Mapper to pass a dataset on to a set of mappers and combine there output.
Output combination or aggregation is currently done by hstacking or vstacking the resulting datasets.
Notes
Available conditional attributes:
(Conditional attributes enabled by default suffixed with +)
Parameters : | mappers : list combine_axis : [‘h’, ‘v’] enable_ca : None or list of str
disable_ca : None or list of str
auto_train : bool
force_train : bool
space: str, optional :
postproc : Node instance, optional
descr : str
|
---|
Examples
>>> import numpy as np
>>> from mvpa2.mappers.base import CombinedMapper
>>> from mvpa2.featsel.base import StaticFeatureSelection
>>> from mvpa2.datasets import Dataset
>>> mp = CombinedMapper([StaticFeatureSelection([1,2]),
... StaticFeatureSelection([2,3])],
... combine_axis='h')
>>> mp.is_trained = True
>>> ds = Dataset(np.arange(12).reshape(3,4))
>>> out = mp(ds)
>>> out.samples
array([[ 1, 2, 2, 3],
[ 5, 6, 6, 7],
[ 9, 10, 10, 11]])