Package elki.clustering.subspace
Class P3C.Par
- java.lang.Object
-
- elki.clustering.subspace.P3C.Par
-
- All Implemented Interfaces:
Parameterizer
- Enclosing class:
- P3C
public static class P3C.Par extends java.lang.Object implements Parameterizer
Parameterization class.- Author:
- Florian Nuecke
-
-
Field Summary
Fields Modifier and Type Field Description protected doublealphaParameter for the chi squared test threshold.static OptionIDALPHA_THRESHOLD_IDParameter for the chi squared test threshold.static OptionIDEM_DELTA_IDThreshold when to stop EM iterations.protected doubleemDeltaThreshold when to stop EM iterations.static OptionIDMAX_EM_ITERATIONS_IDMaximum number of iterations for the EM step.protected intmaxEmIterationsMaximum number of iterations for the EM step.static OptionIDMIN_CLUSTER_SIZE_IDMinimum cluster size for noise flagging.protected intminClusterSizeMinimum cluster size for noise flagging.static OptionIDPOISSON_THRESHOLD_IDParameter for the poisson test threshold.protected doublepoissonThresholdParameter for the poisson test threshold.
-
Constructor Summary
Constructors Constructor Description Par()
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description voidconfigure(Parameterization config)Configure the class.P3Cmake()Make an instance after successful configuration.
-
-
-
Field Detail
-
ALPHA_THRESHOLD_ID
public static final OptionID ALPHA_THRESHOLD_ID
Parameter for the chi squared test threshold.
-
POISSON_THRESHOLD_ID
public static final OptionID POISSON_THRESHOLD_ID
Parameter for the poisson test threshold.
-
MAX_EM_ITERATIONS_ID
public static final OptionID MAX_EM_ITERATIONS_ID
Maximum number of iterations for the EM step.
-
EM_DELTA_ID
public static final OptionID EM_DELTA_ID
Threshold when to stop EM iterations.
-
MIN_CLUSTER_SIZE_ID
public static final OptionID MIN_CLUSTER_SIZE_ID
Minimum cluster size for noise flagging. (Not existant in the original publication).
-
alpha
protected double alpha
Parameter for the chi squared test threshold. While statistical values such as 0.01 are a good choice, we found the need to modify this parameter in our experiments.
-
poissonThreshold
protected double poissonThreshold
Parameter for the poisson test threshold.
-
maxEmIterations
protected int maxEmIterations
Maximum number of iterations for the EM step.
-
emDelta
protected double emDelta
Threshold when to stop EM iterations.
-
minClusterSize
protected int minClusterSize
Minimum cluster size for noise flagging. (Not existant in the original publication).
-
-
Method Detail
-
configure
public void configure(Parameterization config)
Description copied from interface:ParameterizerConfigure the class.Note: the status is collected by the parameterization object, so that multiple errors may arise and be reported in one run.
- Specified by:
configurein interfaceParameterizer- Parameters:
config- Parameterization
-
make
public P3C make()
Description copied from interface:ParameterizerMake an instance after successful configuration.Note: your class should return the exact type, only this very broad interface should use
Objectas return type.- Specified by:
makein interfaceParameterizer- Returns:
- a new instance
-
-