public HashSet <HtmlNode> RunOnTestSeenSet()
{
HashSet <HtmlNode> classifierSelectedNodes = new HashSet <HtmlNode>();
InitTestSeen();
foreach (string featureString in FeaturesUsed)
{
HashSet <HtmlNode> resNodes = DomPool.TESTSeenRunXpathQuery(useNormalPerformanceQUERY(featureString));
foreach (HtmlNode nd in resNodes)
{
if (!testSeenAllNodes.Contains(nd))
{
continue;
}
testSeenNodeFeatures[nd].Add(featureString);
}
}
FastVector fvWekaAttributes = GetDataSetAtts();
Instances testSet = new Instances("TestSeenSet", fvWekaAttributes, 10);
testSet.setClassIndex(fvWekaAttributes.size() - 1);
foreach (HtmlNode currNode in testSeenAllNodes)
{
Instance item = new SparseInstance(fvWekaAttributes.size());
for (int i = 0; i < fvWekaAttributes.size() - 1; i++)
{
weka.core.Attribute currFeature = (weka.core.Attribute)fvWekaAttributes.elementAt(i);
if (testSeenNodeFeatures[currNode].Contains(currFeature.name()))
{
item.setValue(currFeature, 1);
}
else
{
item.setValue(currFeature, 0);
}
}
//set the class
weka.core.Attribute classFeature = (weka.core.Attribute)fvWekaAttributes.elementAt(fvWekaAttributes.size() - 1);
//string rightVal = DomPool.TargetNodes.Contains(currNode) ? "yes" : "no";
item.setDataset(testSet);
double classifierdv = classifierTree.classifyInstance(item);
string classifierVal = classFeature.value((int)classifierdv);
if (classifierVal.Equals("yes"))
{
classifierSelectedNodes.Add(currNode);
}
testSet.add(item);
}
return(classifierSelectedNodes);
}
public void LearnModel()
{
Init();
foreach (Feature currFeature in DomPool.SelectorFeatures)
{
String featureString = currFeature.ToString();
HashSet <HtmlNode> resNodes = DomPool.RunXpathQuery(featureString);
foreach (HtmlNode nd in resNodes)
{
if (!allNodes.Contains(nd))
{
continue;
}
nodeFeatures[nd].Add(featureString);
}
}
FastVector fvWekaAttributes = GetDataSetAtts();
Instances trainingSet = new Instances("TS", fvWekaAttributes, 100);
trainingSet.setClassIndex(fvWekaAttributes.size() - 1);
foreach (HtmlNode currNode in allNodes)
{
Instance item = new SparseInstance(fvWekaAttributes.size());
for (int i = 0; i < fvWekaAttributes.size() - 1; i++)
{
weka.core.Attribute currFeature = (weka.core.Attribute)fvWekaAttributes.elementAt(i);
if (nodeFeatures[currNode].Contains(currFeature.name()))
{
item.setValue(currFeature, 1);
}
else
{
item.setValue(currFeature, 0);
}
}
//set the class
weka.core.Attribute classFeature = (weka.core.Attribute)fvWekaAttributes.elementAt(fvWekaAttributes.size() - 1);
item.setValue(classFeature, (DomPool.TargetNodes.Contains(currNode)?"yes":"no"));
item.setDataset(trainingSet);
if (DomPool.TargetNodes.Contains(currNode))
{
for (int t = 0; t < (DomPool.NonTargetNodes.Count() / DomPool.TargetNodes.Count()); t++)
{
trainingSet.add(new SparseInstance(item));
}
}
else
{
trainingSet.add(item);
}
}
String[] options = new String[2];
options[0] = "-C"; // unpruned tree
options[1] = "0.1";
J48 tree = new J48(); // new instance of tree
tree.setOptions(options); // set the options
tree.buildClassifier(trainingSet); // build classifier
//save the resulting classifier
classifierTree = tree;
Reader treeDot = new StringReader(tree.graph());
TreeBuild treeBuild = new TreeBuild();
Node treeRoot = treeBuild.create(treeDot);
FeaturesUsed = getTreeFeatures(treeRoot);
}
public void LearnModel()
{
Init();
foreach (Feature currFeature in DomPool.SelectorFeatures)
{
String featureString = currFeature.ToString();
HashSet <HtmlNode> resNodes = DomPool.RunXpathQuery(featureString);
foreach (HtmlNode nd in resNodes)
{
if (!allNodes.Contains(nd))
{
continue;
}
nodeFeatures[nd].Add(featureString);
}
}
FastVector fvWekaAttributes = GetDataSetAtts();
Instances trainingSet = new Instances("TS", fvWekaAttributes, 10);
trainingSet.setClassIndex(fvWekaAttributes.size() - 1);
foreach (HtmlNode currNode in allNodes)
{
Instance item = new SparseInstance(fvWekaAttributes.size());
for (int i = 0; i < fvWekaAttributes.size() - 1; i++)
{
weka.core.Attribute currFeature = (weka.core.Attribute)fvWekaAttributes.elementAt(i);
if (nodeFeatures[currNode].Contains(currFeature.name()))
{
item.setValue(currFeature, 1);
}
else
{
item.setValue(currFeature, 0);
}
}
//set the class
weka.core.Attribute classFeature = (weka.core.Attribute)fvWekaAttributes.elementAt(fvWekaAttributes.size() - 1);
item.setValue(classFeature, (DomPool.TargetNodes.Contains(currNode)?"yes":"no"));
item.setDataset(trainingSet);
if (DomPool.TargetNodes.Contains(currNode))
{
for (int t = 0; t < (DomPool.NonTargetNodes.Count() / DomPool.TargetNodes.Count()); t++)
{
trainingSet.add(new SparseInstance(item));
}
}
else
{
trainingSet.add(item);
}
}
//String[] options = new String[2];
//options = new string[] { "-C", "0.05" }; // unpruned tree
NaiveBayes cls = new NaiveBayes(); // new instance of tree
//cls.setOptions(weka.core.Utils.splitOptions("-C 1.0 -L 0.0010 -P 1.0E-12 -N 0 -V -1 -W 1 -K \"weka.classifiers.functions.supportVector.PolyKernel -C 250007 -E 1.0\""));
//cls.setOptions(options); // set the options
cls.buildClassifier(trainingSet); // build classifier
//save the resulting classifier
classifier = cls;
// Reader treeDot = new StringReader(tree.graph());
// TreeBuild treeBuild = new TreeBuild();
// Node treeRoot = treeBuild.create(treeDot);
FeaturesUsed = new HashSet <string>();
foreach (Feature f in DomPool.SelectorFeatures)
{
FeaturesUsed.Add(f.ToString());
}
}