nessai.reparameterisations.rescale ================================== .. py:module:: nessai.reparameterisations.rescale .. autoapi-nested-parse:: Reparameterisations that rescale the parameters. .. !! processed by numpydoc !! Classes ------- .. autoapisummary:: nessai.reparameterisations.rescale.PrePostRescalingMixin nessai.reparameterisations.rescale.ScaleAndShift nessai.reparameterisations.rescale.Rescale nessai.reparameterisations.rescale.RescaleToBounds Module Contents --------------- .. py:class:: PrePostRescalingMixin Mixin that adds support for pre- and post-rescaling functions .. !! processed by numpydoc !! .. py:method:: configure_pre_rescaling(pre_rescaling) Configure the rescaling applied before the standard rescaling. :Parameters: **pre_rescaling** : str or Tuple[Callable, Callable] Name of the pre-rescaling of tuple contain the forward and inverse functions that should return the rescaled value and the Jacobian. .. !! processed by numpydoc !! .. py:method:: configure_post_rescaling(post_rescaling) Configure the rescaling applied after the standard rescaling. Used to apply the logit/sigmoid transforms after rescaling to [0, 1] :Parameters: **post_rescaling** : str or Tuple[Callable, Callable] Name of the post-rescaling of tuple contain the forward and inverse functions that should return the rescaled value and the Jacobian. .. !! processed by numpydoc !! .. py:method:: pre_rescaling(x) Function applied before rescaling to bounds .. !! processed by numpydoc !! .. py:method:: pre_rescaling_inv(x) Inverse of function applied before rescaling to bounds .. !! processed by numpydoc !! .. py:method:: post_rescaling(x) Function applied after rescaling to bounds .. !! processed by numpydoc !! .. py:method:: post_rescaling_inv(x) Inverse of function applied after rescaling to bounds .. !! processed by numpydoc !! .. py:class:: ScaleAndShift(parameters=None, prior_bounds=None, scale=None, shift=None, estimate_scale=False, estimate_shift=False, pre_rescaling=None, post_rescaling=None, rng=None) Bases: :py:obj:`PrePostRescalingMixin`, :py:obj:`nessai.reparameterisations.base.Reparameterisation` Reparameterisation that shifts and scales by a value. Applies .. math:: x' = (x - shift) / scale Can apply the Z-score rescaling if :code:`estimate_scale` and :code:`estimate_shift` are both enabled. The values are initialised to one and zero respectively. :Parameters: **parameters** : Union[str, List[str]] Name of parameters to reparameterise. **prior_bounds** : list, dict or None Prior bounds for the parameter(s). **scale** : Optional[float] Scaling constant. If not specified, :code:`estimate_scale` must be True. **shift** : Optional[float] Shift constant. If not specified, no shift is applied. **estimate_scale** : bool If true, the value of :code:`scale` will be ignored and the standard deviation of the data will be used. **estimate_shift** : bool If true, the value of :code:`shift` will be ignored and the standard deviation of the data will be used. **pre_rescaling** : tuple of functions or str A function that applies a rescaling prior to the main rescaling and its inverse. Each function should return a value and the log-Jacobian determinant. Alternatively, can be the name of a known rescaling. **post_rescaling** : tuple of functions or str A function that applies a rescaling after to the main rescaling and its inverse. Each function should return a value and the log-Jacobian determinant. Alternatively, can be the name of a known rescaling .. !! processed by numpydoc !! .. py:method:: reparameterise(x, x_prime, log_j, **kwargs) Apply the reparameterisation to convert from x-space to x'-space :Parameters: **x** : structured array Array **x_prime** : structured array Array to be update **log_j** : Log jacobian to be updated .. .. !! processed by numpydoc !! .. py:method:: inverse_reparameterise(x, x_prime, log_j, **kwargs) Apply the reparameterisation to convert from x-space to x'-space :Parameters: **x** : structured array Array **x_prime** : structured array Array to be update **log_j** : Log jacobian to be updated .. .. !! processed by numpydoc !! .. py:method:: update(x) Update the scale and shift parameters if enabled. .. !! processed by numpydoc !! .. py:method:: reset() Reset the scale and shift parameters .. !! processed by numpydoc !! .. py:class:: Rescale(parameters=None, prior_bounds=None, scale=None, shift=None, estimate_scale=False, estimate_shift=False, pre_rescaling=None, post_rescaling=None, rng=None) Bases: :py:obj:`ScaleAndShift` Reparameterisation that rescales the parameters by a constant factor that does not depend on the prior bounds. .. !! processed by numpydoc !! .. py:class:: RescaleToBounds(parameters=None, prior_bounds=None, prior=None, rescale_bounds=None, boundary_inversion=None, detect_edges=False, inversion_type='split', detect_edges_kwargs=None, offset=False, update_bounds=True, pre_rescaling=None, post_rescaling=None, rng=None) Bases: :py:obj:`PrePostRescalingMixin`, :py:obj:`nessai.reparameterisations.base.Reparameterisation` Reparameterisation that maps to the specified interval. By default the interval is [-1, 1]. Also includes options for boundary inversion. This reparameterisation can handle multiple parameters. :Parameters: **parameters** : list of str List of the names of parameters **prior_bounds** : dict Dictionary of prior bounds for each parameter. Does not need to be specified by the user. **rescale_bounds** : list of tuples, optional Bounds to rescale to. **update_bounds** : bool, optional Enable or disable updating bounds. **prior** : {'uniform', None} Type of prior used, if uniform prime prior is enabled. **boundary_inversion** : bool, list, dict, optional Configuration for boundary inversion. If a list, inversion is only applied to the parameters in the list based on `inversion_type`. If a `dict` then each item should be a parameter and a corresponding inversion type `{'split', 'inversion'}`. **detect_edges** : bool, optional Enable or disable edge detection for inversion. **detect_edges_kwargs** : dict, optional Dictionary of kwargs used to configure edge detection. **offset** : bool, optional Enable or disable offset subtraction. If `True` then the mean value of the prior is subtract of the parameter before the rescaling is applied. This is computed and applied after the 'pre-rescaling' if it has been specified. **pre_rescaling** : tuple of functions A function that applies a rescaling prior to the main rescaling and its inverse. Each function should return a value and the log-Jacobian determinant. **post_rescaling** : tuple of functions or {'logit} A function that applies a rescaling after to the main rescaling and its inverse. Each function should return a value and the log-Jacobian determinant. For example applying a logit after rescaling to [0, 1]. .. !! processed by numpydoc !! .. py:method:: configure_post_rescaling(post_rescaling) Configure the rescaling applied after the standard rescaling. Used to apply the logit/sigmoid transforms after rescaling to [0, 1] :Parameters: **post_rescaling** : str or Tuple[Callable, Callable] Name of the post-rescaling of tuple contain the forward and inverse functions that should return the rescaled value and the Jacobian. .. !! processed by numpydoc !! .. py:method:: pre_rescaling(x) Function applied before rescaling to bounds .. !! processed by numpydoc !! .. py:method:: pre_rescaling_inv(x) Inverse of function applied before rescaling to bounds .. !! processed by numpydoc !! .. py:method:: post_rescaling(x) Function applied after rescaling to bounds .. !! processed by numpydoc !! .. py:method:: post_rescaling_inv(x) Inverse of function applied after rescaling to bounds .. !! processed by numpydoc !! .. py:method:: reparameterise(x, x_prime, log_j, compute_radius=False, **kwargs) Rescale inputs to the prime space :Parameters: **x, x_prime** : array_like Arrays of samples in the physical and prime space **log_j** : array_like Array of values of log-Jacobian **compute_radius** : bool, optional If true force duplicate for inversion **kwargs** Parsed to inversion function .. !! processed by numpydoc !! .. py:method:: inverse_reparameterise(x, x_prime, log_j, **kwargs) Map inputs to the physical space from the prime space .. !! processed by numpydoc !! .. py:method:: reset_inversion() Reset the edges for inversion .. !! processed by numpydoc !! .. py:method:: set_bounds(prior_bounds) Set the initial bounds for rescaling .. !! processed by numpydoc !! .. py:method:: update_bounds(x) Update the bounds used for the reparameterisation .. !! processed by numpydoc !! .. py:method:: update(x) Update the reparameterisation given some points. Includes resetting the inversions and updating the bounds. .. !! processed by numpydoc !! .. py:method:: reset() Reset the reparameterisation. Resets the inversion and the bounds. .. !! processed by numpydoc !!