public static HashSet <Feature> KeepTopK(HashSet <Feature> featureSet, int k)
{
//this line is here to disable the filtering, it costs in performance much more than it saves
if (featureSet.Count() <= k * 200)
{
return(featureSet);
}
HashSet <Feature> finalRes = null;
LinkedList <object[]> toSort = new LinkedList <object[]>();
foreach (Feature f in featureSet)
{
HashSet <HtmlNode> res = DomPool.RunXpathQuery(XpathTools.FeatureSetToXpath(new HashSet <Feature>(new Feature[] { f })));
HashSet <HtmlNode> selectedPos = new HashSet <HtmlNode>(res.Intersect(DomPool.TargetNodes));
double entropy = Statistics.CalculateEntropy(((double)selectedPos.Count() / res.Count()), 1 - ((double)selectedPos.Count() / res.Count()));
object[] toSortObj = new object[2];
toSortObj[0] = f;
toSortObj[1] = entropy;
toSort.AddFirst(toSortObj);
}
var resTopK = toSort.OrderBy(x => ((double)(x[1]))).Select(x => (Feature)(x[0])).Take(k);
finalRes = new HashSet <Feature>(resTopK.ToList());
return(finalRes);
}
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 HashSet <HtmlNode> selectTrue(HashSet <HtmlNode> nodes, HashSet <Feature> prevFeatures, Boolean right, double threshold = 1)
{
if (this.precision >= threshold)
{
return(nodes);
}
HashSet <Feature> currFeature = new HashSet <Feature>(this.FeatureSet.Except(prevFeatures));
if (currFeature.Count() == 0)
{
if (right)
{
return(nodes);
}
else
{
return(new HashSet <HtmlNode>());
}
}
Feature cf = currFeature.First();
HashSet <HtmlNode> featureRes = DomPool.RunXpathQuery(XpathTools.FeatureSetToXpath(new HashSet <Feature>()
{
cf
}));
featureRes.IntersectWith(nodes);
HashSet <HtmlNode> rightRes = this.SetSelected.selectTrue(featureRes, this.FeatureSet, true, threshold);
HashSet <HtmlNode> leftRes = this.SetNotSelected.selectTrue(nodes, prevFeatures, false, threshold);
return(new HashSet <HtmlNode>(rightRes.Union(leftRes)));
}
public static string LearnXpathFromTrainingFiles(string filesLocation)
{
DomPool.LoadDocuments(filesLocation);
DomPool.Initiate();
DomPool.ExtractAllFeatures();
DecisionNode dn = new DecisionNode();
dn.InitialNodeSet = new HashSet <HtmlNode>(DomPool.TargetNodes.Union(DomPool.NonTargetNodes));
dn.SelectedNegative = new HashSet <HtmlNode>(DomPool.NonTargetNodes.Except(DomPool.TargetNodesPrecision));
dn.SelectedPositive = new HashSet <HtmlNode>(DomPool.TargetNodes);
dn.FeatureSet = new HashSet <Feature>();
dn.CalculateEntropy();
DecisionTreeLearning.RecursiveTreeImprovement(dn);
return(XpathTools.GenerateAForgivingXpath(dn));
//"//*["+XpathTools.DecisionTreeToXpath(dn,new HashSet<Feature>())+"]";
}
public static void RunTest(string filesLocation)
{
string[] folders = Directory.GetDirectories(filesLocation);
foreach (string fldr in folders)
{
Console.WriteLine("Running for category:" + fldr);
string[] innerfolders = Directory.GetDirectories(fldr);
foreach (string innerdir in innerfolders)
{
Console.Out.Flush();
Console.WriteLine("Running for att:" + innerdir);
DomPool.LoadTestDocuments(innerdir.Replace(filesLocation, "testset"));
DomPool.LoadDocuments(innerdir);
//for(int i= (DomPool.allDocsNames.Count() - 1); i <= (DomPool.allDocsNames.Count()-1)/*DomPool.allDocsNames.Count()*/; i++)
for (int i = 1; i <= (DomPool.allDocsNames.Count() - 1); i++)
{
string[] tools = new string[] { "our", "our - not forgiving", "j48", "svm", "xpath-align", "svm" };
int toolStart = 5;
Dictionary <string, string> xpathNonForgiving = new Dictionary <string, string>();
for (int tool = toolStart; tool < 6; tool++)
{
Console.WriteLine("[-] running for training set size=" + i);
IEnumerable <IEnumerable <int> > subsetsIndexes = Subsets(DomPool.allDocsNames.Count(), i);
//Reduce size ...for testing only
//subsetsIndexes = subsetsIndexes.Take(30);
double totalAccuracy = 0;
double totalRecall = 0;
long totalTime = 0;
Console.WriteLine("[-] tool:" + tools[tool]);
Console.WriteLine("+ will run " + subsetsIndexes.Count() + " different iterations for the current set size");
int s = 0;
Dictionary <String, double> SiteTotalRecall = new Dictionary <string, double>();
Dictionary <String, double> SiteTotalPrecision = new Dictionary <string, double>();
Dictionary <String, double> SiteTotalTests = new Dictionary <string, double>();
foreach (string site in DomPool.allDocsNames)
{
SiteTotalPrecision[site] = 0;
SiteTotalRecall[site] = 0;
SiteTotalTests[site] = 0;
}
foreach (IEnumerable <int> currSubsetIndexes in subsetsIndexes)
{
List <int> listRep = new List <int>(currSubsetIndexes);
string stringRep = listRep.Aggregate("", (b, x) => b + "," + x);
s++;
if (s % 10 == 0)
{
//Console.Write("(" + s + "/" + subsetsIndexes.Count() + ") ");
Console.Write(".");
}
//if (tool == toolStart)
//{
HashSet <String> currSubset = GetSubSet(DomPool.allDocsNames, currSubsetIndexes);
DomPool.Initiate(currSubset);
DomPool.ExtractAllFeatures();
//}
var runres = new HashSet <HtmlNode>();
//our method
if (tool < 2)
{
string xpath = "";
if (tool == 0)
{
DecisionNode dn = new DecisionNode();
dn.InitialNodeSet = new HashSet <HtmlNode>(DomPool.TargetNodes.Union(DomPool.NonTargetNodes));
dn.SelectedNegative = new HashSet <HtmlNode>(DomPool.NonTargetNodes.Except(DomPool.TargetNodesPrecision));
dn.SelectedPositive = new HashSet <HtmlNode>(DomPool.TargetNodes);
dn.FeatureSet = new HashSet <Feature>();
dn.CalculateEntropy();
DecisionTreeLearning.RecursiveTreeImprovement(dn);
xpath = XpathTools.GenerateAForgivingXpath(dn);
xpathNonForgiving[stringRep] = XpathTools.DecisionTreeToXpath(dn, new HashSet <Feature>(), 1);
xpathNonForgiving[stringRep] = "//*" + (xpathNonForgiving[stringRep].Equals("") ? "" : ("[" + xpathNonForgiving[stringRep] + "]"));
}
if (tool == 1)
{
xpath = xpathNonForgiving[stringRep];
}
Console.WriteLine("Query:" + xpath);
var watch = Stopwatch.StartNew();
runres = DomPool.TESTRunXpathQuery(xpath);
watch.Stop();
var elapsedMs = watch.ElapsedMilliseconds;
totalTime = totalTime + elapsedMs;
}
else
{
if (tool == 2)
{
ModelLearner model = new ModelLearner();
model.LearnModel();
var watch = Stopwatch.StartNew();
runres = model.RunOnTestSet();
watch.Stop();
var elapsedMs = watch.ElapsedMilliseconds;
totalTime = totalTime + elapsedMs;
}
else
{
if (tool == 3)
{
NB model = new NB();
model.LearnModel();
var watch = Stopwatch.StartNew();
runres = model.RunOnTestSet();
watch.Stop();
var elapsedMs = watch.ElapsedMilliseconds;
totalTime = totalTime + elapsedMs;
}
else
{
if (tool == 4)
{
XpathAlignment model = new XpathAlignment();
model.LearnModel();
var watch = Stopwatch.StartNew();
runres = model.RunOnTestSet();
watch.Stop();
var elapsedMs = watch.ElapsedMilliseconds;
totalTime = totalTime + elapsedMs;
}
else
{
SVM model = new SVM();
model.LearnModel();
var watch = Stopwatch.StartNew();
runres = model.RunOnTestSet();
watch.Stop();
var elapsedMs = watch.ElapsedMilliseconds;
totalTime = totalTime + elapsedMs;
}
}
}
}
HashSet <HtmlNode> spos = new HashSet <HtmlNode>(DomPool.TESTTargetNodes.Intersect(runres));
HashSet <HtmlNode> sposprecision = new HashSet <HtmlNode>(DomPool.TESTTargetNodesPrecision.Intersect(runres));
foreach (var entry in DomPool.docsAndNames)
{
if (DomPool.trainingDocsNames.Contains(entry.Key))
{
continue;
}
HashSet <HtmlNode> docNodes = new HashSet <HtmlNode>(entry.Value.SelectNodes("//*"));
HashSet <HtmlNode> currspos = new HashSet <HtmlNode>(spos.Intersect(docNodes));
HashSet <HtmlNode> currrunres = new HashSet <HtmlNode>(runres.Intersect(docNodes));
HashSet <HtmlNode> currsposprecision = new HashSet <HtmlNode>(sposprecision.Intersect(docNodes));
HashSet <HtmlNode> currTargetNodes = new HashSet <HtmlNode>(DomPool.TESTTargetNodes.Intersect(docNodes));
double currSiteAccuracy = (currsposprecision.Count() / ((double)currrunres.Count()));
double currSiteRecall = (currspos.Count() / ((double)currTargetNodes.Count()));
if (((double)currrunres.Count()) > 0)
{
SiteTotalPrecision[entry.Key] = SiteTotalPrecision[entry.Key] + currSiteAccuracy;
SiteTotalRecall[entry.Key] = SiteTotalRecall[entry.Key] + currSiteRecall;
}
SiteTotalTests[entry.Key] = SiteTotalTests[entry.Key] + 1;
}
double currAccuracy = (sposprecision.Count() / ((double)runres.Count()));
double currRecall = (spos.Count() / ((double)DomPool.TESTTargetNodes.Count()));
if (runres.Count() > 0)
{
totalAccuracy = totalAccuracy + currAccuracy;
totalRecall = totalRecall + currRecall;
}
}
totalAccuracy = totalAccuracy / subsetsIndexes.Count();
totalRecall = totalRecall / subsetsIndexes.Count();
Console.WriteLine("########## Results " + tools[tool] + " for i=" + i + "##########");
Console.WriteLine("+++++++++ Detailed Results for i=" + i + "++++++++++#");
double count = 0;
double totalSumPrecision = 0;
double totalSumRecall = 0;
double avgRecall = 0;
double avgPrecision = 0;
double avgFscore = 0;
double numPrecision = 0;
foreach (string site in DomPool.allDocsNames)
{
if (SiteTotalTests[site] < 1)
{
SiteTotalTests[site]++;
}
else
{
numPrecision++;
}
double sitePrecision = SiteTotalPrecision[site] / SiteTotalTests[site];
double siteRecall = SiteTotalRecall[site] / SiteTotalTests[site];
double siteFscore = 2 * (sitePrecision * siteRecall) / (sitePrecision + siteRecall);
if (siteRecall == 0 && sitePrecision == 0)
{
siteFscore = 0;
}
count++;
avgRecall = avgRecall + siteRecall;
avgPrecision = avgPrecision + sitePrecision;
avgFscore = avgFscore + siteFscore;
Console.WriteLine(">" + site + ": Precision:" + sitePrecision + " , Recall:" + siteRecall + ", F-score:" + siteFscore);
}
Console.WriteLine("++++++++++++++++Total+++++++++++++++++");
avgRecall = avgRecall / count;
avgPrecision = avgPrecision / numPrecision;
avgFscore = avgFscore / count;
Console.WriteLine("Recall:" + avgRecall);
Console.WriteLine("Precision:" + avgPrecision);
Console.WriteLine("F-score:" + avgFscore);
Console.WriteLine("Time:" + totalTime);
}
}
}
}
Console.ReadLine();
}
public static void ImproveTree(DecisionNode dn, int level)
{
double maxScore = 0;
Feature maxGainFeature = null;;
HashSet <HtmlNode> newFeatureSelected = null;
Object lockObj = new object();
double balanceFix = Math.Max(1, (Math.Pow(0.3, Math.Sqrt(level + 1))) * (DomPool.NonTargetNodes.Count() / DomPool.TargetNodes.Count()));
double dnEntropy = dn.CalculateEntropy(1, balanceFix);
Parallel.ForEach(DomPool.SelectorFeatures, (currCandidate) =>
{
HashSet <Feature> newSelectorSet = new HashSet <Feature>(dn.FeatureSet);
newSelectorSet.Add(currCandidate);
string currFeatureXpath = XpathTools.FeatureSetToXpath(new HashSet <Feature>()
{
currCandidate
});
HashSet <HtmlNode> currFeatureXpathSelected = DomPool.RunXpathQuery(currFeatureXpath);
HashSet <HtmlNode> xpathSelected = new HashSet <HtmlNode>(currFeatureXpathSelected.Intersect(dn.InitialNodeSet));
HashSet <HtmlNode> xpathCurrSelected = new HashSet <HtmlNode>(dn.InitialNodeSet.Intersect(xpathSelected));
HashSet <HtmlNode> xpathCurrNotSelected = new HashSet <HtmlNode>(dn.InitialNodeSet.Except(xpathCurrSelected));
//calculate information gain
HashSet <HtmlNode> currSelectedPositive = new HashSet <HtmlNode>(xpathCurrSelected.Intersect(dn.SelectedPositive));
HashSet <HtmlNode> currSelectedNegative = new HashSet <HtmlNode>(xpathCurrSelected.Intersect(dn.SelectedNegative));
HashSet <HtmlNode> currNotSelectedPositive = new HashSet <HtmlNode>(xpathCurrNotSelected.Intersect(dn.SelectedPositive));
HashSet <HtmlNode> currNotSelectedNegative = new HashSet <HtmlNode>(xpathCurrNotSelected.Intersect(dn.SelectedNegative));
double sp = ((double)currSelectedPositive.Count()) / xpathCurrSelected.Count();
double sn = ((double)currSelectedNegative.Count()) / xpathCurrSelected.Count();
double relativeRecall = ((double)currSelectedPositive.Count()) / ((double)dn.SelectedPositive.Count());
//FIX:
sn = sn / (1 + Math.Pow(0, level + 1));
sn = sn / balanceFix;
double selectedProbability = ((double)xpathCurrSelected.Count()) / dn.InitialNodeSet.Count();
double selectedEntropy = Statistics.CalculateEntropy(sp, sn);
double nsp = ((double)currNotSelectedPositive.Count()) / xpathCurrNotSelected.Count();
double nsn = 1 - nsp;
// Apply Fix
nsn = nsn / balanceFix;
double notselectedProbability = 1 - selectedProbability;
double notSelectedEntropy = Statistics.CalculateEntropy(nsp, nsn);
double balanceFixProb = balanceFix;
double sumTemp = (selectedProbability * sn + selectedProbability * sp * balanceFixProb + notselectedProbability * nsn + notselectedProbability * nsp * balanceFixProb);
selectedProbability = (selectedProbability * sn + selectedProbability * sp * balanceFixProb) / sumTemp;
notselectedProbability = (notselectedProbability * nsn + notselectedProbability * nsp * balanceFixProb) / sumTemp;
double gain = dnEntropy - ((selectedProbability * selectedEntropy) + (notselectedProbability * notSelectedEntropy));
double phaseOfDecrease = 1;
if (DomPool.trainingDocsNames.Count() > 3)
{
phaseOfDecrease = 3 / DomPool.trainingDocsNames.Count();
}
//Choose the most cost effective feature
gain = gain / (currCandidate.cost + (((1 - relativeRecall) + (1 - ((double)DomPool.FeatureFrequencey[currCandidate.feature.First().ToLower()]) / DomPool.trainingDocsNames.Count))) * Math.Pow(0.3, level));
lock (lockObj)
{
if (gain > maxScore && sp > nsp)
{
maxScore = gain;
maxGainFeature = currCandidate;
newFeatureSelected = xpathCurrSelected;
}
}
});
if (maxGainFeature == null)
{
return;
}
dn.SetSelected = new DecisionNode();
dn.SetSelected.InitialNodeSet = newFeatureSelected;
dn.SetSelected.FeatureSet = new HashSet <Feature>(dn.FeatureSet);
dn.SetSelected.FeatureSet.Add(maxGainFeature);
dn.SetSelected.SelectedNegative = new HashSet <HtmlNode>(dn.SetSelected.InitialNodeSet.Intersect(dn.SelectedNegative));
dn.SetSelected.SelectedPositive = new HashSet <HtmlNode>(dn.SetSelected.InitialNodeSet.Intersect(dn.SelectedPositive));
dn.SetSelected.CalculateEntropy();
dn.SetNotSelected = new DecisionNode();
dn.SetNotSelected.InitialNodeSet = new HashSet <HtmlNode>(dn.InitialNodeSet.Except(newFeatureSelected));
//FIX FOR NOT BRANCH, INSTEAD OF HAVING THE NOT.
if (FixEnabledForNotBranch)
{
dn.SetNotSelected.InitialNodeSet.UnionWith(dn.SetSelected.SelectedNegative);
}
dn.SetNotSelected.FeatureSet = new HashSet <Feature>(dn.FeatureSet);
dn.SetNotSelected.SelectedNegative = new HashSet <HtmlNode>(dn.SetNotSelected.InitialNodeSet.Intersect(dn.SelectedNegative));
dn.SetNotSelected.SelectedPositive = new HashSet <HtmlNode>(dn.SetNotSelected.InitialNodeSet.Intersect(dn.SelectedPositive));
dn.SetNotSelected.CalculateEntropy();
dn.FeatureSet.Add(maxGainFeature);
}
static void Main(string[] args)
{
Console.WriteLine("T for test, R for Run, S for seen overall testing and O for overall testing:");
string res = ReadLine();
if (res.ToLower().Trim().Equals("huge"))
{
TestSites.TestAllSites();
return;
}
if (res.ToLower().Trim().Equals("t"))
{
DomPool.LoadDocuments(FILES_LOCATION);
DomPool.Initiate();
Console.WriteLine("insert query:");
string q = ReadLine();
while (!q.Equals("exit"))
{
var runres = DomPool.RunXpathQuery(q);
if (runres != null)
{
Console.WriteLine("result size" + runres.Count());
HashSet <HtmlNode> spos = new HashSet <HtmlNode>(DomPool.TargetNodes.Intersect(runres));
HashSet <HtmlNode> sposprecision = new HashSet <HtmlNode>(DomPool.TargetNodesPrecision.Intersect(runres));
foreach (var entry in DomPool.docsAndNames)
{
HashSet <HtmlNode> docNodes = new HashSet <HtmlNode>(entry.Value.SelectNodes("//*"));
HashSet <HtmlNode> currspos = new HashSet <HtmlNode>(spos.Intersect(docNodes));
HashSet <HtmlNode> currrunres = new HashSet <HtmlNode>(runres.Intersect(docNodes));
HashSet <HtmlNode> currsposprecision = new HashSet <HtmlNode>(sposprecision.Intersect(docNodes));
HashSet <HtmlNode> currTargetNodes = new HashSet <HtmlNode>(DomPool.TargetNodes.Intersect(docNodes));
Console.WriteLine(entry.Key + "-Accuracy:" + (currsposprecision.Count() / ((double)currrunres.Count())) + ". Recall:" + (currspos.Count() / ((double)currTargetNodes.Count())) + "");
}
Console.WriteLine("Accuracy:" + (sposprecision.Count() / ((double)runres.Count())) + ". Recall:" + (spos.Count() / ((double)DomPool.TargetNodes.Count())) + "");
}
else
{
Console.WriteLine("null");
}
Console.WriteLine("insert query:");
q = ReadLine();
}
}
else
{
if (res.ToLower().Trim().Equals("r"))
{
Console.WriteLine(LearnXpathWrapper.LearnXpathFromTrainingFiles(FILES_LOCATION));
Console.ReadLine();
}
else
{
if (res.ToLower().Trim().Equals("s"))
{
Console.WriteLine("Output is redirected to resultsSeen.txt in the debug dir");
//write results to text file instead of windows
FileStream fs = new FileStream("resultsSeen.txt", FileMode.Create);
StreamWriter sw = new StreamWriter(fs);
TextWriter tmp = Console.Out;
Console.SetOut(sw);
OverallSeenTesting.RunTest(FILES_LOCATION);
Console.SetOut(tmp);
sw.Flush();
sw.Close();
}
else
{
if (res.ToLower().Trim().Equals("archive"))
{
Console.WriteLine("Output is redirected to results.txt in the debug dir");
//write results to text file instead of windows
FileStream fs = new FileStream("archive2-results.txt", FileMode.Create);
StreamWriter sw = new StreamWriter(fs);
TextWriter tmp = Console.Out;
Console.SetOut(sw);
OverallArchive2Testing.RunTest(ARCHIVE_FILES_LOCATION);
Console.SetOut(tmp);
sw.Flush();
sw.Close();
}
else
{
if (res.ToLower().Trim().Equals("a"))
{
Console.WriteLine("Please enter file name to parse:");
string fnp = ReadLine().Trim();
parseres.learn(fnp);
parseres.save("parsed" + fnp);
}
else
{
Console.WriteLine("Output is redirected to results.txt in the debug dir");
//write results to text file instead of windows
FileStream fs = new FileStream("results.txt", FileMode.Create);
StreamWriter sw = new StreamWriter(fs);
TextWriter tmp = Console.Out;
Console.SetOut(sw);
OverallTesting.RunTest(FILES_LOCATION);
Console.SetOut(tmp);
sw.Flush();
sw.Close();
}
}
}
}
}
}
public static void PorcessSites(List <SiteInfo> siteinfos)
{
foreach (SiteInfo si in siteinfos)
{
try {
int leftPages = pagesNum * si.attributeExtraction.Keys.Count();
List <HtmlNode> sitePages = new List <HtmlNode>(0);
if (!SiteDocuments.ContainsKey(si.SiteName))
{
SiteDocuments[si.SiteName] = new Dictionary <string, Dictionary <String, HtmlNode> >();
SiteLinks[si.SiteName] = new Dictionary <string, HashSet <String> >();
foreach (String attrName in si.attributeExtraction.Keys)
{
SiteDocuments[si.SiteName][attrName] = new Dictionary <string, HtmlNode>();
SiteLinks[si.SiteName][attrName] = new HashSet <string>();
}
}
//Download all URLs
foreach (String startURL in si.StartURLs)
{
try
{
String currURL = startURL;
while (currURL != null)
{
HtmlDocument doc = new HtmlDocument();
var currHTML = URLDownloader.GetHtmlOfURL(currURL);
doc.LoadHtml(currHTML);
if (!String.IsNullOrEmpty(si.PageExtractionXpath))
{
var links = doc.DocumentNode.SelectNodes(si.PageExtractionXpath);
foreach (HtmlNode lnk in links)
{
try
{
String pageLink = lnk.Attributes["href"].Value;
// var htmlstr = URLDownloader.GetHtmlOfURL(URLDownloader.UrlFixIfRelative(pageLink, currURL));
foreach (string attr in si.attributeExtraction.Keys)
{
var newURL = URLDownloader.UrlFixIfRelative(pageLink, currURL);
if (SiteLinks[si.SiteName][attr].Contains(newURL))
{
continue;
}
//HtmlDocument innerDoc = new HtmlDocument();
//innerDoc.LoadHtml(htmlstr);
//SiteDocuments[si.SiteName][attr].Add(pageLink, innerDoc.DocumentNode);
SiteLinks[si.SiteName][attr].Add(newURL);
if (--leftPages <= 0)
{
break;
}
}
if (leftPages <= 0)
{
break;
}
}
catch (Exception e) {
// Console.WriteLine(e.StackTrace);
}
}
}
else
{
foreach (string attr in si.attributeExtraction.Keys)
{
try
{
if (SiteLinks[si.SiteName][attr].Contains(currURL))
{
continue;
}
// HtmlDocument innerDoc = new HtmlDocument();
// innerDoc.LoadHtml(currHTML);
// SiteDocuments[si.SiteName][attr].Add(currURL, innerDoc.DocumentNode);
SiteLinks[si.SiteName][attr].Add(currURL);
if (--leftPages <= 0)
{
break;
}
}
catch
{
break;
}
}
}
if (leftPages <= 0)
{
break;
}
//get next page
String nextLink = null;
try
{
nextLink = HttpUtility.HtmlDecode(doc.DocumentNode.SelectSingleNode(si.NextPageXPath).Attributes["href"].Value);
}
catch { nextLink = null; }
if (nextLink != null)
{
nextLink = URLDownloader.UrlFixIfRelative(nextLink, currURL);
}
if (!currURL.ToLower().Trim().Equals(nextLink.ToLower().Trim()))
{
currURL = nextLink;
}
else
{
break;
}
}
}
catch { }
}
foreach (String attr in si.attributeExtraction.Keys)
{
var trainingkeys = new HashSet <String>(SiteLinks[si.SiteName][attr].Take(5)); //new HashSet<String>(SiteDocuments[si.SiteName][attr].Keys.Take(5));
var trainingDic = new Dictionary <String, HtmlNode>(); //SiteDocuments[si.SiteName][attr].Where(x => trainingkeys.Contains(x.Key)).ToDictionary(kv => kv.Key, kv => kv.Value);
foreach (String lnk in trainingkeys)
{
trainingDic.Add(lnk, GetHtmlNode(lnk));
}
var testDic = SiteDocuments[si.SiteName][attr].Where(x => !trainingkeys.Contains(x.Key)).ToDictionary(kv => kv.Key, kv => kv.Value);
foreach (var lnk in trainingDic.Keys)
{
HtmlNode adoc = trainingDic[lnk];
try
{
var gt = adoc.SelectNodes(si.attributeExtraction[attr]);
if (gt != null)
{
foreach (var targetNode in gt)
{
//Console.Write(":");
if (targetNode.Attributes.Contains("userselected"))
{
targetNode.SetAttributeValue("userselected", "yes");
}
else
{
targetNode.Attributes.Add("userselected", "yes");
}
}
}
}
catch { }
MD5 md5 = MD5.Create();
if (!File.Exists("huge/" + si.SiteName + "/training/" + attr + "/" + getMD5(lnk) + ".html"))
{
Directory.CreateDirectory("huge/" + si.SiteName + "/training/" + attr);
File.WriteAllText("huge/" + si.SiteName + "/training/" + attr + "/" + getMD5(lnk) + ".html", adoc.InnerHtml);
}
}
DomPool.LoadDocuments(trainingDic);
//DomPool.LoadTestDocuments();
DomPool.Initiate(new HashSet <string>(trainingDic.Keys));
DomPool.ExtractAllFeatures();
// Run code
DecisionNode dn = new DecisionNode();
dn.InitialNodeSet = new HashSet <HtmlNode>(DomPool.TargetNodes.Union(DomPool.NonTargetNodes));
dn.SelectedNegative = new HashSet <HtmlNode>(DomPool.NonTargetNodes.Except(DomPool.TargetNodesPrecision));
dn.SelectedPositive = new HashSet <HtmlNode>(DomPool.TargetNodes);
dn.FeatureSet = new HashSet <Feature>();
dn.CalculateEntropy();
DecisionTreeLearning.RecursiveTreeImprovement(dn);
var xpath = XpathTools.GenerateAForgivingXpath(dn);
var xpathNonForgiving = XpathTools.DecisionTreeToXpath(dn, new HashSet <Feature>(), 1);
xpathNonForgiving = "//*" + (xpathNonForgiving.Equals("") ? "" : ("[" + xpathNonForgiving + "]"));
XpathAlignment model = new XpathAlignment();
model.LearnModel();
var alignmentXpath = model.xpath;
CheckOnTest(new HashSet <string>(SiteLinks[si.SiteName][attr].Except(trainingkeys)), xpath, si.attributeExtraction[attr], si.SiteName, attr, "ForgivingXP");
CheckOnTest(new HashSet <string>(SiteLinks[si.SiteName][attr].Except(trainingkeys)), alignmentXpath, si.attributeExtraction[attr], si.SiteName, attr, "Alignment");
}
}finally{
}
SiteDocuments.Remove(si.SiteName);
}
Console.ReadLine();
}
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());
}
}
public HashSet <HtmlNode> RunOnTestSeenSet()
{
return(DomPool.TESTSeenRunXpathQuery(xpath));
}
/// <summary> /// Initialize DOM with a selector string. /// </summary> /// <param name="selector">DOM Selector string.</param> public static ISyncDom _(string selector) => DomPool.GetDom(selector);
