MatrixPredictor
- class remu.likelihood.MatrixPredictor(matrices, constants=0.0, *, sparse_indices=slice(None, None, None), **kwargs)[source]
Bases:
remu.likelihood.LinearEinsumPredictor
Predictor that uses a matrix to fold parameters into reco space.
output = matrix X parameters [+ constants]
- Parameters
- matricesndarray
Shape:
([n_systematics,]n_reco_bins,n_parameters)
- constantsndarray, optional
Shape:
([n_systematics,]n_reco_bins)
- weightsndarray, optional
Shape:
(n_systematics)
- boundsndarray, optional
Lower and upper bounds for all parameters. Can be
+/- np.inf
.- defaultsndarray, optional
“Reasonable” default values for the parameters. Used in optimisation.
- sparse_indiceslist or array of int, optional
Used with sparse matrices that provide only the specified columns. All other columns are assumed to be 0, i.e. the parameters corresponding to these have no effect.
See also
Attributes
bounds
(ndarray) Lower and upper bounds for all parameters. Can be
+/- np.inf
.defaults
(ndarray) “Reasonable” default values for the parameters. Used optimisation.
sparse_indices
(list or array of int or slice) Used with sparse matrices that provide only the specified columns. All other columns are assumed to be 0, i.e. the parameters corresponding to these have no effect.
Methods
__call__
(*args, **kwargs)See
prediction()
.check_bounds
(parameters)Check that all parameters are within bounds.
compose
(other)Return a new Predictor that is a composition with other.
fix_parameters
(fix_values)Return a new Predictor with fewer free parameters.
prediction
(parameters, *args, **kwargs)Turn a set of parameters into a reco prediction.
- check_bounds(parameters)
Check that all parameters are within bounds.
- compose(other)[source]
Return a new Predictor that is a composition with other.
new_predictor(parameters) = self(other(parameters))
- fix_parameters(fix_values)[source]
Return a new Predictor with fewer free parameters.
- Parameters
- fix_valuesiterable
List of the parameter values that the parameters should be fixed at. The list must be of the same length as the number of parameters of predictor. Any parameters that should remain unfixed should be specified with
None
ornp.nan
.
See also