|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES All Classes | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectde.jstacs.classifiers.assessment.ClassifierAssessment
de.jstacs.classifiers.assessment.KFoldCrossValidation
public class KFoldCrossValidation
This class implements a k-fold crossvalidation. A k-fold crossvalidation assesses classifiers using the following methodology. The user supplies datasets (one for each class the classifiers are capable to distinguish). The data is randomly, mutually exclusive partitioned into k parts. Each of those parts is used once as a test dataset while the remaining k-1 parts are used as train dataset. In each of the k iterations, the train datasets are used to train the classifier and the test datasets are used to assess the classifier's performance to predict the elements therein. Additional the user has to define which assessment measures should be used.
Field Summary |
---|
Fields inherited from class de.jstacs.classifiers.assessment.ClassifierAssessment |
---|
myAbstractClassifier, myModel, myTempMeanResultSets, skipLastClassifiersDuringClassifierTraining |
Constructor Summary | |
---|---|
|
KFoldCrossValidation(AbstractClassifier... aCs)
Creates a new KFoldCrossValidation from a set of
AbstractClassifier s. |
|
KFoldCrossValidation(AbstractClassifier[] aCs,
boolean buildClassifiersByCrossProduct,
TrainableStatisticalModel[]... aMs)
This constructor allows to assess a collection of given AbstractClassifier s and those constructed using the given
TrainableStatisticalModel s by a KFoldCrossValidation
. |
protected |
KFoldCrossValidation(AbstractClassifier[] aCs,
TrainableStatisticalModel[][] aMs,
boolean buildClassifiersByCrossProduct,
boolean checkAlphabetConsistencyAndLength)
Creates a new KFoldCrossValidation from an array of
AbstractClassifier s and a two-dimensional array of TrainableStatisticalModel
s, which are combined to additional classifiers. |
|
KFoldCrossValidation(boolean buildClassifiersByCrossProduct,
TrainableStatisticalModel[]... aMs)
Creates a new KFoldCrossValidation from a set of TrainableStatisticalModel s. |
Method Summary | |
---|---|
ListResult |
assessWithPredefinedSplits(NumericalPerformanceMeasureParameterSet mp,
ClassifierAssessmentAssessParameterSet caaps,
ProgressUpdater pU,
DataSet[]... splitData)
This method implements a k-fold crossvalidation on previously split data. |
protected void |
evaluateClassifier(NumericalPerformanceMeasureParameterSet mp,
ClassifierAssessmentAssessParameterSet assessPS,
DataSet[] s,
ProgressUpdater pU)
Evaluates a classifier. |
Methods inherited from class de.jstacs.classifiers.assessment.ClassifierAssessment |
---|
assess, assess, assess, getClassifier, getNameOfAssessment, prepareAssessment, test, train |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Constructor Detail |
---|
protected KFoldCrossValidation(AbstractClassifier[] aCs, TrainableStatisticalModel[][] aMs, boolean buildClassifiersByCrossProduct, boolean checkAlphabetConsistencyAndLength) throws IllegalArgumentException, WrongAlphabetException, CloneNotSupportedException, ClassDimensionException
KFoldCrossValidation
from an array of
AbstractClassifier
s and a two-dimensional array of TrainableStatisticalModel
s, which are combined to additional classifiers. If
buildClassifiersByCrossProduct
is true
, the
cross-product of all TrainableStatisticalModel
s in aMs
is built to
obtain these classifiers.
aCs
- the predefined classifiersaMs
- the TrainableStatisticalModel
s that are used to build additional
classifiersbuildClassifiersByCrossProduct
- Determines how classifiers are constructed using the given
models. Suppose a k-class problem. In this case, each
classifier is supposed to consist of k models, one responsible
for each class. S_i
be the set of all models in
aMs[i]
. Let S
be the set
S_1 x S_2 x ... x S_k
(cross-product).true
: all possible classifiers consisting of a
subset (set of k models) of S
are constructed false
: one classifier consisting of the models
aMs[0][i]
,aMs[1][i]
,...,
aMs[k][i]
for a fixed i
is
constructed. In this case, all second dimensions of
aMs
have to be equal, say m
. In
total m
classifiers are constructed.checkAlphabetConsistencyAndLength
- indicates if alphabets and lengths shall be checked for
consistency
IllegalArgumentException
- if the classifiers have different lengths
WrongAlphabetException
- if the classifiers use different alphabets
CloneNotSupportedException
- if something went wrong while cloning
ClassDimensionException
- if there is something wrong with the class dimension of the
classifierClassifierAssessment.ClassifierAssessment(AbstractClassifier[],
TrainableStatisticalModel[][], boolean, boolean)
public KFoldCrossValidation(AbstractClassifier... aCs) throws IllegalArgumentException, WrongAlphabetException, CloneNotSupportedException, ClassDimensionException
KFoldCrossValidation
from a set of
AbstractClassifier
s.
aCs
- contains the classifiers to be assessed.assess( ... )
.s
in order (s[0]
contains foreground data, s[1]
contains
background data)
IllegalArgumentException
- if the classifiers have different lengths
WrongAlphabetException
- if not all given classifiers are defined on the same
AlphabetContainer
CloneNotSupportedException
- if something went wrong while cloning
ClassDimensionException
- if there is something wrong with the class dimension of the
classifierClassifierAssessment.ClassifierAssessment(AbstractClassifier...)
public KFoldCrossValidation(boolean buildClassifiersByCrossProduct, TrainableStatisticalModel[]... aMs) throws IllegalArgumentException, WrongAlphabetException, CloneNotSupportedException, ClassDimensionException
KFoldCrossValidation
from a set of TrainableStatisticalModel
s.
The argument buildClassifiersByCrossProduct
determines how
these TrainableStatisticalModel
s are combined to classifiers.
buildClassifiersByCrossProduct
- S_i
be the set of all models in
aMs[i]
. Let S
be the set
S_1 x S_2 x ... x S_k
(cross-product).true
: all possible classifiers consisting of a
subset (set of k models) of S
are constructed false
: one classifier consisting of the models
aMs[0][i]
,aMs[1][i]
,...,
aMs[k][i]
for a fixed i
is
constructed. In this case, all second dimensions of
aMs
have to be equal, say m
. In
total m
classifiers are constructed.aMs
- aMs[i]
) contains the
models according to class i
.s
... . s
in order (s[0]
contains foreground data, s[1]
contains
background data)
IllegalArgumentException
- if the classifiers have different lengths
WrongAlphabetException
- if not all given classifiers are defined on the same
AlphabetContainer
CloneNotSupportedException
- if something went wrong while cloning
ClassDimensionException
- if there is something wrong with the class dimension of the
classifierClassifierAssessment.ClassifierAssessment(boolean, TrainableStatisticalModel[][])
public KFoldCrossValidation(AbstractClassifier[] aCs, boolean buildClassifiersByCrossProduct, TrainableStatisticalModel[]... aMs) throws IllegalArgumentException, WrongAlphabetException, CloneNotSupportedException, ClassDimensionException
AbstractClassifier
s and those constructed using the given
TrainableStatisticalModel
s by a KFoldCrossValidation
.
aCs
- contains some AbstractClassifier
s that should be
assessed in addition to the AbstractClassifier
constructed using the given
TrainableStatisticalModel
sbuildClassifiersByCrossProduct
- S_i
be the set of all models in
aMs[i]
. Let S
be the set
S_1 x S_2 x ... x S_k
(cross-product).true
: all possible classifiers consisting of a
subset (set of k models) of S
are constructed false
: one classifier consisting of the models
aMs[0][i]
,aMs[1][i]
,...,
aMs[k][i]
for a fixed i
is
constructed. In this case, all second dimensions of
aMs
have to be equal, say m
. In
total m
classifiers are constructed.aMs
- aMs[i]
) contains the
models according to class i
.s
... . s
in order (s[0]
contains foreground data, s[1]
contains
background data)
IllegalArgumentException
- if the classifiers have different lengths
WrongAlphabetException
- if not all given classifiers are defined on the same
AlphabetContainer
CloneNotSupportedException
- if something went wrong while cloning
ClassDimensionException
- if there is something wrong with the class dimension of the
classifierClassifierAssessment.ClassifierAssessment(AbstractClassifier[],
boolean, TrainableStatisticalModel[][])
Method Detail |
---|
protected void evaluateClassifier(NumericalPerformanceMeasureParameterSet mp, ClassifierAssessmentAssessParameterSet assessPS, DataSet[] s, ProgressUpdater pU) throws IllegalArgumentException, Exception
evaluateClassifier
in class ClassifierAssessment
mp
- defines which performance measures are used to assess
classifierspU
- the progress updater which shows the progress of the k-fold
crossvalidations
- contains the data to be used for assessment. The order of
samples is important. s
. If
the models are trained directly, the order of the given models
during initiation of this assessment object determines, which
sample will be used for training which model. In general the
first model will be trained using the first sample in
s
... . s
in order (s[0]
contains foreground data, s[1]
contains
background data)
assessPS
- contains parameters for a run of this
KFoldCrossValidation
. Must be of type
KFoldCrossValidationAssessParameterSet
.
IllegalArgumentException
- if the given assessPS
is not of type
KFoldCrossValidationAssessParameterSet
Exception
- if something went wrongClassifierAssessment.evaluateClassifier(NumericalPerformanceMeasureParameterSet, ClassifierAssessmentAssessParameterSet, DataSet[], ProgressUpdater)
public ListResult assessWithPredefinedSplits(NumericalPerformanceMeasureParameterSet mp, ClassifierAssessmentAssessParameterSet caaps, ProgressUpdater pU, DataSet[]... splitData) throws Exception
mp
- defines which performance measures are used to assess
classifierscaaps
- contains the defined element length and choice whether an
exception should be thrown if a measure could not be computedpU
- the progress updater which shows the progress of the k-fold
crossvalidationsplitData
- the previously split data; splitData[i]
contains
the splits for class i
; therefore the length of
each subarray splitData[i]
has to to be identical
ListResult
Exception
- if something went wrong
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES All Classes | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |