Package mdp :: Package contrib :: Class ShogunSVMNode

Class ShogunSVMNode

The ShogunSVMNode works as a wrapper class for accessing the shogun library
for support vector machines.

Nested Classes

[hide private]

Inherited from Node

__metaclass__
This Metaclass is meant to overwrite doc strings of methods like execute, stop_training, inverse with the ones defined in the corresponding private methods _execute, _stop_training, _inverse, etc...

Instance Methods

[hide private]

__init__(self, classifier='libsvmmulticlass', classifier_options=None, kernel='GaussianKernel', kernel_options=None, num_threads='autodetect', input_dim=None, dtype=None)
Keyword arguments:

_get_classification_type(self)

_set_num_threads(self)

_stop_training(self)

classify(self, x)
Classify the input data 'x'...

set_classifier(self, name='libsvm')
Sets and initialises the classifier.

set_classifier_param(self, param, *value)
Sets parameters for the classifier.

set_kernel(self, name, options=None)
Sets the Kernel along with options.

training_set(self, ordered=False)
Shows the set of data that has been inserted to be trained.

Inherited from svm_nodes._SVMNode: is_invertible, train

Inherited from svm_nodes._SVMNode (private): _check_train_args, _normalize_labels, _set_input_dim, _set_output_dim, _train

Inherited from object: __delattr__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __setattr__

Inherited from Node

__add__(self, other)

__call__(self, x, *args, **kargs)
Calling an instance of Node is equivalent to call its 'execute' method.

__repr__(self)
repr(x)

__str__(self)
str(x)

_check_input(self, x)

_check_output(self, y)

_execute(self, x)

_get_supported_dtypes(self)
Return the list of dtypes supported by this node.

_get_train_seq(self)

_if_training_stop_training(self)

_inverse(self, x)

_pre_execution_checks(self, x)
This method contains all pre-execution checks.

_pre_inversion_checks(self, y)
This method contains all pre-inversion checks.

_refcast(self, x)
Helper function to cast arrays to the internal dtype.

_set_dtype(self, t)

copy(self, protocol=-1)
Return a deep copy of the node.

execute(self, x, *args, **kargs)
Process the data contained in 'x'.

get_current_train_phase(self)
Return the index of the current training phase.

get_dtype(self)
Return dtype.

get_input_dim(self)
Return input dimensions.

get_output_dim(self)
Return output dimensions.

get_remaining_train_phase(self)
Return the number of training phases still to accomplish.

get_supported_dtypes(self)
Return dtypes supported by the node as a list of numpy.dtype objects.

inverse(self, y, *args, **kargs)
Invert 'y'.

is_trainable(self)
Return True if the node can be trained, False otherwise.

is_training(self)
Return True if the node is in the training phase, False otherwise.

save(self, filename, protocol=-1)
Save a pickled serialization of the node to 'filename'.

set_dtype(self, t)
Set internal structures' dtype.

set_input_dim(self, n)
Set input dimensions.

set_output_dim(self, n)
Set output dimensions.

stop_training(self, *args, **kwargs)
Stop the training phase.

Class Variables

[hide private]

default_parameters = {'C': 1, 'epsilon': 0.001}

kernel_parameters = {'GaussianKernel': [('size', 10), ('width'...

Properties

[hide private]

Inherited from object: __class__

Inherited from Node

_train_seq
List of tuples: [(training-phase1, stop-training-phase1), (training-phase2, stop_training-phase2), ...

dtype
dtype

input_dim
Input dimensions

output_dim
Output dimensions

supported_dtypes
Supported dtypes

Method Details

[hide private]

init(self, classifier=`'libsvmmulticlass'`, classifier_options=None, kernel=`'GaussianKernel'`, kernel_options=None, num_threads=`'autodetect'`, input_dim=None, dtype=None)
(Constructor)


Keyword arguments:
    
    classifier  -- The classifier to use
    classifier_options -- Options for the classifier
    kernel      -- The kernel to use. Default parameters are specified for
                     "PolyKernel"
                     "GaussianKernel"
                     "LinearKernel"
                     "SigmoidKernel"
                    Further kernels are possible if they are included in shogun
                    and if kernel_options provides the correct init arguments.
    kernel_options -- For known kernels, a dict specifying the options is possible,
                   options not included take a default value.
                   Unknown kernels need an ordered list of constructor arguments.
    num_threads -- The number of threads, shogun should use
                   can be set to "autodetect", then shogun will use the number of cpu cores.
                   Attention: this could crash on windows

Overrides: object.__init__

_get_classification_type(self)

_set_num_threads(self)

_stop_training(self)

Overrides: Node._stop_training

classify(self, x)

Classify the input data 'x'

set_classifier(self, name=`'libsvm'`)

Sets and initialises the classifier. If a classifier is reset by the user, 
the parameters will have to be set again.
'name' can be a string, a subclass of shogun.Classifier or an instance of such
a class

set_classifier_param(self, param, *value)

Sets parameters for the classifier.

set_kernel(self, name, options=None)

Sets the Kernel along with options.

training_set(self, ordered=False)

Shows the set of data that has been inserted to be trained.

Class Variable Details

[hide private]

default_parameters

Value:

{'C': 1, 'epsilon': 0.001}

kernel_parameters

Value:

{'GaussianKernel': [('size', 10), ('width', 1)],
 'LinearKernel': [],
 'PolyKernel': [('size', 10), ('degree', 3), ('inhomogene', True)],
 'SigmoidKernel': [('size', 10), ('gamma', 1), ('coef0', 0)]}

Class ShogunSVMNode

__init__(self, classifier='libsvmmulticlass', classifier_options=None, kernel='GaussianKernel', kernel_options=None, num_threads='autodetect', input_dim=None, dtype=None) (Constructor)

_get_classification_type(self)

_set_num_threads(self)

_stop_training(self)

classify(self, x)

set_classifier(self, name='libsvm')

set_classifier_param(self, param, *value)

set_kernel(self, name, options=None)

training_set(self, ordered=False)

default_parameters

kernel_parameters

init(self, classifier=`'libsvmmulticlass'`, classifier_options=None, kernel=`'GaussianKernel'`, kernel_options=None, num_threads=`'autodetect'`, input_dim=None, dtype=None)
(Constructor)

set_classifier(self, name=`'libsvm'`)