Package mdp :: Class ClassifierNode

NodeMetaclass ClassifierNode

Known Subclasses:

ClassifierCumulator

A ClassifierNode can be used for classification tasks that should not
interfere with the normal execution flow. A reason for that is that the
labels used for classification do not form a vector space, and so they don't
make much sense in a flow.

Instance Methods

[hide private]

__init__(self, execute_method=None, input_dim=None, output_dim=None, dtype=None)
Initialize classifier.

_execute(self, x)

_label(self, x, *args, **kargs)

_prob(self, x, *args, **kargs)

execute(self, x)
Process the data contained in `x`.

label(self, x, *args, **kwargs)
Returns an array with best class labels.

prob(self, x, *args, **kwargs)
Returns the probability for each datapoint and label (e.g., [{1:0.1, 2:0.0, 3:0.9}, {1:1.0, 2:0.0, 3:0.0}, ...])

rank(self, x, threshold=None)
Returns ordered list with all labels ordered according to prob(x) (e.g., [[3 1 2], [2 1 3], ...]).

Inherited from PreserveDimNode (private): _set_input_dim, _set_output_dim

Inherited from unreachable.newobject: __long__, __native__, __nonzero__, __unicode__, next

Inherited from Node

__add__(self, other)

__call__(self, x, *args, **kwargs)
Calling an instance of `Node` is equivalent to calling its `execute` method.

__repr__(self)

__str__(self)

_check_input(self, x)

_check_output(self, y)

_check_train_args(self, x, *args, **kwargs)

_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)

_stop_training(self, *args, **kwargs)

_train(self, x)

copy(self, protocol=None)
Return a deep copy of the node.

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.

has_multiple_training_phases(self)
Return True if the node has multiple training phases.

inverse(self, y, *args, **kwargs)
Invert `y`.

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.

train(self, x, *args, **kwargs)
Update the internal structures according to the input data `x`.

Static Methods

[hide private]

Inherited from Node

is_invertible()
Return True if the node can be inverted, False otherwise.

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

Properties

[hide private]

Inherited from Node

_train_seq
List of tuples::

dtype
dtype

input_dim
Input dimensions

output_dim
Output dimensions

supported_dtypes
Supported dtypes

Method Details

[hide private]

init(self, execute_method=None, input_dim=None, output_dim=None, dtype=None)
(Constructor)

Initialize classifier.

execute_method -- Set to string value 'label', 'rank', or 'prob' to
    force the corresponding classification method being used instead
    of the standard identity execution (which is used when
    execute_method has the default value None). This can be used when
    the node is last in a flow, the return value from Flow.execute
    will then consist of the classification results.

Overrides: Node.__init__

_execute(self, x)

Overrides: Node._execute

_label(self, x, *args, **kargs)

_prob(self, x, *args, **kargs)

execute(self, x)

Process the data contained in `x`.

If the object is still in the training phase, the function
`stop_training` will be called.
`x` is a matrix having different variables on different columns
and observations on the rows.

By default, subclasses should overwrite `_execute` to implement
their execution phase. The docstring of the `_execute` method
overwrites this docstring.

Overrides: Node.execute

label(self, x, *args, **kwargs)

Returns an array with best class labels.

By default, subclasses should overwrite _label to implement
their label. The docstring of the '_label' method
overwrites this docstring.

prob(self, x, *args, **kwargs)

Returns the probability for each datapoint and label
(e.g., [{1:0.1, 2:0.0, 3:0.9}, {1:1.0, 2:0.0, 3:0.0}, ...])

By default, subclasses should overwrite _prob to implement
their prob. The docstring of the '_prob' method
overwrites this docstring.

rank(self, x, threshold=None)

Returns ordered list with all labels ordered according to prob(x)
(e.g., [[3 1 2], [2 1 3], ...]).

The optional threshold parameter is used to exclude labels having equal
or less probability. E.g. threshold=0 excludes all labels with zero
probability.

NodeMetaclass ClassifierNode

__init__(self, execute_method=None, input_dim=None, output_dim=None, dtype=None) (Constructor)

_execute(self, x)

_label(self, x, *args, **kargs)

_prob(self, x, *args, **kargs)

execute(self, x)

label(self, x, *args, **kwargs)

prob(self, x, *args, **kwargs)

rank(self, x, threshold=None)

init(self, execute_method=None, input_dim=None, output_dim=None, dtype=None)
(Constructor)