nessai.proposal.importance ========================== .. py:module:: nessai.proposal.importance .. autoapi-nested-parse:: Proposals specifically for use with the importance based nested sampler. .. !! processed by numpydoc !! Classes ------- .. autoapisummary:: nessai.proposal.importance.ImportanceFlowProposal Module Contents --------------- .. py:class:: ImportanceFlowProposal(model: nessai.model.Model, output: str, rng: Optional[numpy.random.Generator] = None, flow_config: dict = None, training_config: dict = None, reparameterisation: str = 'logit', weighted_kl: bool = True, reset_flow: Union[bool, int] = True, clip: bool = False, plot_training: bool = False) Bases: :py:obj:`nessai.proposal.base.Proposal` Flow-based proposal for importance-based nested sampling. :Parameters: **model** : :obj:`nessai.model.Model` User-defined model. **rng** : :obj:`numpy.random.Generator`, optional Random number generator. If not provided, a new generator is created. **output** : str Output directory. **flow_config** : dict Configuration for the flow. **reparameterisation** : str Reparameterisation to use. If None, only the unit-hypercube reparameterisation is used. **weighted_kl** : bool If true, use the weights (prior / meta-proposal) when training the next flow. **rest_flow** : Union[bool, int] When to reset the flow. If False, the flow is not reset. If True the flow is reset every time a new flow is added. If an integer, every nth flow is reset. **clip** : bool If true the samples generated by flow will be clipped to [0, 1] before being mapped back from the unit-hypercube. This is only needed when the mapping cannot be defined outside of [0, 1]. In cases where it can, these points will be rejected when the prior bounds are checked. **plot_training** : bool If True, produce plots during training. If False, no plots are produced. .. !! processed by numpydoc !! .. py:property:: flow_config :type: dict Return the configuration for the flow .. !! processed by numpydoc !! .. py:property:: weights :type: dict Dictionary containing the weights for each proposal .. !! processed by numpydoc !! .. py:property:: weights_array :type: numpy.ndarray Array of weights for each proposal .. !! processed by numpydoc !! .. py:property:: n_proposals :type: int Current number of proposals in the meta proposal .. !! processed by numpydoc !! .. py:method:: initialise() Initialise the proposal .. !! processed by numpydoc !! .. py:method:: verify_rescaling(n: int = 1000, rtol: float = 1e-08, atol: float = 1e-08) -> None Verify the rescaling is invertible. Uses :code:`numpy.allclose`, see numpy documentation for more details. :Parameters: **n** : int Number of samples to test. **atol** : float The absolute tolerance. **rtol** : float The relative tolerance. .. !! processed by numpydoc !! .. py:method:: to_prime(x: numpy.ndarray) -> Tuple[numpy.ndarray, numpy.ndarray] Convert samples from the unit hypercube to samples in x'-space :Parameters: **x_prime** Unstructured array of samples in the unit hypercube :Returns: x Unstructured array of samples in x'-space log_j Corresponding log-Jacobian determinant. .. !! processed by numpydoc !! .. py:method:: from_prime(x_prime: numpy.ndarray) -> Tuple[numpy.ndarray, numpy.ndarray] Convert samples the x'-space to samples in the unit hypercube. :Parameters: **x_prime** Unstructured array of samples. :Returns: x Unstructured array of samples in the unit hypercube. log_j Corresponding log-Jacobian determinant. .. !! processed by numpydoc !! .. py:method:: rescale(x: numpy.ndarray) -> Tuple[numpy.ndarray, numpy.ndarray] Convert to the space in which the flow is trained. Returns an unstructured array. .. !! processed by numpydoc !! .. py:method:: inverse_rescale(x_prime: numpy.ndarray) -> numpy.ndarray Convert from the space in which the flow is trained. Returns a structured array. .. !! processed by numpydoc !! .. py:method:: update_proposal_weights(weights: dict) -> None Method to update the proposal weights dictionary. :Raises: RuntimeError If the weights do not sum to 1 are the update. .. !! processed by numpydoc !! .. py:method:: train(samples: numpy.ndarray, plot: bool = False, output: Union[str, None] = None, weights: numpy.ndarray = None, **kwargs) -> None Train the proposal with a set of samples. :Parameters: **samples** : numpy.ndarray Array of samples for training. **plot** : bool Flag to enable or disable plotting. **output** : Union[str, None] Output directory to use instead of default output. If None the default that was set when the class what initialised is used. **kwargs** Key-word arguments passed to :py:meth:`nessai.flowmodel.FlowModel.train`. .. !! processed by numpydoc !! .. py:method:: compute_log_Q(x_prime: numpy.ndarray, log_j: Optional[numpy.ndarray] = None) -> Tuple[numpy.ndarray, numpy.ndarray] Compute the log meta proposal (log Q) for an array of points. :Parameters: **x_prime** : numpy.ndarray Array of samples in the unit hypercube. **log_j** : Optional[numpy.ndarray] Log-Jacobian determinant of the prime samples. Must be supplied if proposal includes flows. :Returns: **log_Q** : numpy.ndarray Value of the meta-proposal in the prime space. **log_q** : numpy.ndarray Array of values for flow in the flow in the proposal. Array will have shape (# samples, # flows) .. !! processed by numpydoc !! .. py:method:: draw(n: int, flow_number: Optional[int] = None) -> Tuple[numpy.ndarray, numpy.ndarray] Draw n new points. :Parameters: **n** : int Number of points to draw. **flow_number** : Optional[int] Specifies which flow to use. If not specified the last flow will be used. :Returns: np.ndarray Array of new points. np.ndarray Log-proposal probabilities (log_q) .. !! processed by numpydoc !! .. py:method:: update_log_q(samples: numpy.ndarray, log_q: numpy.ndarray) -> numpy.ndarray Update the array of proposal probabilities for a set of samples .. !! processed by numpydoc !! .. py:method:: compute_meta_proposal_from_log_q(log_q) Compute the meta-proposal from an array of proposal log-probabilities .. !! processed by numpydoc !! .. py:method:: compute_meta_proposal_samples(samples: numpy.ndarray) -> numpy.ndarray Compute the meta proposal Q for a set of samples. Includes any rescaling that has been configured. :Returns: **log_meta_proposal** : numpy.ndarray Array of meta-proposal log probabilities (log Q) **log_q** : numpy.ndarray Array of log q for each flow. .. !! processed by numpydoc !! .. py:method:: get_proposal_log_prob(it: int) -> Callable Get a pointer to the function for ith proposal. .. !! processed by numpydoc !! .. py:method:: compute_kl_between_proposals(x: numpy.ndarray, p_it: Optional[int] = None, q_it: Optional[int] = None) -> float Compute the KL divergence between two proposals. Samples should be drawn from p. If proposals aren't specified the current and previous proposals are used. .. !! processed by numpydoc !! .. py:method:: draw_from_prior(n: int) -> Tuple[numpy.ndarray, numpy.ndarray] Draw from the prior .. !! processed by numpydoc !! .. py:method:: draw_from_flows(n: int, weights=None, counts=None) -> Tuple[numpy.ndarray, numpy.ndarray, numpy.ndarray] Draw n points from all flows (g). :Parameters: **n** : int Number of points **weights** Array of (normalised) weights. Ignored if counts is specified. **counts** Number of samples to draw from each proposal. .. !! processed by numpydoc !! .. py:method:: resume(model, flow_config, weights_path=None) Resume the proposal .. !! processed by numpydoc !!