Changeset 129 for trunk/CrossPare/src/de/ugoe/cs/cpdp/dataprocessing

Timestamp:

06/22/16 11:25:46 (8 years ago)

Author:

sherbold

Message:

• added the same workaround for the problem with Discretize to the TopMetricFilter?. We slightly refactored the implementation within the AbstractCODEP by putting the rescaling of sets to the WekaUtils? to facilitate better re-use.

File:

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

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

@@ -21 +21 @@
 import java.util.TreeSet;
 import java.util.logging.Level;
+import java.util.regex.Matcher;
+import java.util.regex.Pattern;
 import java.util.stream.IntStream;
 
@@ -29 +31 @@
 
 import de.ugoe.cs.cpdp.util.SortUtils;
+import de.ugoe.cs.cpdp.util.WekaUtils;
 import de.ugoe.cs.util.console.Console;
 import weka.attributeSelection.AttributeSelection;
@@ -96 +99 @@
         List<Set<Integer>> cfsSets = new LinkedList<>();
         for( Instances traindata : traindataSet ) {
-            AttributeSelection attsel = new AttributeSelection();
-            CfsSubsetEval eval = new CfsSubsetEval();
-            GreedyStepwise search = new GreedyStepwise();
-            search.setSearchBackwards(true);
-            attsel.setEvaluator(eval);
-            attsel.setSearch(search);
-            attsel.SelectAttributes(traindata);
-            Set<Integer> cfsSet = new HashSet<>();
-            for( int attr : attsel.selectedAttributes() ) {
-                cfsSet.add(attr);
-            }
-            cfsSets.add(cfsSet);
+            boolean selectionSuccessful = false;
+            boolean secondAttempt = false;
+            Instances traindataCopy = null;
+            do {
+                try {
+                    if (secondAttempt) {
+                        AttributeSelection attsel = new AttributeSelection();
+                        CfsSubsetEval eval = new CfsSubsetEval();
+                        GreedyStepwise search = new GreedyStepwise();
+                        search.setSearchBackwards(true);
+                        attsel.setEvaluator(eval);
+                        attsel.setSearch(search);
+                        attsel.SelectAttributes(traindataCopy);
+                        Set<Integer> cfsSet = new HashSet<>();
+                        for( int attr : attsel.selectedAttributes() ) {
+                            cfsSet.add(attr);
+                        }
+                        cfsSets.add(cfsSet);
+                        selectionSuccessful = true;
+                    }
+                    else {
+                        AttributeSelection attsel = new AttributeSelection();
+                        CfsSubsetEval eval = new CfsSubsetEval();
+                        GreedyStepwise search = new GreedyStepwise();
+                        search.setSearchBackwards(true);
+                        attsel.setEvaluator(eval);
+                        attsel.setSearch(search);
+                        attsel.SelectAttributes(traindata);
+                        Set<Integer> cfsSet = new HashSet<>();
+                        for( int attr : attsel.selectedAttributes() ) {
+                            cfsSet.add(attr);
+                        }
+                        cfsSets.add(cfsSet);
+                        selectionSuccessful = true;
+                    }
+                }
+                catch (IllegalArgumentException e) {
+                    String regex = "A nominal attribute \\((.*)\\) cannot have duplicate labels.*";
+                    Pattern p = Pattern.compile(regex);
+                    Matcher m = p.matcher(e.getMessage());
+                    if (!m.find()) {
+                        // cannot treat problem, rethrow exception
+                        throw e;
+                    }
+                    String attributeName = m.group(1);
+                    int attrIndex = traindata.attribute(attributeName).index();
+                    if (secondAttempt) {
+                        traindataCopy = WekaUtils.upscaleAttribute(traindataCopy, attrIndex);
+                    }
+                    else {
+                        traindataCopy = WekaUtils.upscaleAttribute(traindata, attrIndex);
+                    }
+                    Console
+                        .traceln(Level.FINE,
+                                 "upscaled attribute " + attributeName + "; restarting training");
+                    secondAttempt = true;
+                    continue;
+                }
+            }
+            while (!selectionSuccessful); // dummy loop for internal continue
         }
         
@@ -143 +194 @@
         }
         Set<Integer> topkSetIndexSet = new TreeSet<>();
-        for( int j=0; j<bestCoverageIndex; j++ ) {
+        // j<30 ensures that the computational time does not explode since the powerset is 2^n in complexity
+        for( int j=0; j<bestCoverageIndex && j<30 ; j++ ) {
             topkSetIndexSet.add(j);
         }
@@ -157 +209 @@
                 }
                 for( Set<Integer> cfsSet : cfsSets ) {
-                    currentCoverage += (coverage(combination, cfsSet)/traindataSet.size());
+                    currentCoverage += (coverage(topkCombination, cfsSet)/traindataSet.size());
                 }
                 if( currentCoverage > bestOptCoverage ) {