org.apache.commons.math.stat.ranking
Class NaturalRanking

java.lang.Object
  org.apache.commons.math.stat.ranking.NaturalRanking

All Implemented Interfaces:

RankingAlgorithm

public class NaturalRanking
extends Object
implements RankingAlgorithm

Ranking based on the natural ordering on doubles.

NaNs are treated according to the configured NaNStrategy and ties are handled using the selected TiesStrategy. Configuration settings are supplied in optional constructor arguments. Defaults are NaNStrategy.MAXIMAL and TiesStrategy.AVERAGE, respectively. When using TiesStrategy.RANDOM, a RandomGenerator may be supplied as a constructor argument.

Examples:

Input data: (20, 17, 30, 42.3, 17, 50, Double.NaN, Double.NEGATIVE_INFINITY, 17)
NaNStrategy	TiesStrategy	rank(data)
default (NaNs maximal)	default (ties averaged)	(5, 3, 6, 7, 3, 8, 9, 1, 3)
default (NaNs maximal)	MINIMUM	(5, 2, 6, 7, 2, 8, 9, 1, 2)
MINIMAL	default (ties averaged)	(6, 4, 7, 8, 4, 9, 1.5, 1.5, 4)
REMOVED	SEQUENTIAL	(5, 2, 6, 7, 3, 8, 1, 4)
MINIMAL	MAXIMUM	(6, 5, 7, 8, 5, 9, 2, 2, 5)

Since:

2.0

Version:

$Revision: 811827 $ $Date: 2009-09-06 11:32:50 -0400 (Sun, 06 Sep 2009) $

Nested Class Summary

private static class

NaturalRanking.IntDoublePair Represents the position of a double value in an ordering.

Field Summary

static NaNStrategy	DEFAULT_NAN_STRATEGY default NaN strategy
static TiesStrategy	DEFAULT_TIES_STRATEGY default ties strategy
private NaNStrategy	nanStrategy NaN strategy - defaults to NaNs maximal
private RandomData	randomData Source of random data - used only when ties strategy is RANDOM
private TiesStrategy	tiesStrategy Ties strategy - defaults to ties averaged

Constructor Summary

NaturalRanking()
Create a NaturalRanking with default strategies for handling ties and NaNs.

NaturalRanking(NaNStrategy nanStrategy)
Create a NaturalRanking with the given NaNStrategy.

NaturalRanking(NaNStrategy nanStrategy, RandomGenerator randomGenerator)
Create a NaturalRanking with the given NaNStrategy, TiesStrategy.RANDOM and the given source of random data.

NaturalRanking(NaNStrategy nanStrategy, TiesStrategy tiesStrategy)
Create a NaturalRanking with the given NaNStrategy and TiesStrategy.

NaturalRanking(RandomGenerator randomGenerator)
Create a NaturalRanking with TiesStrategy.RANDOM and the given RandomGenerator as the source of random data.

NaturalRanking(TiesStrategy tiesStrategy)
Create a NaturalRanking with the given TiesStrategy.

Method Summary

private boolean	containsNaNs(NaturalRanking.IntDoublePair[] ranks) Checks for presence of NaNs in ranks.
private void	fill(double[] data, List<Integer> tiesTrace, double value) Setsdata[i] = value for each i in tiesTrace.
private List<Integer>	getNanPositions(NaturalRanking.IntDoublePair[] ranks) Returns a list of indexes where ranks is NaN.
NaNStrategy	getNanStrategy() Return the NaNStrategy
TiesStrategy	getTiesStrategy() Return the TiesStrategy
double[]	rank(double[] data) Rank data using the natural ordering on Doubles, with NaN values handled according to nanStrategy and ties resolved using tiesStrategy.
private void	recodeNaNs(NaturalRanking.IntDoublePair[] ranks, double value) Recodes NaN values to the given value.
private NaturalRanking.IntDoublePair[]	removeNaNs(NaturalRanking.IntDoublePair[] ranks) Returns an array that is a copy of the input array with IntDoublePairs having NaN values removed.
private void	resolveTie(double[] ranks, List<Integer> tiesTrace) Resolve a sequence of ties, using the configured TiesStrategy.
private void	restoreNaNs(double[] ranks, List<Integer> nanPositions) Set ranks[i] = Double.NaN for each i in nanPositions.

Methods inherited from class java.lang.Object

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

Field Detail

DEFAULT_NAN_STRATEGY

public static final NaNStrategy DEFAULT_NAN_STRATEGY

default NaN strategy

DEFAULT_TIES_STRATEGY

public static final TiesStrategy DEFAULT_TIES_STRATEGY

default ties strategy

nanStrategy

private final NaNStrategy nanStrategy

NaN strategy - defaults to NaNs maximal

tiesStrategy

private final TiesStrategy tiesStrategy

Ties strategy - defaults to ties averaged

randomData

private final RandomData randomData

Source of random data - used only when ties strategy is RANDOM

Constructor Detail

NaturalRanking

public NaturalRanking()

Create a NaturalRanking with default strategies for handling ties and NaNs.

NaturalRanking

public NaturalRanking(TiesStrategy tiesStrategy)

Create a NaturalRanking with the given TiesStrategy.

Parameters:

tiesStrategy - the TiesStrategy to use

NaturalRanking

public NaturalRanking(NaNStrategy nanStrategy)

Create a NaturalRanking with the given NaNStrategy.

Parameters:

nanStrategy - the NaNStrategy to use

NaturalRanking

public NaturalRanking(NaNStrategy nanStrategy,
                      TiesStrategy tiesStrategy)

Create a NaturalRanking with the given NaNStrategy and TiesStrategy.

Parameters:

nanStrategy - NaNStrategy to use

tiesStrategy - TiesStrategy to use

NaturalRanking

public NaturalRanking(RandomGenerator randomGenerator)

Create a NaturalRanking with TiesStrategy.RANDOM and the given RandomGenerator as the source of random data.

Parameters:

randomGenerator - source of random data

NaturalRanking

public NaturalRanking(NaNStrategy nanStrategy,
                      RandomGenerator randomGenerator)

Create a NaturalRanking with the given NaNStrategy, TiesStrategy.RANDOM and the given source of random data.

Parameters:

nanStrategy - NaNStrategy to use

randomGenerator - source of random data

Method Detail

getNanStrategy

public NaNStrategy getNanStrategy()

Return the NaNStrategy

Returns:

returns the NaNStrategy

getTiesStrategy

public TiesStrategy getTiesStrategy()

Return the TiesStrategy

Returns:

the TiesStrategy

rank

public double[] rank(double[] data)

Rank data using the natural ordering on Doubles, with NaN values handled according to nanStrategy and ties resolved using tiesStrategy.

Specified by:

rank in interface RankingAlgorithm

Parameters:

data - array to be ranked

Returns:

array of ranks

removeNaNs

private NaturalRanking.IntDoublePair[] removeNaNs(NaturalRanking.IntDoublePair[] ranks)

Returns an array that is a copy of the input array with IntDoublePairs having NaN values removed.

Parameters:

ranks - input array

Returns:

array with NaN-valued entries removed

recodeNaNs

private void recodeNaNs(NaturalRanking.IntDoublePair[] ranks,
                        double value)

Recodes NaN values to the given value.

Parameters:

ranks - array to recode

value - the value to replace NaNs with

containsNaNs

private boolean containsNaNs(NaturalRanking.IntDoublePair[] ranks)

Checks for presence of NaNs in ranks.

Parameters:

ranks - array to be searched for NaNs

Returns:

true iff ranks contains one or more NaNs

resolveTie

private void resolveTie(double[] ranks,
                        List<Integer> tiesTrace)

Resolve a sequence of ties, using the configured TiesStrategy. The input ranks array is expected to take the same value for all indices in tiesTrace. The common value is recoded according to the tiesStrategy. For example, if ranks = <5,8,2,6,2,7,1,2>, tiesTrace = <2,4,7> and tiesStrategy is MINIMUM, ranks will be unchanged. The same array and trace with tiesStrategy AVERAGE will come out <5,8,3,6,3,7,1,3>.

Parameters:

ranks - array of ranks

tiesTrace - list of indices where ranks is constant -- that is, for any i and j in TiesTrace, ranks[i] == ranks[j]

fill

private void fill(double[] data,
                  List<Integer> tiesTrace,
                  double value)

Setsdata[i] = value for each i in tiesTrace.

Parameters:

data - array to modify

tiesTrace - list of index values to set

value - value to set

restoreNaNs

private void restoreNaNs(double[] ranks,
                         List<Integer> nanPositions)

Set ranks[i] = Double.NaN for each i in nanPositions.

Parameters:

ranks - array to modify

nanPositions - list of index values to set to Double.NaN

getNanPositions

private List<Integer> getNanPositions(NaturalRanking.IntDoublePair[] ranks)

Returns a list of indexes where ranks is NaN.

Parameters:

ranks - array to search for NaNs

Returns:

list of indexes i such that ranks[i] = NaN