mvpa2.algorithms.hyperalignment

Transformation of individual feature spaces into a common space

The Hyperalignment class in this module implements an algorithm published in Haxby et al., Neuron (2011) A common, high-dimensional model of the representational space in human ventral temporal cortex.

Functions

Doi(\*args, \*\*kwargs)	Perform no good and no bad
deepcopy(x[, memo, _nil])	Deep copy operation on arbitrary Python objects.
expand_contraint_spec(spec)	Helper to translate literal contraint specs into functional ones
get_trained_mapper(ds, commonspace, mapper)	Trains a given mapper using dataset and commonspace and computes residuals if necessary.
mean_axis0(a)
mean_xy(x, y[, weights])
zscore(ds, \*\*kwargs)	In-place Z-scoring of a Dataset or ndarray.

Classes

AltConstraints(\*constraints)	Logical OR for constraints.
ChainMapper(nodes, \*\*kwargs)	Class that amends ChainNode with a mapper-like interface.
ClassWithCollections([descr])	Base class for objects which contain any known collection
ConditionalAttribute([enabled])	Simple container intended to conditionally store the value
Constraint	Base class for input value conversion/validation.
Constraints(\*constraints)	Logical AND for constraints.
Dataset(samples[, sa, fa, a])	Generic storage class for datasets with multiple attributes.
EnsureBool	Ensure that an input is a bool.
EnsureChoice(\*values)	Ensure an input is element of a set of possible values
EnsureDType(dtype)	Ensure that an input (or several inputs) are of a particular data type.
EnsureFloat()	Ensure that an input (or several inputs) are of a data type ‘float’.
EnsureInt()	Ensure that an input (or several inputs) are of a data type ‘int’.
EnsureListOf(dtype)	Ensure that an input is a list of a particular data type
EnsureNone	Ensure an input is of value None
EnsureRange([min, max])	Ensure an input is within a particular range
EnsureStr	Ensure an input is a string.
EnsureTupleOf(dtype)	Ensure that an input is a tuple of a particular data type
Hyperalignment(\*\*kwargs)	Align the features across multiple datasets into a common feature space.
Parameter(default[, constraints, ro, index, ...])	This class shall serve as a representation of a parameter.
ProcrusteanMapper([space])	Mapper to project from one space to another using Procrustean transformation (shift + scaling + rotation).
SVDMapper(\*\*kwargs)	Mapper to project data onto SVD components estimated from some dataset.
StaticProjectionMapper(proj[, recon])	Mapper to project data onto arbitrary space using transformation given as input.
ZScoreMapper([params, param_est, ...])	Mapper to normalize features (Z-scoring).