Changeset 135 for trunk/CrossPare/src/de/ugoe/cs/cpdp/util/WekaUtils.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/util/WekaUtils.java (modified) (11 diffs)

trunk/CrossPare/src/de/ugoe/cs/cpdp/util/WekaUtils.java

@@ -15 +15 @@
 package de.ugoe.cs.cpdp.util;
 
-// TODO comment
 import org.apache.commons.math3.ml.distance.EuclideanDistance;
 
@@ -21 +20 @@
 import weka.core.Instances;
 
+/**
+ * <p>
+ * Collections of helper functions to work with Weka.
+ * </p>
+ * 
+ * @author Steffen Herbold
+ */
 public class WekaUtils {
 
+    /**
+     * <p>
+     * Data class for distance between instances within a data set based on their distributional
+     * characteristics.
+     * </p>
+     * 
+     * @author Steffen Herbold
+     */
     public static class DistChar {
         public final double mean;
@@ -29 +43 @@
         public final double max;
         public final int num;
+
         private DistChar(double mean, double std, double min, double max, int num) {
             this.mean = mean;
@@ -37 +52 @@
         }
     }
-    
+
     /**
      * Scaling value that moves the decimal point by 5 digets.
      */
     public final static double SCALER = 10000.0d;
-    
+
     /**
      * <p>
@@ -66 +81 @@
         return distance;
     }
-    
+
+    /**
+     * <p>
+     * Returns a double array of the values without the classification.
+     * </p>
+     *
+     * @param instance
+     *            the instance
+     * @return double array
+     */
     public static double[] instanceValues(Instance instance) {
-        double[] values = new double[instance.numAttributes()-1];
-        int k=0; 
-        for( int j=0; j<instance.numAttributes() ; j++ ) {
-            if( j!= instance.classIndex() ) {
+        double[] values = new double[instance.numAttributes() - 1];
+        int k = 0;
+        for (int j = 0; j < instance.numAttributes(); j++) {
+            if (j != instance.classIndex()) {
                 values[k] = instance.value(j);
                 k++;
@@ -78 +102 @@
         return values;
     }
-    
+
+    /**
+     * <p>
+     * Calculates the distributional characteristics of the distances the instances within a data
+     * set have to each other.
+     * </p>
+     *
+     * @param data
+     *            data for which the instances are characterized
+     * @return characteristics
+     */
     public static DistChar datasetDistance(Instances data) {
         double distance;
@@ -87 +121 @@
         int numCmp = 0;
         int l = 0;
-        double[] inst1 = new double[data.numAttributes()-1];
-        double[] inst2 = new double[data.numAttributes()-1];
+        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() ) {
+        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++ ) {
-                if( j!=i ) {
-                    l=0;
-                    for( int k=0; k<data.numAttributes(); k++ ) {
-                        if( k!=data.classIndex() ) {
+            for (int j = 0; j < data.numInstances(); j++) {
+                if (j != i) {
+                    l = 0;
+                    for (int k = 0; k < data.numAttributes(); k++) {
+                        if (k != data.classIndex()) {
                             inst2[l] = data.instance(j).value(k);
                         }
@@ -107 +141 @@
                     distance = euclideanDistance.compute(inst1, inst2);
                     sumAll += distance;
-                    sumAllQ += distance*distance;
+                    sumAllQ += distance * distance;
                     numCmp++;
-                    if( distance < min ) {
+                    if (distance < min) {
                         min = distance;
                     }
-                    if( distance > max ) {
+                    if (distance > max) {
                         max = distance;
                     }
@@ -119 +153 @@
         }
         double mean = sumAll / numCmp;
-        double std = Math.sqrt((sumAllQ-(sumAll*sumAll)/numCmp) *
-                                  (1.0d / (numCmp - 1)));
+        double std = Math.sqrt((sumAllQ - (sumAll * sumAll) / numCmp) * (1.0d / (numCmp - 1)));
         return new DistChar(mean, std, min, max, data.numInstances());
     }
-    
-    // like above, but for single attribute
+
+    /**
+     * <p>
+     * Calculates the distributional characteristics of the distances of a single attribute the
+     * instances within a data set have to each other.
+     * </p>
+     *
+     * @param data
+     *            data for which the instances are characterized
+     * @param index
+     *            attribute for which the distances are characterized
+     * @return characteristics
+     */
     public static DistChar attributeDistance(Instances data, int index) {
         double distance;
@@ -133 +177 @@
         int numCmp = 0;
         double value1, value2;
-        for( int i=0; i<data.numInstances(); i++ ) {
+        for (int i = 0; i < data.numInstances(); i++) {
             value1 = data.instance(i).value(index);
-            for( int j=0; j<data.numInstances(); j++ ) {
-                if( j!=i ) {
+            for (int j = 0; j < data.numInstances(); j++) {
+                if (j != i) {
                     value2 = data.instance(j).value(index);
-                    distance = Math.abs(value1-value2);
+                    distance = Math.abs(value1 - value2);
                     sumAll += distance;
-                    sumAllQ += distance*distance;
+                    sumAllQ += distance * distance;
                     numCmp++;
-                    if( distance < min ) {
+                    if (distance < min) {
                         min = distance;
                     }
-                    if( distance > max ) {
+                    if (distance > max) {
                         max = distance;
                     }
@@ -152 +196 @@
         }
         double mean = sumAll / numCmp;
-        double std = Math.sqrt((sumAllQ-(sumAll*sumAll)/numCmp) *
-                                  (1.0d / (numCmp - 1)));
+        double std = Math.sqrt((sumAllQ - (sumAll * sumAll) / numCmp) * (1.0d / (numCmp - 1)));
         return new DistChar(mean, std, min, max, data.numInstances());
     }
-    
+
     /**
      * <p>