Home       Trees       Indices       Help   
PyMVPA: Python MultiVariate Pattern Analysis
Package mvpa :: Package clfs :: Module gpr :: Class GPR
[hide private]
[frames] | no frames]

Class GPR

source code

Gaussian Process Regression (GPR).
Nested Classes [hide private]

Inherited from misc.state.ClassWithCollections: __metaclass__

Instance Methods [hide private]
 
__init__(self, kernel=None, **kwargs)
Initialize a GPR regression analysis.		 source code
 
_init_internals(self)
Reset some internal variables to None.		 source code
 
__repr__(self)
String summary of the object		 source code
 
compute_log_marginal_likelihood(self)
Compute log marginal likelihood using self.train_fv and self.labels.		 source code
 
compute_gradient_log_marginal_likelihood(self)
Compute gradient of the log marginal likelihood. This version use a more compact formula provided by Williams and Rasmussen book.		 source code
 
compute_gradient_log_marginal_likelihood_logscale(self)
Compute gradient of the log marginal likelihood when hyperparameters are in logscale. This version use a more compact formula provided by Williams and Rasmussen book.		 source code
 
getSensitivityAnalyzer(self, flavor='auto', **kwargs)
Returns a sensitivity analyzer for GPR.		 source code
 
_train(self, data)
Train the classifier using data (Dataset).		 source code
 
_predict(self, data)
Predict the output for the provided data.		 source code
 
_setRetrainable(self, value, force=False)
Internal function : need to set _km_test_test		 source code
 
untrain(self)
Reset trained state		 source code
 
set_hyperparameters(self, hyperparameter)
Set hyperparameters' values.		 source code

Inherited from base.Classifier: __str__, clone, isTrained, predict, repredict, retrain, summary, train, trained

Inherited from base.Classifier (private): _getFeatureIds, _postpredict, _posttrain, _prepredict, _pretrain, _regressionIsBogus

Inherited from misc.state.ClassWithCollections: __getattribute__, __new__, __setattr__, reset

Inherited from object: __delattr__, __format__, __hash__, __reduce__, __reduce_ex__, __sizeof__, __subclasshook__

Class Variables [hide private]
  predicted_variances = StateVariable(enabled= False, doc= "Vari...
  log_marginal_likelihood = StateVariable(enabled= False, doc= "...
  log_marginal_likelihood_gradient = StateVariable(enabled= Fals...
  _clf_internals = ['gpr', 'regression', 'retrainable']
Describes some specifics about the classifier -- is that it is doing regression for instance....
  sigma_noise = Parameter(0.001, allowedtype= 'float', min= 1e-1...
  lm = Parameter(0.0, min= 0.0, allowedtype= 'float', doc= """Th...
  kernel = property(fget= lambda self: self.__kernel)

Inherited from base.Classifier: _DEV__doc__, feature_ids, predicting_time, predictions, regression, retrainable, trained_dataset, trained_labels, trained_nsamples, training_confusion, training_time, values

Inherited from misc.state.ClassWithCollections: descr

Properties [hide private]

Inherited from object: __class__

Method Details [hide private]

__init__(self, kernel=None, **kwargs)
(Constructor)

source code 
Initialize a GPR regression analysis.
Parameters:
  • kernel (Kernel) - a kernel object defining the covariance between instances. (Defaults to KernelSquaredExponential if None in arguments)
Overrides: object.__init__

_init_internals(self)

source code 

Reset some internal variables to None.

To be used in constructor and untrain()

__repr__(self)
(Representation operator)

source code 
String summary of the object
Parameters:
  • fullname - Either to include full name of the module
  • prefixes - What other prefixes to prepend to list of arguments
Overrides: object.__repr__

getSensitivityAnalyzer(self, flavor='auto', **kwargs)

source code 
Returns a sensitivity analyzer for GPR.
Parameters:
  • flavor (basestring) - What sensitivity to provide. Valid values are 'linear', 'model_select', 'auto'. In case of 'auto' selects 'linear' for linear kernel and 'model_select' for the rest. 'linear' corresponds to GPRLinearWeights and 'model_select' to GRPWeights
Overrides: base.Classifier.getSensitivityAnalyzer

_train(self, data)

source code 
Train the classifier using data (Dataset).
Overrides: base.Classifier._train

_predict(self, data)

source code 
Predict the output for the provided data.
Overrides: base.Classifier._predict

_setRetrainable(self, value, force=False)

source code 
Internal function : need to set _km_test_test
Overrides: base.Classifier._setRetrainable

untrain(self)

source code 
Reset trained state
Overrides: base.Classifier.untrain
(inherited documentation)

set_hyperparameters(self, hyperparameter)

source code 

Set hyperparameters' values.

Note that 'hyperparameter' is a sequence so the order of its values is important. First value must be sigma_noise, then other kernel's hyperparameters values follow in the exact order the kernel expect them to be.


Class Variable Details [hide private]

predicted_variances

Value:
StateVariable(enabled= False, doc= "Variance per each predicted value"\
)

log_marginal_likelihood

Value:
StateVariable(enabled= False, doc= "Log Marginal Likelihood")

log_marginal_likelihood_gradient

Value:
StateVariable(enabled= False, doc= "Log Marginal Likelihood Gradient")

sigma_noise

Value:
Parameter(0.001, allowedtype= 'float', min= 1e-10, doc= "the standard \
deviation of the gaussian noise.")

lm

Value:
Parameter(0.0, min= 0.0, allowedtype= 'float', doc= """The regularizat\
ion term lambda.
                   Increase this when the kernel matrix is not positiv\
e, definite.""")

   Home       Trees       Indices       Help   
PyMVPA: Python MultiVariate Pattern Analysis
Generated by Epydoc 3.0.1 on Tue Jun 25 14:50:46 2013 http://epydoc.sourceforge.net