public abstract class LocalSearchMiner<M> extends OptimalMiner<M>
Modifier and Type | Field and Description |
---|---|
protected static boolean |
debug |
protected static int |
MAX_ITER |
protected static int |
MAX_MOVES_WITHOUT_IMPROVEMENT |
bestDistance, bestState, classMapping, context, costMap, currentState, eventClasses, function, log, origLog, origModel, traceMapping, trustLog, trustModel
Constructor and Description |
---|
LocalSearchMiner(DistanceFunction function,
org.processmining.framework.plugin.PluginContext context,
org.deckfour.xes.model.XLog log,
M model) |
Modifier and Type | Method and Description |
---|---|
protected abstract SearchState<M> |
move(Neighborhood<M> neighborhood,
SearchState<M> currentState)
We assume that the alignment guides us in changing the graph and the log.
|
protected void |
performSearch()
Simple local search meta-heuristic, where we stop searching
after MAX_MOVES_WITHOUT_IMPROVEMENT moves without improvement,
or after MAX_ITER iterations.
|
protected abstract Neighborhood<M> |
recomputeNeighborhood(SearchState<M> state) |
protected abstract void |
visualizeState(M model) |
computeDistance, getBestLog, getBestModel, getClone, getEventClasses, getLogDistance, getTraceMapping, searchForBetterLogAndModel, setTrustLevels
protected static final int MAX_ITER
protected static final int MAX_MOVES_WITHOUT_IMPROVEMENT
protected static boolean debug
public LocalSearchMiner(DistanceFunction function, org.processmining.framework.plugin.PluginContext context, org.deckfour.xes.model.XLog log, M model)
protected void performSearch()
performSearch
in class OptimalMiner<M>
protected abstract Neighborhood<M> recomputeNeighborhood(SearchState<M> state)
protected abstract void visualizeState(M model)
protected abstract SearchState<M> move(Neighborhood<M> neighborhood, SearchState<M> currentState)
neighborhood
- the Neighborhood
consisting of possible moves (possibly with weights that reflect
their chances to improve the alignment)