/** Sort results to identify potential keywords. */
public void sortResults(final long max_results) {
Arrays.sort(
nodeList,
new Comparator<Node>() {
public int compare(Node n1, Node n2) {
if (n1.rank > n2.rank) {
return -1;
} else if (n1.rank < n2.rank) {
return 1;
} else {
return 0;
}
}
});
// mark the top-ranked nodes
distStats.clear();
for (int i = 0; i < nodeList.length; i++) {
final Node n1 = nodeList[i];
if (i <= max_results) {
n1.marked = true;
distStats.addValue(n1.rank);
}
if (LOG.isDebugEnabled()) {
LOG.debug("n: " + n1.key + " " + n1.rank + " " + n1.marked);
for (Node n2 : n1.edges) {
LOG.debug(" - " + n2.key);
}
}
}
}
/**
* Calculates the average, min ad max throughput time out of the throughput times of all traces in
* piList. Next to this, the arrival rate is calculated. All metrics are based on the process
* instances in piList only
*
* @param piList ArrayList: the process instances used
* @param fitOption int: the fit option used (how to deal with non-conformance)
* @throws Exception
*/
public void calculateMetrics(ArrayList piList, int fitOption) throws Exception {
properFrequency = 0;
timeStats.clear();
arrivalStats.clear();
ArrayList arrivalDates = new ArrayList();
ListIterator lit = piList.listIterator();
while (lit.hasNext()) {
ExtendedLogTrace currentTrace = (ExtendedLogTrace) lit.next();
if (currentTrace.hasProperlyTerminated() && currentTrace.hasSuccessfullyExecuted()) {
properFrequency++;
}
try {
long tp = (currentTrace.getEndDate().getTime() - currentTrace.getBeginDate().getTime());
if (fitOption == 0) {
// timeStats based on all traces
timeStats.addValue(tp);
arrivalDates.add(currentTrace.getBeginDate());
}
if (currentTrace.hasProperlyTerminated() && currentTrace.hasSuccessfullyExecuted()) {
if (fitOption == 1) {
// timeStats based on fitting traces only
timeStats.addValue(tp);
arrivalDates.add(currentTrace.getBeginDate());
}
}
} catch (NullPointerException ex) {
ex.printStackTrace();
}
}
Date[] arrivals = (Date[]) arrivalDates.toArray(new Date[0]);
// make sure arrivaldates are sorted
Arrays.sort(arrivals);
if (arrivals.length > 1) {
for (int i = 1; i < arrivals.length; i++) {
long t1 = arrivals[i].getTime();
long t2 = arrivals[i - 1].getTime();
long iat = arrivals[i].getTime() - arrivals[i - 1].getTime();
if (iat >= 0) {
arrivalStats.addValue(iat);
}
}
}
}
/** Iterate through the graph, calculating rank. */
protected void iterateGraph(final int max_iterations) {
final double[] rankList = new double[nodeList.length];
// either run through N iterations, or until the standard
// error converges below a threshold
for (int k = 0; k < max_iterations; k++) {
distStats.clear();
// calculate the next rank for each node
for (int i = 0; i < nodeList.length; i++) {
final Node n1 = nodeList[i];
double rank = 0.0D;
for (Node n2 : n1.edges) {
rank += n2.rank / (double) n2.edges.size();
}
rank *= TEXTRANK_DAMPING_FACTOR;
rank += 1.0D - TEXTRANK_DAMPING_FACTOR;
rankList[i] = rank;
distStats.addValue(Math.abs(n1.rank - rank));
// System.out.println("node : " + n1.key + " rank : " + Math.abs((n1.rank - rank)));
}
final double standard_error =
distStats.getStandardDeviation() / Math.sqrt((double) distStats.getN());
// swap in new rank values
for (int i = 0; i < nodeList.length; i++) {
nodeList[i].rank = rankList[i];
}
if (standard_error < STANDARD_ERROR_THRESHOLD) {
break;
}
}
}
/**
* Calculates the rank weighting scores for all the nodes in the graph. Iterative calculates over
* the graph until convergence at the standard error threshold or until max iterations.
*
* @param maxIterations Max number of iterations allowed for calculating rank scores
* @param language Language of the text to calculate rank weighting scores for Available
* languages: Icelandic and English
*/
public void weigthingScore(int maxIterations, Language language) {
LinkedList<Node> nodes = new LinkedList<Node>();
// Add nodes to LinkedList, we need them to stay in order
for (int i = 0; i < nodeList.length; i++) {
nodes.add(nodeList[i]);
}
/*
WS(Vi) = ( 1 - d) + d * Sum(VjIn) ________Wij________ * WS(Vj)
Sum(Vk outVj) Wjk
*/
for (int k = 0; k < maxIterations; k++) {
distStats.clear();
// Use dynamic programming to calculate the scores
double previousWSScore[] = new double[nodes.size()];
// Read in scores already calculated for nodes
for (Node s : nodeList) {
previousWSScore[nodes.indexOf(s)] = s.rank;
}
// For all nodes in the graph
for (Node sentence_i : nodes) {
double resultSumVji = 0;
// For all in-coming edges of Vi
for (Node sentence_j : sentence_i.edgesIN) {
// Do not compare a sentence to it self, we do not allow self voting here
if (!sentence_j.value.text.equalsIgnoreCase(sentence_i.value.text)) {
// Calculate the sum of all similarity measurements
// from all Vj nodes with outgoing edges to Vk nodes, see Wjk in equation
double sumWjk = getSumWjk(sentence_j, language);
if (sumWjk != 0) {
double Wji = 0.0;
if (language.equals(Language.ICELANDIC)) {
// Calculate Wij, similarity between two sentences
Wji = sentence_i.similarity(sentence_j);
} else if (language.equals(Language.ENGLISH)) {
// Calculate Wij, similarity between two sentences
Wji = sentence_i.similarityEN(sentence_j);
}
// Get the score for the previous node
double WSVj = previousWSScore[nodes.indexOf(sentence_j)];
// Sum all (j in Vj)
resultSumVji += ((Wji / sumWjk) * WSVj);
}
}
}
// Calculate weighting score WS(Vi)
double WSVi = (1.0 - TEXTRANK_DAMPING_FACTOR) + TEXTRANK_DAMPING_FACTOR * resultSumVji;
distStats.addValue(Math.abs(sentence_i.rank - WSVi));
sentence_i.rank = WSVi;
}
// Calculate the Standard Error of the Mean
final double standard_error =
distStats.getStandardDeviation() / Math.sqrt((double) distStats.getN());
// if std error of the mean is less than threshold
// the graph has converged and we break
if (standard_error < STANDARD_ERROR_THRESHOLD) {
break;
}
}
}