Changeset 139 for trunk/CrossPare

Timestamp:

08/18/16 16:56:35 (8 years ago)

Author:

atrautsch

Message:

Code Cleanup

File:

• trunk/CrossPare/src/de/ugoe/cs/cpdp/training/MetricMatchingTraining.java (modified) (14 diffs)

trunk/CrossPare/src/de/ugoe/cs/cpdp/training/MetricMatchingTraining.java

@@ -25 +25 @@
 import java.util.List;
 import java.util.Map;
+import java.util.Map.Entry;
 import java.util.logging.Level;
 
@@ -30 +31 @@
 
 import org.apache.commons.collections4.list.SetUniqueList;
-import org.apache.commons.math3.stat.inference.ChiSquareTest;
 import org.apache.commons.math3.stat.correlation.SpearmansCorrelation;
 import org.apache.commons.math3.stat.inference.KolmogorovSmirnovTest;
@@ -44 +44 @@
 
 /**
- * Implements Heterogenous Defect Prediction after Nam et al.  2015.
+ * Implements Heterogenous Defect Prediction after Nam et al. 2015.
  * 
  * We extend WekaBaseTraining because we have to Wrap the Classifier to use MetricMatching.
  * This also means we can use any Weka Classifier not just LogisticRegression.
  * 
- * TODO:
- * - spacing, coding conventions
- * - clean up attribute selection on train data
- * - percentile test run
  */
 public class MetricMatchingTraining extends WekaBaseTraining implements ISetWiseTestdataAwareTrainingStrategy {
 
-    private SetUniqueList<Instances> traindataSet;
     private MetricMatch mm = null;
     private Classifier classifier = new MetricMatchingClassifier();
@@ -64 +59 @@
     
     /**
-     * We wrap the classifier here because of classifyInstance
+     * We wrap the classifier here because of classifyInstance with our MetricMatchingClassfier
      * @return
      */
@@ -129 +124 @@
                     Console.traceln(Level.INFO, "[MATCHED ATTRIBUTE] source attribute: [" + this.mm.train.attribute(attmatch.getKey()).name() + "], target attribute: [" + this.mm.test.attribute(attmatch.getValue()).name() + "]");
                 }
-                
-                // replace traindataSet
-                //traindataSet.clear();
-                //traindataSet.add(ilist);
+            }else {
+                Console.traceln(Level.INFO, "[NO MATCH FOUND]");
             }
                 
-                // if we have a match we build the special classifier, if not we fall back to FixClass
+                // if we have a match we build the MetricMatchingClassifier, if not we fall back to FixClass Classifier
                 try {
                         if(this.mm != null) {
@@ -163 +156 @@
                 @Override
                 public void buildClassifier(Instances traindata) throws Exception {
-                        this.classifier = setupClassifier();  // parent method from WekaBase
+                        this.classifier = setupClassifier();
                         this.classifier.buildClassifier(traindata);
                 }
@@ -213 +206 @@
                 protected ArrayList<double[]> test_values;
 
-                 
+                
                 public MetricMatch(Instances train, Instances test) {
-                        this.train = train;
-                        this.test = test;
+                        // this is expensive but we need to keep the original data intact
+                    this.train = this.deepCopy(train);
+                        this.test = test; // we do not need a copy here because we do not drop attributes before the matching and after the matching we create a new Instances with only the matched attributes
                         
                         // convert metrics of testdata and traindata to later use in similarity tests
@@ -330 +324 @@
                 }
 
-                
+        /**
+         * Deep Copy (well, reasonably deep, not sure about header information of attributes) Weka Instances.
+         * 
+         * @param data Instances
+         * @return copy of Instances passed
+         */
+                private Instances deepCopy(Instances data) {
+                    Instances newInst = new Instances(data);
+                    
+                    newInst.clear();
+                    
+            for (int i=0; i < data.size(); i++) {
+                Instance ni = new DenseInstance(data.numAttributes());
+                for(int j = 0; j < data.numAttributes(); j++) {
+                    ni.setValue(newInst.attribute(j), data.instance(i).value(data.attribute(j)));
+                }
+                newInst.add(ni);
+            }
+            
+            return newInst;
+                }
+
         /**
          * Returns a deep copy of passed Instances data for Train or Test data.
@@ -392 +407 @@
                  */
                 public void attributeSelection() throws Exception {
-                        //Console.traceln(Level.INFO, "Attribute Selection on Training Attributes ("+this.train.numAttributes()+")");
-                        this.attributeSelection(this.train);
-                        //Console.traceln(Level.INFO, "-----");
-                        //Console.traceln(Level.INFO, "Attribute Selection on Test Attributes ("+this.test.numAttributes()+")");
-                        //this.attributeSelection(this.test);
-                        //Console.traceln(Level.INFO, "-----");
-                }
-                
-                
-                private void attributeSelection(Instances which) throws Exception {
-                        // 1. step we have to categorize the attributes
-                        //http://weka.sourceforge.net/doc.packages/probabilisticSignificanceAE/weka/attributeSelection/SignificanceAttributeEval.html
-                        
+                    
+                    // it is a wrapper, we may decide to implement ChiSquare or other means of selecting attributes
+                        this.attributeSelectionBySignificance(this.train);
+                }
+                
+                private void attributeSelectionBySignificance(Instances which) throws Exception {
+                        // Uses: http://weka.sourceforge.net/doc.packages/probabilisticSignificanceAE/weka/attributeSelection/SignificanceAttributeEval.html
                         SignificanceAttributeEval et = new SignificanceAttributeEval();
                         et.buildEvaluator(which);
-                        //double tmp[] = new double[this.train.numAttributes()];
+                        
+                        // evaluate all training attributes
                         HashMap<String,Double> saeval = new HashMap<String,Double>();
-                        // evaluate all training attributes
-                        // select top 15% of metrics
                         for(int i=0; i < which.numAttributes(); i++) { 
                                 if(which.classIndex() != i) {
                                         saeval.put(which.attribute(i).name(), et.evaluateAttribute(i));
                                 }
-                                //Console.traceln(Level.SEVERE, "Significance Attribute Eval: " + tmp);
                         }
                         
-                        HashMap<String, Double> sorted = sortByValues(saeval);
+                        // sort by significance
+                        HashMap<String, Double> sorted = (HashMap<String, Double>) sortByValues(saeval);
                         
-                        // die besten 15% wollen wir haben
+                        // Keep the best 15%
                         double last = ((double)saeval.size() / 100.0) * 15.0;
                         int drop_first = saeval.size() - (int)last;
                         
-                        //Console.traceln(Level.INFO, "Dropping "+ drop_first + " of " + sorted.size() + " attributes (we only keep the best 15% "+last+")");
-                        /*
-                        Iterator it = sorted.entrySet().iterator();
-                    while (it.hasNext()) {
-                        Map.Entry pair = (Map.Entry)it.next();
-                        Console.traceln(Level.INFO, "key: "+(int)pair.getKey()+", value: " + (double)pair.getValue() + "");
-                    }*/
-                        
                         // drop attributes above last
-                        Iterator it = sorted.entrySet().iterator();
+                        Iterator<Entry<String, Double>> it = sorted.entrySet().iterator();
                     while (drop_first > 0) {
-                        Map.Entry pair = (Map.Entry)it.next();
+                        Map.Entry<String, Double> pair = (Map.Entry<String, Double>)it.next();
                         if(which.attribute((String)pair.getKey()).index() != which.classIndex()) {
-                                
                                 which.deleteAttributeAt(which.attribute((String)pair.getKey()).index());
-                                //Console.traceln(Level.INFO, "dropping attribute: "+ (String)pair.getKey());
                         }
                         drop_first-=1;
                     }
-                    //Console.traceln(Level.INFO, "Now we have " + which.numAttributes() + " attributes left (incl. class attribute!)");
-                }
-                
-                
-                private HashMap sortByValues(HashMap map) {
-               List list = new LinkedList(map.entrySet());
-
-               Collections.sort(list, new Comparator() {
-                    public int compare(Object o1, Object o2) {
-                       return ((Comparable) ((Map.Entry) (o1)).getValue())
-                          .compareTo(((Map.Entry) (o2)).getValue());
+                }
+                
+                /**
+                 * Helper method to sort a hashmap by its values.
+                 * 
+                 * @param map
+                 * @return sorted map
+                 */
+                private HashMap<String, Double> sortByValues(HashMap<String, Double> map) {
+               List<Map.Entry<String, Double>> list = new LinkedList<Map.Entry<String, Double>>(map.entrySet());
+
+               Collections.sort(list, new Comparator<Map.Entry<String, Double>>() {
+                    public int compare(Map.Entry<String, Double> o1, Map.Entry<String, Double> o2) {
+                       return (o1.getValue()).compareTo( o2.getValue() );
                     }
                });
 
-
-               HashMap sortedHashMap = new LinkedHashMap();
-               for (Iterator it = list.iterator(); it.hasNext();) {
-                      Map.Entry entry = (Map.Entry) it.next();
-                      sortedHashMap.put(entry.getKey(), entry.getValue());
-               } 
+               HashMap<String, Double> sortedHashMap = new LinkedHashMap<String, Double>();
+               for(Map.Entry<String, Double> item : list) {
+                   sortedHashMap.put(item.getKey(), item.getValue());
+               }
                return sortedHashMap;
                 }
-                 
+                
                 
         /**
@@ -553 +552 @@
                  
                 /**
-                 * Calculate Spearmans rank correlation coefficient as matching score
+                 * Calculate Spearmans rank correlation coefficient as matching score.
                  * The number of instances for the source and target needs to be the same so we randomly sample from the bigger one.
                  * 
@@ -573 +572 @@
             // try out possible attribute combinations
             for (int i=0; i < this.train.numAttributes(); i++) {
-
                 for (int j=0; j < this.test.numAttributes(); j++) {
                     // negative infinity counts as not present, we do this so we don't have to map between attribute indexs in weka
@@ -591 +589 @@
                                             this.p_sum += p;
                         mwbm.setWeight(i, j, p);
-                                            //Console.traceln(Level.INFO, "Found match: p-val: " + p);
                                         }
                                 }
                     }
-
-            //Console.traceln(Level.INFO, "Found " + this.attributes.size() + " matching attributes");
-        }
-
-                 
-        public void sample(Instances bigger, Instances smaller, ArrayList<double[]> values) {
+        }
+
+                /**
+                 * Helper method to sample instances for the Spearman rank correlation coefficient method.
+                 * 
+                 * @param bigger
+                 * @param smaller
+                 * @param values
+                 */
+        private void sample(Instances bigger, Instances smaller, ArrayList<double[]> values) {
             // we want to at keep the indices we select the same
             int indices_to_draw = smaller.size();
@@ -646 +647 @@
             
                         KolmogorovSmirnovTest t = new KolmogorovSmirnovTest();
-
-                        //Console.traceln(Level.INFO, "Starting Kolmogorov-Smirnov test for traindata size: " + this.train.size() + " attributes("+this.train.numAttributes()+") and testdata size: " + this.test.size() + " attributes("+this.test.numAttributes()+")");
                         for (int i=0; i < this.train.numAttributes(); i++) {
                                 for ( int j=0; j < this.test.numAttributes(); j++) {
@@ -673 +672 @@
                                 }
                         }
-                        //Console.traceln(Level.INFO, "Found " + this.attributes.size() + " matching attributes");
             }
     }