de.lmu.ifi.dbs.elki.evaluation.histogram
Class ComputeOutlierHistogram<O extends DatabaseObject>

java.lang.Object
  de.lmu.ifi.dbs.elki.logging.AbstractLoggable
      de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm<O,MultiResult>
          de.lmu.ifi.dbs.elki.evaluation.histogram.ComputeOutlierHistogram<O>

Type Parameters:

O - Database object type

All Implemented Interfaces:

Algorithm<O,MultiResult>, Parameterizable

public class ComputeOutlierHistogram<O extends DatabaseObject>
extends AbstractAlgorithm<O,MultiResult>

Compute a Histogram to evaluate a ranking algorithm. The parameter -hist.positive specifies the class label of "positive" hits.

Author:

Lisa Reichert, Erich Schubert

Field Summary

private Algorithm<O,Result>	algorithm Holds the algorithm to run.
private ObjectParameter<Algorithm<O,Result>>	ALGORITHM_PARAM Parameter to specify the algorithm to be applied, must extend Algorithm.
private int	bins Number of bins
static OptionID	BINS_ID OptionID for BINS_ID
private IntParameter	BINS_PARAM number of bins for the histogram Default value: EuclideanDistanceFunction Key: -comphist.bins
private Pattern	positive_class_name Stores the "positive" class.
static OptionID	POSITIVE_CLASS_NAME_ID OptionID for POSITIVE_CLASS_NAME_PARAM
private PatternParameter	POSITIVE_CLASS_NAME_PARAM The object pattern to identify positive classes Key: -comphist.positive
private ScalingFunction	scaling Scaling function to use
static OptionID	SCALING_ID OptionID for SCALING_PARAM
private ObjectParameter<ScalingFunction>	SCALING_PARAM Parameter to specify a scaling function to use.
private boolean	splitfreq Flag to make split frequencies
static OptionID	SPLITFREQ_ID OptionID for SPLITFREQ_PARAM
private Flag	SPLITFREQ_PARAM Flag to count frequencies of outliers and non-outliers separately Key: -histogram.splitfreq

Fields inherited from class de.lmu.ifi.dbs.elki.logging.AbstractLoggable

debug, logger

Constructor Summary

ComputeOutlierHistogram(Parameterization config)
Constructor, adhering to Parameterizable

Method Summary

private OutlierResult	getOutlierResult(Database<O> database, Result result) Find an OutlierResult to work with.
protected MultiResult	runInTime(Database<O> database) The run method encapsulated in measure of runtime.

Methods inherited from class de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm

isTime, isVerbose, run, setTime, setVerbose

Methods inherited from class de.lmu.ifi.dbs.elki.logging.AbstractLoggable

debugFine, debugFiner, debugFinest, exception, progress, verbose, warning

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

POSITIVE_CLASS_NAME_ID

public static final OptionID POSITIVE_CLASS_NAME_ID

OptionID for POSITIVE_CLASS_NAME_PARAM

BINS_ID

public static final OptionID BINS_ID

OptionID for BINS_ID

SCALING_ID

public static final OptionID SCALING_ID

OptionID for SCALING_PARAM

SPLITFREQ_ID

public static final OptionID SPLITFREQ_ID

OptionID for SPLITFREQ_PARAM

POSITIVE_CLASS_NAME_PARAM

private final PatternParameter POSITIVE_CLASS_NAME_PARAM

The object pattern to identify positive classes

Key: -comphist.positive

BINS_PARAM

private final IntParameter BINS_PARAM

number of bins for the histogram

Default value: EuclideanDistanceFunction

Key: -comphist.bins

ALGORITHM_PARAM

private final ObjectParameter<Algorithm<O extends DatabaseObject,Result>> ALGORITHM_PARAM

Parameter to specify the algorithm to be applied, must extend Algorithm.

Key: -algorithm

SCALING_PARAM

private final ObjectParameter<ScalingFunction> SCALING_PARAM

Parameter to specify a scaling function to use.

Key: -comphist.scaling

SPLITFREQ_PARAM

private final Flag SPLITFREQ_PARAM

Flag to count frequencies of outliers and non-outliers separately

Key: -histogram.splitfreq

positive_class_name

private Pattern positive_class_name

Stores the "positive" class.

bins

private int bins

Number of bins

algorithm

private Algorithm<O extends DatabaseObject,Result> algorithm

Holds the algorithm to run.

scaling

private ScalingFunction scaling

Scaling function to use

splitfreq

private boolean splitfreq

Flag to make split frequencies

Constructor Detail

ComputeOutlierHistogram

public ComputeOutlierHistogram(Parameterization config)

Constructor, adhering to Parameterizable

Parameters:

config - Parameterization

Method Detail

runInTime

protected MultiResult runInTime(Database<O> database)
                         throws IllegalStateException

Description copied from class: AbstractAlgorithm

The run method encapsulated in measure of runtime. An extending class needs not to take care of runtime itself.

Specified by:

runInTime in class AbstractAlgorithm<O extends DatabaseObject,MultiResult>

Parameters:

database - the database to run the algorithm on

Returns:

the Result computed by this algorithm

Throws:

IllegalStateException - if the algorithm has not been initialized properly (e.g. the setParameters(String[]) method has been failed to be called).

getOutlierResult

private OutlierResult getOutlierResult(Database<O> database,
                                       Result result)

Find an OutlierResult to work with.

Parameters:

database - Database context

result - Result object

Returns:

Iterator to work with