Changeset 135 for trunk/CrossPare/src/de/ugoe/cs/cpdp/dataselection/CLIFF.java

Timestamp:

07/18/16 12:26:03 (8 years ago)

Author:

sherbold

Message:

• code documentation and formatting

File:

• trunk/CrossPare/src/de/ugoe/cs/cpdp/dataselection/CLIFF.java (modified) (5 diffs)

trunk/CrossPare/src/de/ugoe/cs/cpdp/dataselection/CLIFF.java

@@ -28 +28 @@
 public class CLIFF implements IPointWiseDataselectionStrategy, ISetWiseDataselectionStrategy {
 
+    /**
+     * percentage of data selected
+     */
     private double percentage = 0.10;
-    
+
+    /**
+     * number of ranges considered
+     */
     private final int numRanges = 10;
 
@@ -40 +46 @@
     @Override
     public void setParameter(String parameters) {
-        if( parameters!=null ) {
+        if (parameters != null) {
             percentage = Double.parseDouble(parameters);
         }
     }
-    
-    /**
+
+    /*
      * @see de.ugoe.cs.cpdp.dataselection.SetWiseDataselectionStrategy#apply(weka.core.Instances,
-     *      org.apache.commons.collections4.list.SetUniqueList)
+     * org.apache.commons.collections4.list.SetUniqueList)
      */
     @Override
     public void apply(Instances testdata, SetUniqueList<Instances> traindataSet) {
-        for( Instances traindata : traindataSet ) {
+        for (Instances traindata : traindataSet) {
             applyCLIFF(traindata);
         }
     }
 
-    /**
+    /*
      * @see de.ugoe.cs.cpdp.dataselection.PointWiseDataselectionStrategy#apply(weka.core.Instances,
-     *      weka.core.Instances)
+     * weka.core.Instances)
      */
     @Override
@@ -65 +71 @@
     }
 
+    /**
+     * <p>
+     * Applies the CLIFF relevancy filter to the data.
+     * </p>
+     *
+     * @param data
+     *            the data
+     * @return CLIFF-filtered data
+     */
     protected Instances applyCLIFF(Instances data) {
         final double[][] powerAttributes = new double[data.size()][data.numAttributes()];
         final double[] powerEntity = new double[data.size()];
-        
+
         final int[] counts = data.attributeStats(data.classIndex()).nominalCounts;
         final double probDefect = data.numInstances() / (double) counts[1];
-        
-        for( int j=0; j<data.numAttributes(); j++ ) {
-            if( data.attribute(j)!=data.classAttribute()) {
+
+        for (int j = 0; j < data.numAttributes(); j++) {
+            if (data.attribute(j) != data.classAttribute()) {
                 final double[] ranges = getRanges(data, j);
                 final double[] probDefectRange = getRangeProbabilities(data, j, ranges);
-                
-                for( int i=0 ; i<data.numInstances() ; i++ ) {
+
+                for (int i = 0; i < data.numInstances(); i++) {
                     final double value = data.instance(i).value(j);
                     final int range = determineRange(ranges, value);
                     double probClass, probNotClass, probRangeClass, probRangeNotClass;
-                    if( data.instance(i).classValue()==1 ) {
+                    if (data.instance(i).classValue() == 1) {
                         probClass = probDefect;
-                        probNotClass = 1.0-probDefect;
+                        probNotClass = 1.0 - probDefect;
                         probRangeClass = probDefectRange[range];
-                        probRangeNotClass = 1.0-probDefectRange[range];
-                    } else {
-                        probClass = 1.0-probDefect;
+                        probRangeNotClass = 1.0 - probDefectRange[range];
+                    }
+                    else {
+                        probClass = 1.0 - probDefect;
                         probNotClass = probDefect;
-                        probRangeClass = 1.0-probDefectRange[range];
+                        probRangeClass = 1.0 - probDefectRange[range];
                         probRangeNotClass = probDefectRange[range];
                     }
-                    powerAttributes[i][j] = Math.pow(probRangeClass, 2.0)/(probRangeClass*probClass+probRangeNotClass*probNotClass);
+                    powerAttributes[i][j] = Math.pow(probRangeClass, 2.0) /
+                        (probRangeClass * probClass + probRangeNotClass * probNotClass);
                 }
             }
         }
-        
-        for( int i=0; i<data.numInstances(); i++ ) {
+
+        for (int i = 0; i < data.numInstances(); i++) {
             powerEntity[i] = 1.0;
-            for (int j=0; j<data.numAttributes() ; j++ ) {
+            for (int j = 0; j < data.numAttributes(); j++) {
                 powerEntity[i] *= powerAttributes[i][j];
             }
@@ -105 +122 @@
         double[] sortedPower = powerEntity.clone();
         Arrays.sort(sortedPower);
-        double cutOff = sortedPower[(int) (data.numInstances()*(1-percentage))];
+        double cutOff = sortedPower[(int) (data.numInstances() * (1 - percentage))];
 
         final Instances selected = new Instances(data);
         selected.delete();
-        for (int i=0; i<data.numInstances(); i++) {
-            if( powerEntity[i]>=cutOff ) {
+        for (int i = 0; i < data.numInstances(); i++) {
+            if (powerEntity[i] >= cutOff) {
                 selected.add(data.instance(i));
             }
@@ -116 +133 @@
         return selected;
     }
-    
+
+    /**
+     * <p>
+     * Gets an array with the ranges from the data for a given attribute
+     * </p>
+     *
+     * @param data
+     *            the data
+     * @param j
+     *            index of the attribute
+     * @return the ranges for the attribute
+     */
     private double[] getRanges(Instances data, int j) {
-        double[] values = new double[numRanges+1];
-        for( int k=0; k<numRanges; k++ ) {
-            values[k] = data.kthSmallestValue(j, (int) (data.size()*(k+1.0)/numRanges));
+        double[] values = new double[numRanges + 1];
+        for (int k = 0; k < numRanges; k++) {
+            values[k] = data.kthSmallestValue(j, (int) (data.size() * (k + 1.0) / numRanges));
         }
         values[numRanges] = data.attributeStats(j).numericStats.max;
         return values;
     }
-    
+
+    /**
+     * <p>
+     * Gets the probabilities of a positive prediction for each range for a given attribute
+     * </p>
+     *
+     * @param data
+     *            the data
+     * @param j
+     *            index of the attribute
+     * @param ranges
+     *            the ranges
+     * @return probabilities for each range
+     */
     private double[] getRangeProbabilities(Instances data, int j, double[] ranges) {
         double[] probDefectRange = new double[numRanges];
         int[] countRange = new int[numRanges];
         int[] countDefect = new int[numRanges];
-        for( int i=0; i<data.numInstances() ; i++ ) {
-            int range = determineRange(ranges, data.instance(i).value(j)); 
+        for (int i = 0; i < data.numInstances(); i++) {
+            int range = determineRange(ranges, data.instance(i).value(j));
             countRange[range]++;
-            if( data.instance(i).classValue()== 1 ) {
+            if (data.instance(i).classValue() == 1) {
                 countDefect[range]++;
             }
 
         }
-        for( int k=0; k<numRanges; k++ ) {
+        for (int k = 0; k < numRanges; k++) {
             probDefectRange[k] = ((double) countDefect[k]) / countRange[k];
         }
         return probDefectRange;
     }
-    
+
+    /**
+     * <p>
+     * Determines the range of a give value
+     * </p>
+     *
+     * @param ranges
+     *            the possible ranges
+     * @param value
+     *            the value
+     * @return index of the range
+     */
     private int determineRange(double[] ranges, double value) {
-        for( int k=0; k<numRanges; k++ ) {
-            if( value<=ranges[k+1] ) {
+        for (int k = 0; k < numRanges; k++) {
+            if (value <= ranges[k + 1]) {
                 return k;
             }