rules_base.hh File Reference

#include <openmodeller/om.hh>
#include <openmodeller/Sample.hh>

Include dependency graph for rules_base.hh:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Classes
class	GarpRule

Enumerations
enum	PerfIndex {   PerfUtil = 0, PerfPrStr = 1, PerfPrProb = 2, PerfPrDist = 3,   PerfPostStr = 4, PerfPostProb = 5, PerfPostDist = 6, PerfCov = 7,   PerfSig = 8, PerfErr = 9 }
enum	RuleOrigin { OriginColonization = 0, OriginMutation = 1, OriginJoin = 2, OriginCrossover = 3 }
enum	RuleType {   VirtualRuleType = -1, RangeRuleType = 0, NegatedRuleType = 1, LogitRuleType = 2,   AtomicRuleType = 3 }

Functions
bool	equalEps (double v1, double v2)
bool	between (double value, double min, double max)
int	membership (double value1, double value2, double value)

Detailed Description

Declaration of GarpRule classe used in GARP

Author

Ricardo Scachetti Pereira (rpere.nosp@m.ira@.nosp@m.ku.ed.nosp@m.u)

Date

2004-04-01

Id:

rules_base.hh 1026 2005-06-23 20:28:29Z kruland

LICENSE INFORMATION

Copyright(c), The Center for Research, University of Kansas, 2385 Irving Hill Road, Lawrence, KS 66044-4755, USA. Copyright(c), David R.B. Stockwell of Symbiotik Pty. Ltd. Copyright(c), CRIA - Centro de Referencia em Informacao Ambiental

http://www.nhm.ku.edu

This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version.

This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details:

http://www.gnu.org/copyleft/gpl.html

This is an implementation of the GARP algorithm first developed by David Stockwell

Definition in file rules_base.hh.

Enumeration Type Documentation

enum PerfIndex

Enumerator
PerfUtil	Utility: main performance value. Default is significance.
PerfPrStr	pXs/n. This is the proportion of data points the rule applies to
PerfPrProb	Prior probability = pYs/n This is the proportion of the predicted class in the training set.
PerfPrDist	Prior distance = pYcs/n
PerfPostStr	Posterior strength = pXSs/no
PerfPostProb	Posterior probability = pXYs/no
PerfPostDist	Posterior distance = pYcXs/no
PerfCov	Coverage = no/n
PerfSig	Significance = (pXYs-no*pYs/n)/sqrt(no*pYs*(1-pYs/n)/n)
PerfErr	Error = Significance*sqrt( (pXYs/no)*(1-pXYs/no) )/no

Definition at line 42 of file rules_base.hh.

enum RuleOrigin

Enumerator
OriginColonization
OriginMutation
OriginJoin
OriginCrossover

Definition at line 89 of file rules_base.hh.

enum RuleType

Enumerator
VirtualRuleType
RangeRuleType
NegatedRuleType
LogitRuleType
AtomicRuleType

Definition at line 99 of file rules_base.hh.

Function Documentation

bool between	(	double	value,
		double	min,
		double	max
	)

Definition at line 67 of file rules_base.cpp.

Referenced by NegatedRangeRule::applies(), and RangeRule::applies().

bool equalEps	(	double	v1,
		double	v2
	)

Definition at line 62 of file rules_base.cpp.

Referenced by NegatedRangeRule::applies(), RangeRule::applies(), LogitRule::getStrength(), membership(), and GarpRule::similar().

int membership	(	double	value1,
		double	value2,
		double	value
	)

Definition at line 73 of file rules_base.cpp.

References equalEps().

Referenced by RangeRule::getStrength().

Here is the call graph for this function: