public void testRule(NumericalRule rule, int minSupport, float minAccuracy) throws SQLException {
// System.out.println("!!!"+rule.getRuleString()+"!!!");
String prediction = rule.getHead().getConstant();
int positivesCount = 0;
int negativesCount = 0;
String sparql = createTestQuery(rule);
// System.out.println(sparql);
long t = System.currentTimeMillis();
ResultSet rs = (ResultSet) qh.executeQuery(sparql);
// System.out.println("Executed in "+(System.currentTimeMillis()-t));
float overallAcc =
((float)
ArrayTools.sum(
ArrayTools.multiply(
rule.getAccuracyDistribution(), rule.getSupportDistribution())))
/ ((float) ArrayTools.sum(rule.getSupportDistribution()));
float[] acc =
ArrayTools.getAccuraciesWithMinSupport(
rule.getSupportDistribution(), rule.getBodySupportDistribution(), minSupport);
String ranges = "";
for (int i = 0; i < acc.length; i++) {
if (acc[i] >= minAccuracy) ranges += "+";
else ranges += "-";
}
// System.out.println(ranges);
// ArrayTools.print(acc);
float lastNum = Float.NaN;
while (rs.next()) {
float num = rs.getFloat(1);
String observation = rs.getString(2).replaceAll("\"", "");
int count = rs.getInt(3);
int bucket = histogram.getBucket(num);
if (acc[bucket] >= minAccuracy) {
if (prediction.equals(observation)) positivesCount += count;
else negativesCount += count;
}
lastNum = num;
}
int coveringCount = positivesCount + negativesCount;
float predictionAccuracy = ((float) positivesCount) / (((float) (coveringCount)));
// System.out.println(rule.getRuleString() + "\n[" + predictionAccuracy + "," + coveringCount +
// "] = ("+positivesCount+"/"+negativesCount+")");
rule.observedConfidence = predictionAccuracy;
rule.observedPositives = positivesCount;
rule.observedNegatives = negativesCount;
rule.observedOverallConfidence = overallAcc;
}
public static void main(String[] args) throws Exception {
String output = "";
float confidenceThreshold = (float) 0.7;
// double[] indepTSArray = {/*0.0, 5.0, 10.0, 15.0, 20.0, 30.0,*/ 50.0/*, 75.0, 100.0*/};
// double[] kldivTSArray = {/*0.000, */0.0125, 0.0250, 0.0325, 0.0500, 0.0625, 0.0750, 0.0825,
// 0.100};
// int[] suppTSArray = {25/*, 50, 75, 100, 125, 150, 300, 500, 1000*/};
double[] indepTSArray = {0.0};
int[] suppTSArray = {5};
// int[] maxNodesArray =
// {5,10,15,20,25,30,40,50,60,70,80,90,100,110,120,130,140,150,200,250,300,350,400,450,500};
// int[] maxNodesArray = {10,20,30,40,50,60,70,80,90,100};
// int[] maxNodesArray = {10,50,100};
int[] maxNodesArray = {1000};
double[] kldivTSArray = {0.0};
for (int measure = 0; measure <= 0; measure++)
for (int numBuckets = 25; numBuckets <= 25; numBuckets += 25)
for (int l = 0; l < maxNodesArray.length; l++)
for (int k = 0; k < suppTSArray.length; k++)
for (int i = 0; i < indepTSArray.length; i++) {
for (int j = 0; j < kldivTSArray.length; j++) {
// Connection connPartition = Driver.connect("src/rdf3x-dblp.properties");
// Connection connPartition = Driver.connect("src/rdf3x-data91-train.properties");
Connection connPartition = Driver.connect("src/rdf3x-yago.properties");
QueryHandler qh = new QueryHandler(connPartition);
info = RelationsInfo.readFromDisk("relationsInfoForRdf3x.ser");
// Relation rootRelation = new Relation("<http://purl.org/dc/terms/citations>",
// null, null);
// Relation rootRelation =
// info.getRelationFromRelations("<http://yago-knowledge.org/resource/hasHeight>");
Relation rootRelation =
info.getRelationFromRelations(
"<http://yago-knowledge.org/resource/hasPopulation>");
// Relation rootRelation = new
// Relation("<http://data-gov.tw.rpi.edu/vocab/p/91/pincp>", null, null);
// Relation rootRelation = new
// Relation("<http://dbpedia.org/property/populationDensity>", null, null);
// Relation rootRelation = new
// Relation("<http://dbpedia.org/property/gdpNominalPerCapita>", null, null);
// Relation rootRelation = new Relation("<http://purl.org/ontology/mo/duration_ms>",
// null, null);
RuleLearner learner = new RuleLearner(qh, null, null, rootRelation);
ArrayTools.measure = measure;
learner.indepThreshold = (float) indepTSArray[i];
learner.klDivThreshold = (float) kldivTSArray[j];
learner.suppThreshold = suppTSArray[k];
learner.maxNodesPerLevel = maxNodesArray[l];
learner.confidenceThreshold = confidenceThreshold;
learner.numOfBuckets = numBuckets;
// RuleLearner learner = new RuleLearner(qh, null, null,
// info.getRelationFromRelations("<http://yago-knowledge.org/resource/hasPopulation>"));
learner.learn();
CorrelationLatticeNode root = learner.getRoot();
// CorrelationLatticeNode root =
// CorrelationLatticeNode.readFromDisk("correlation-lattice-income.ser");
// Collection<NumericalRule> learnedRules =
// CorrelationLatticeNode.searchRules(root);
Collection<NumericalRule> learnedRules = learner.getLearnedRules();
for (NumericalRule r : learnedRules) {
System.out.println(r.getRuleString());
System.out.print("\t");
ArrayTools.print(r.getAccuracyDistribution());
}
root.printSuggestions(null);
// Deserialize load it
/*CorrelationLatticeNode root = CorrelationLatticeNode.readFromDisk("correlation-lattice-income.ser");
Histogram hs = root.getHistogram();
ObjectInputStream ois = new ObjectInputStream(new FileInputStream("rules-income.ser"));
Set<NumericalRule> learnedRules = (HashSet<NumericalRule>) ois.readObject();
for (NumericalRule r: learnedRules) {
System.out.println(r.getRuleString());
}
if (root.getRootLiteral()==null) System.out.println("FODEO!");
*/
// RuleTester rt = new RuleTester(qh,hs,rootRelation);
/*
// Test on test partition
connPartition = Driver.connect("src/rdf3x-data91-test.properties");
qh = new QueryHandler(connPartition);
float negatives = 0;
float positives = 0;
float avgGain = 0;
RuleTester rt = new RuleTester(root,qh);
for (NumericalRule r: learnedRules) {
rt.testRule(r, learner.suppThreshold, confidenceThreshold);
boolean isSpecialization = false;
NumericalRule generalization = null;
for (NumericalRule r1: learnedRules) {
if (r.isSpecializationOf(r1)) {
isSpecialization = true;
generalization = r1;
break;
}
}
if (r.observedOverallConfidence<confidenceThreshold) {
float gain = r.observedConfidence/r.observedOverallConfidence;
if (!Float.isNaN(gain)) {
float observedTotal = (float)(r.observedPositives+r.observedNegatives);
float currentTotal = (float)(positives+negatives);
avgGain = (avgGain*(currentTotal) + gain*(observedTotal))/(currentTotal+observedTotal);
}
if (!isSpecialization) {
positives += r.observedPositives;
negatives += r.observedNegatives;
} else {
//System.out.println("Specialization of: "+generalization.getRuleString());
}
}
}
output += "\n\nkldiv="+learner.klDivThreshold+"\tindep="+learner.indepThreshold + "\tminsup="+learner.suppThreshold + "\tmaxnodes="+learner.maxNodesPerLevel + "\tbuckets="+numBuckets + "\tmeasure="+measure +
"\nElapsedTime="+learner.elapsedTime+" \t("+learner.firstLevelTime+" + "+(learner.elapsedTime-learner.firstLevelTime)+")" +
"\nacc="+(positives/(positives+negatives)) +
"\nsup="+(positives+negatives) +
"\ngain="+(avgGain) +
"\nnodes="+root.countNonPruned() +
"\nrules="+learnedRules.size();
*/
CorrelationLatticeNode.reset();
}
}
System.out.println("\n\n\n\nFinalOutput" + output);
}
