Changeset 10 for trunk/CrossPare

Timestamp:

08/25/14 12:52:14 (10 years ago)

Author:

sherbold

Message:

• added some source code comments

Location:

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

Files:

• dataprocessing/DataGravitation.java (modified) (1 diff)
• dataprocessing/InformationGainFilter.java (modified) (1 diff)
• dataprocessing/Undersampling.java (modified) (3 diffs)
• training/BaggingTraining.java (modified) (1 diff)
• training/WekaBaggingTraining2.java (modified) (1 diff)

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

@@ -7 +7 @@
 import weka.core.Instances;
 
-// TODO comment
+/**
+ * Implements an approach for data weighting suggested after Y. Ma, G. Luo, X. Zeng, and A. Chen: Transfer learning for
+ * cross-company software defect prediction. The instances are weighted higher, the more attributes are within the range they are in the training data. 
+ * @author Steffen Herbold
+ */
 public class DataGravitation implements IProcessesingStrategy, ISetWiseProcessingStrategy {
 

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

@@ -62 +62 @@
         
         /**
-         * Internal helper function. TODO
-         * @param testdata
-         * @param traindata
-         * @param removeFromTest
+         * Internal helper function for the application of the filter to both all data set as well as a single data set.
+         * @param testdata data of the target product
+         * @param traindata data of the training product
+         * @param removeFromTest defines whether the attributes shall be removed from the test data as well or not
          */
         private void apply(Instances testdata, Instances traindata, boolean removeFromTest) {

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

@@ -7 +7 @@
 import weka.filters.supervised.instance.Resample;
 
-// TODO comment
+/**
+ * Implements undersampling, a strategy for handling bias in data. In case there are less positive samples (i.e. defect-prone) samples in the
+ * data than negative samples (i.e. non-defect-prone), the non-defect-prone entities are sampled such thatthe number of defect-prone and non-defect-prone instances is the same afterwards.  
+ * @author Steffen Herbold
+ */
 public class Undersampling implements IProcessesingStrategy,
                 ISetWiseProcessingStrategy {
@@ -21 +25 @@
         }
 
-
+        /*
+         * (non-Javadoc)
+         * @see de.ugoe.cs.cpdp.dataprocessing.ISetWiseProcessingStrategy#apply(weka.core.Instances, org.apache.commons.collections4.list.SetUniqueList)
+         */
         @Override
         public void apply(Instances testdata, SetUniqueList<Instances> traindataSet) {
@@ -29 +36 @@
         }
 
+        /*
+         * (non-Javadoc)
+         * @see de.ugoe.cs.cpdp.dataprocessing.IProcessesingStrategy#apply(weka.core.Instances, weka.core.Instances)
+         */
         @Override
         public void apply(Instances testdata, Instances traindata) {

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

@@ -58 +58 @@
                 public double classifyInstance(Instance instance) {
                         if( classifiers==null ) {
-                                return 0.0; // TODO check how WEKA expects classifyInstance to behave if no classifier exists yet
+                                return 0.0;
                         }
                         

trunk/CrossPare/src/de/ugoe/cs/cpdp/training/WekaBaggingTraining2.java

@@ -67 +67 @@
                 public double classifyInstance(Instance instance) {
                         if( classifiers==null ) {
-                                return 0.0; // TODO check how WEKA expects classifyInstance to behave if no classifier exists yet
+                                return 0.0;
                         }