
O - Object typepublic class ValidateApproximativeKNNIndex<O,D extends Distance<D>> extends AbstractDistanceBasedAlgorithm<O,D,Result>
| Modifier and Type | Class and Description | 
|---|---|
static class  | 
ValidateApproximativeKNNIndex.Parameterizer<O,D extends Distance<D>>
Parameterization class 
 | 
| Modifier and Type | Field and Description | 
|---|---|
protected boolean | 
forcelinear
Force linear scanning. 
 | 
protected int | 
k
Number of neighbors to retrieve. 
 | 
private static Logging | 
LOG
The logger for this class. 
 | 
protected Pattern | 
pattern
Filter pattern 
 | 
protected DatabaseConnection | 
queries
The alternate query point source. 
 | 
protected RandomFactory | 
random
Random generator factory 
 | 
protected double | 
sampling
Sampling size. 
 | 
DISTANCE_FUNCTION_ID| Constructor and Description | 
|---|
ValidateApproximativeKNNIndex(DistanceFunction<? super O,D> distanceFunction,
                             int k,
                             DatabaseConnection queries,
                             double sampling,
                             boolean forcelinear,
                             RandomFactory random,
                             Pattern pattern)
Constructor. 
 | 
| Modifier and Type | Method and Description | 
|---|---|
TypeInformation[] | 
getInputTypeRestriction()
Get the input type restriction used for negotiating the data query. 
 | 
protected Logging | 
getLogger()
Get the (STATIC) logger for this class. 
 | 
Result | 
run(Database database,
   Relation<O> relation)
Run the algorithm. 
 | 
getDistanceFunctionmakeParameterDistanceFunction, runprivate static final Logging LOG
protected int k
protected DatabaseConnection queries
protected double sampling
protected boolean forcelinear
protected RandomFactory random
protected Pattern pattern
public ValidateApproximativeKNNIndex(DistanceFunction<? super O,D> distanceFunction, int k, DatabaseConnection queries, double sampling, boolean forcelinear, RandomFactory random, Pattern pattern)
distanceFunction - Distance function to usek - K parameterqueries - Query data set (may be null!)sampling - Sampling raterandom - Random factoryforcelinear - Force the use of linear scanning.pattern - public Result run(Database database, Relation<O> relation)
database - Databaserelation - Relationpublic TypeInformation[] getInputTypeRestriction()
AbstractAlgorithmgetInputTypeRestriction in interface AlgorithmgetInputTypeRestriction in class AbstractAlgorithm<Result>protected Logging getLogger()
AbstractAlgorithmgetLogger in class AbstractAlgorithm<Result>