def __init__(self, similarities, prototypes=None, **kwargs):
"""
Parameters
----------
similarities : list
A list of similarity functions.
prototypes : Dataset or list
A dataset or a list of instances (e.g., streamlines)?
**kwargs:
All keyword arguments are passed to the ProjectionMapper
constructor
"""
ProjectionMapper.__init__(self, **kwargs)
self.similarities = similarities
self.prototypes = prototypes
def __repr__(self):
s = ProjectionMapper.__repr__(self).rstrip(' )')
if not s[-1] == '(': s += ', '
s += "scaling=%d, reflection=%d, reduction=%d, " \
"oblique=%s, oblique_rcond=%g)" % \
(self._scaling, self._reflection, self._reduction,
self._oblique, self._oblique_rcond)
return s
def __repr__(self):
s = ProjectionMapper.__repr__(self).rstrip(' )')
if not s[-1] == '(': s += ', '
s += "scaling=%d, reflection=%d, reduction=%d, " \
"oblique=%s, oblique_rcond=%g)" % \
(self._scaling, self._reflection, self._reduction,
self._oblique, self._oblique_rcond)
return s
def __init__(self, **kwargs):
"""Initialize the SVDMapper
Parameters
----------
**kwargs:
All keyword arguments are passed to the ProjectionMapper
constructor.
Note, that for the 'selector' argument this class also supports
passing a `ElementSelector` instance, which will be used to
determine the to be selected features, based on the singular
values of each component.
"""
ProjectionMapper.__init__(self, **kwargs)
self._sv = None
"""Singular values of the training matrix."""
def __init__(self,
similarities,
prototypes=None,
**kwargs):
"""
Parameters
----------
similarities : list
A list of similarity functions.
prototypes : Dataset or list
A dataset or a list of instances (e.g., streamlines)?
**kwargs:
All keyword arguments are passed to the ProjectionMapper
constructor
"""
ProjectionMapper.__init__(self, **kwargs)
self.similarities = similarities
self.prototypes = prototypes
def __init__(self, **kwargs):
"""Initialize the SVDMapper
Parameters
----------
**kwargs:
All keyword arguments are passed to the ProjectionMapper
constructor.
Notes
-----
For the 'selector' argument this class also supports
passing a `ElementSelector` instance, which will be used to
determine the to be selected features, based on the singular
values of each component.
"""
ProjectionMapper.__init__(self, **kwargs)
self._sv = None
"""Singular values of the training matrix."""
def __init__(self,
scaling=True,
reflection=True,
reduction=True,
oblique=False,
oblique_rcond=-1,
**kwargs):
"""Initialize the ProcrusteanMapper
Parameters
----------
scaling : bool
Scale data for the transformation (no longer rigid body
transformation)
reflection : bool
Allow for the data to be reflected (so it might not be a rotation).
Effective only for non-oblique transformations
reduction : bool
If true, it is allowed to map into lower-dimensional
space. Forward transformation might be suboptimal then and reverse
transformation might not recover all original variance
oblique : bool
Either to allow non-orthogonal transformation -- might heavily overfit
the data if there is less samples than dimensions. Use `oblique_rcond`.
oblique_rcond : float
Cutoff for 'small' singular values to regularize the inverse. See
:class:`~numpy.linalg.lstsq` for more information.
**kwargs
To be passed to ProjectionMapper
"""
ProjectionMapper.__init__(self, **kwargs)
self._scaling = scaling
"""Either to determine the scaling factor"""
self._reduction = reduction
self._reflection = reflection
self._oblique = oblique
self._oblique_rcond = oblique_rcond
self._scale = None
"""Estimated scale"""
def __init__(self, scaling=True, reflection=True, reduction=True,
oblique=False, oblique_rcond=-1, **kwargs):
"""Initialize the ProcrusteanMapper
Parameters
----------
scaling : bool
Scale data for the transformation (no longer rigid body
transformation)
reflection : bool
Allow for the data to be reflected (so it might not be a rotation).
Effective only for non-oblique transformations
reduction : bool
If true, it is allowed to map into lower-dimensional
space. Forward transformation might be suboptimal then and reverse
transformation might not recover all original variance
oblique : bool
Either to allow non-orthogonal transformation -- might heavily overfit
the data if there is less samples than dimensions. Use `oblique_rcond`.
oblique_rcond : float
Cutoff for 'small' singular values to regularize the inverse. See
:class:`~numpy.linalg.lstsq` for more information.
**kwargs
To be passed to ProjectionMapper
"""
ProjectionMapper.__init__(self, **kwargs)
self._scaling = scaling
"""Either to determine the scaling factor"""
self._reduction = reduction
self._reflection = reflection
self._oblique = oblique
self._oblique_rcond = oblique_rcond
self._scale = None
"""Estimated scale"""
