++ ) {
-            l=0;
-            for( int k=0; k<data.numAttributes(); k++ ) {
-                if( k!=data.classIndex() ) {
-                    inst1[l] = data.instance(i).value(k);
-                }
-            }
-            for( int j=0; j<data.numInstances(); j++ ) {
-                l=0;
-                for( int k=0; k<data.numAttributes(); k++ ) {
-                    if( k!=data.classIndex() ) {
-                        inst2[l] = data.instance(j).value(k);
-                    }
-                }
-                distance = euclideanDistance.compute(inst1, inst2);
-                sumAll += distance;
-                sumAllQ += distance*distance;
-                numCmp++;
-                if( distance < min ) {
-                    min = distance;
-                }
-                if( distance > max ) {
-                    max = distance;
-                }
-            }
-        }
-        double mean = sumAll / numCmp;
-        double std = Math.sqrt((sumAllQ-(sumAll*sumAll)/numCmp) *
-                                  (1.0d / (numCmp - 1)));
-        return new DistChar(mean, std, min, max, data.numInstances());
-    }
-
 }

trunk/CrossPare/src/de/ugoe/cs/cpdp/dataprocessing/TransferComponentAnalysis.java

@@ -25 +25 @@
 import org.ojalgo.array.Array1D;
 
+import de.ugoe.cs.cpdp.util.SortUtils;
 import de.ugoe.cs.util.console.Console;
 import weka.core.Attribute;
@@ -89 +90 @@
         Array1D<ComplexNumber> eigenvaluesArray = eigenvalueDecomposition.getEigenvalues();
         System.out.println(eigenvaluesArray.length);
-        final double[] eigenvalues = new double[(int) eigenvaluesArray.length];
+        final Double[] eigenvalues = new Double[(int) eigenvaluesArray.length];
         final int[] index = new int[(int) eigenvaluesArray.length];
         // create kernel transformation matrix from eigenvectors
@@ -96 +97 @@
             index[i] = i;
         }
-        quicksort(eigenvalues, index);
+        SortUtils.quicksort(eigenvalues, index);
 
         final PrimitiveMatrix transformedKernel = kernelMatrix.multiplyRight(eigenvalueDecomposition
@@ -218 +219 @@
         return muMatrix.build();
     }
-
-    // below is from http://stackoverflow.com/a/1040503
-    private static void quicksort(double[] main, int[] index) {
-        quicksort(main, index, 0, index.length - 1);
-    }
-
-    // quicksort a[left] to a[right]
-    private static void quicksort(double[] a, int[] index, int left, int right) {
-        if (right <= left)
-            return;
-        int i = partition(a, index, left, right);
-        quicksort(a, index, left, i - 1);
-        quicksort(a, index, i + 1, right);
-    }
-
-    // partition a[left] to a[right], assumes left < right
-    private static int partition(double[] a, int[] index, int left, int right) {
-        int i = left - 1;
-        int j = right;
-        while (true) {
-            while (less(a[++i], a[right])) // find item on left to swap
-            ; // a[right] acts as sentinel
-            while (less(a[right], a[--j])) // find item on right to swap
-                if (j == left)
-                    break; // don't go out-of-bounds
-            if (i >= j)
-                break; // check if pointers cross
-            exch(a, index, i, j); // swap two elements into place
-        }
-        exch(a, index, i, right); // swap with partition element
-        return i;
-    }
-
-    // is x < y ?
-    private static boolean less(double x, double y) {
-        return (x < y);
-    }
-
-    // exchange a[i] and a[j]
-    private static void exch(double[] a, int[] index, int i, int j) {
-        double swap = a[i];
-        a[i] = a[j];
-        a[j] = swap;
-        int b = index[i];
-        index[i] = index[j];
-        index[j] = b;
-    }
 }

trunk/CrossPare/src/de/ugoe/cs/cpdp/wekaclassifier/AbstractCODEP.java

@@ -27 +27 @@
 import weka.classifiers.functions.RBFNetwork;
 import weka.classifiers.rules.DecisionTable;
+import weka.classifiers.trees.ADTree;
 import weka.core.Attribute;
 import weka.core.DenseInstance;
@@ -103 +104 @@
     /**
      * <p>
-     * Creates a CODEP instance using the classications of the internal classifiers.
+     * Creates a CODEP instance using the classifications of the internal classifiers.
      * </p>
      *
@@ -110 +111 @@
      * @return CODEP instance
      * @throws Exception
-     *             thrown if an exception occurs during classification with an internal classifer
+     *             thrown if an exception occurs during classification with an internal classifier
      */
     private Instance createInternalInstance(Instance instance) throws Exception {
@@ -147 +148 @@
         // create training data with prediction labels
 
-        // TODO ADTree missing?!
+        internalClassifiers.add(new ADTree());
         internalClassifiers.add(new BayesNet());
         internalClassifiers.add(new DecisionTable());