Table Of Contents

Previous topic

mvpa.mappers.pca

Next topic

mvpa.mappers.svd

This Page

Quick search

mvpa.mappers.samplegroup

Data mapper

The comprehensive API documentation for this module, including all technical details, is available in the Epydoc-generated API reference for mvpa.mappers.samplegroup (for developers).

SampleGroupMapper

class mvpa.mappers.samplegroup.SampleGroupMapper(fx=<function FirstAxisMean at 0x8d1be2c>)

Bases: mvpa.mappers.base.Mapper

Mapper to apply a mapping function to samples of the same type.

A customimzable function is applied individually to all samples with the same unique label from the same chunk. This mapper is somewhat unconventional since it doesn’t preserve number of samples (ie the size of 0-th dimension...)

Initialize the PCAMapper

Parameters:
startpoints: A sequence of index value along the first axis of
‘data’.
boxlength: The number of elements after ‘startpoint’ along the
first axis of ‘data’ to be considered for averaging.
offset: The offset between the starting point and the
averaging window (boxcar).
collision_resolution : string
if a sample belonged to multiple output samples, then on reverse, how to resolve the value (choices: ‘mean’)
forward(data)
getInSize()
Returns the number of original samples which were combined.
getOutSize()
Returns the number of output samples.
reverse(data)
This is not implemented.
selectOut(outIds)
Just complain for now
train(dataset)

See also

Derived classes might provide additional methods via their base classes. Please refer to the list of base classes (if it exists) at the begining of the SampleGroupMapper documentation.

Full API documentation of SampleGroupMapper in module mvpa.mappers.samplegroup.