mvpa2.mappers.base.ChainMapper

Inheritance diagram of ChainMapper

class mvpa2.mappers.base.ChainMapper(nodes, **kwargs)

Class that amends ChainNode with a mapper-like interface.

ChainMapper supports sequential training of a mapper chain, as well as reverse-mapping and mapping of single samples.

Notes

Available conditional attributes:

  • calling_time+: Time (in seconds) it took to call the node
  • raw_results: Computed results before invoking postproc. Stored only if postproc is not None.

(Conditional attributes enabled by default suffixed with +)

Methods

append(node) Append a node to the chain.
forward(ds)
forward1(data) Forward data or datasets through the chain.
generate(ds[, startnode])
Parameters:
get_postproc() Returns the post-processing node or None.
get_space() Query the processing space name of this node.
reset()
reverse(data) Reverse-maps data or datasets through the chain (backwards).
reverse1(data) Reverse-maps data or datasets through the chain (backwards).
set_postproc(node) Assigns a post-processing node
set_space(name) Set the processing space name of this node.
train(dataset) Train the mapper chain sequentially.
untrain() Untrain all embedded mappers.
Parameters :

nodes: list :

Node instances.

enable_ca : None or list of str

Names of the conditional attributes which should be enabled in addition to the default ones

disable_ca : None or list of str

Names of the conditional attributes which should be disabled

space: str, optional :

Name of the ‘processing space’. The actual meaning of this argument heavily depends on the sub-class implementation. In general, this is a trigger that tells the node to compute and store information about the input data that is “interesting” in the context of the corresponding processing in the output dataset.

postproc : Node instance, optional

Node to perform post-processing of results. This node is applied in __call__() to perform a final processing step on the to be result dataset. If None, nothing is done.

descr : str

Description of the instance

Methods

append(node) Append a node to the chain.
forward(ds)
forward1(data) Forward data or datasets through the chain.
generate(ds[, startnode])
Parameters:
get_postproc() Returns the post-processing node or None.
get_space() Query the processing space name of this node.
reset()
reverse(data) Reverse-maps data or datasets through the chain (backwards).
reverse1(data) Reverse-maps data or datasets through the chain (backwards).
set_postproc(node) Assigns a post-processing node
set_space(name) Set the processing space name of this node.
train(dataset) Train the mapper chain sequentially.
untrain() Untrain all embedded mappers.
forward(ds)
forward1(data)

Forward data or datasets through the chain.

See Mapper for more information.

reverse(data)

Reverse-maps data or datasets through the chain (backwards).

See Mapper for more information.

reverse1(data)

Reverse-maps data or datasets through the chain (backwards).

See Mapper for more information.

train(dataset)

Train the mapper chain sequentially.

The training dataset is used to train the first mapper. Afterwards it is forward-mapped by this (now trained) mapper and the transformed dataset and then used to train the next mapper. This procedure is done till all mappers are trained.

Parameters :dataset: `Dataset` :
untrain()

Untrain all embedded mappers.

NeuroDebian

NITRC-listed