Package mvpa :: Package mappers :: Module base :: Class CombinedMapper
[hide private]
[frames] | no frames]

Class CombinedMapper

source code


Meta mapper that combines several embedded mappers.

This mapper can be used the map from several input dataspaces into a common
output dataspace. When :meth:`~mvpa.mappers.base.CombinedMapper.forward`
is called with a sequence of data, each element in that sequence is passed
to the corresponding mapper, which in turned forward-maps the data. The
output of all mappers is finally stacked (horizontally or column or
feature-wise) into a single large 2D matrix (nsamples x nfeatures).

.. note::
  This mapper can only embbed mappers that transform data into a 2D
  (nsamples x nfeatures) representation. For mappers not supporting this
  transformation, consider wrapping them in a
  :class:`~mvpa.mappers.base.ChainMapper` with an appropriate
  post-processing mapper.

CombinedMapper fully supports forward and backward mapping, training,
runtime selection of a feature subset (in output dataspace) and retrieval
of neighborhood information.

Instance Methods [hide private]
 
__init__(self, mappers, **kwargs)
:Parameters: mappers: list of Mapper instances The order of the mappers in the list is important, as it will define the order in which data snippets have to be passed to :meth:`~mvpa.mappers.base.CombinedMapper.forward`.
source code
 
forward(self, data)
Map data from the IN spaces into to common OUT space.
source code
 
reverse(self, data)
Reverse map data from OUT space into the IN spaces.
source code
 
train(self, dataset)
Trains all embedded mappers.
source code
 
getInSize(self)
Returns the size of the entity in input space
source code
 
getOutSize(self)
Returns the size of the entity in output space
source code
 
selectOut(self, outIds)
Remove some elements and leave only ids in 'out'/feature space.
source code
 
getNeighbor(self, outId, *args, **kwargs)
Get the ids of the neighbors of a single feature in output dataspace.
source code
 
__repr__(self)
repr(x)
source code

Inherited from Mapper: __call__, getInId, getMetric, getNeighborIn, getNeighbors, isValidInId, isValidOutId, setMetric

Inherited from object: __delattr__, __format__, __getattribute__, __hash__, __new__, __reduce__, __reduce_ex__, __setattr__, __sizeof__, __str__, __subclasshook__

Class Variables [hide private]

Inherited from Mapper: metric, nfeatures

Properties [hide private]

Inherited from object: __class__

Method Details [hide private]

__init__(self, mappers, **kwargs)
(Constructor)

source code 

:Parameters:
  mappers: list of Mapper instances
    The order of the mappers in the list is important, as it will define
    the order in which data snippets have to be passed to
    :meth:`~mvpa.mappers.base.CombinedMapper.forward`.
  **kwargs
    All additional arguments are passed to the base-class constructor.

Parameters:
  • metric - Optional metric
Overrides: object.__init__

forward(self, data)

source code 
Map data from the IN spaces into to common OUT space.
Returns:
array: nsamples x nfeatures
Horizontally stacked array of all embedded mapper outputs.
Overrides: Mapper.forward

reverse(self, data)

source code 
Reverse map data from OUT space into the IN spaces.
Returns:
list
Overrides: Mapper.reverse

train(self, dataset)

source code 
Trains all embedded mappers.

The provided training dataset is splitted appropriately and the
corresponding pieces are passed to the
:meth:`~mvpa.mappers.base.Mapper.train` method of each embedded mapper.

:Parameter:
  dataset: :class:`~mvpa.datasets.base.Dataset` or subclass
    A dataset with the number of features matching the `outSize` of the
    `CombinedMapper`.

Overrides: Mapper.train

getInSize(self)

source code 
Returns the size of the entity in input space
Overrides: Mapper.getInSize

getOutSize(self)

source code 
Returns the size of the entity in output space
Overrides: Mapper.getOutSize

selectOut(self, outIds)

source code 

Remove some elements and leave only ids in 'out'/feature space.

The subset selection is done inplace
Parameters:
  • outIds, sequence - Subset of ids of the current feature in OUT space to keep.
Overrides: Mapper.selectOut

getNeighbor(self, outId, *args, **kwargs)

source code 

Get the ids of the neighbors of a single feature in output dataspace.

Returns a list of outIds

Overrides: Mapper.getNeighbor

Parameters:

outId: int
Single id of a feature in output space, whos neighbors should be determined.
*args, **kwargs
Additional arguments are passed to the metric of the embedded mapper, that is responsible for the corresponding feature.

__repr__(self)
(Representation operator)

source code 
repr(x)
Overrides: object.__repr__
(inherited documentation)