pypomp.core.results.PompTrainResult

class pypomp.core.results.PompTrainResult(method: str, execution_time: float | None, key: Array, timestamp: Timestamp = <factory>, theta: PompParameters | None = None, traces_da: DataArray = <factory>, optimizer: Optimizer = <factory>, J: int = 0, M: int = 0, eta: LearningRate | None = None, alpha: float = 0.97, thresh: float = 0.0, alpha_cooling: float = 1.0)

Bases: PompEstimationTracesMixin, PompBaseResult

Result from Pomp.train() method.

Attributes

J: int = 0

The number of particles used for filtering.

M: int = 0

The number of iterations performed.

alpha: float = 0.97

The discount factor for the gradient moving average.

alpha_cooling: float = 1.0

The cooling factor for the discount factor.

eta: LearningRate | None = None

The learning rate object.

theta: PompParameters | None = None

The parameter object used for the computation.

thresh: float = 0.0

The resampling threshold used.

traces_da: DataArray

Log-likelihood and parameter traces across iterations. Dimensions: (“theta_idx”, “iteration”, “variable”)

optimizer: Optimizer

The optimizer used for training.

method: str

The name of the method that produced this result (e.g., ‘pfilter’, ‘mif’).

execution_time: float | None

Total execution time in seconds.

key: jax.Array

The JAX random key used for this execution.

timestamp: pd.Timestamp

The date and time when the result was created.

Methods

CLL([average])	Return conditional log-likelihoods as a DataFrame.
ESS([average])	Return Effective Sample Size as a DataFrame.
__init__(method, execution_time, key, ...)
merge(*results)	Merge multiple result objects of the same type.
print_summary([n])	Print a summary of this result.
to_dataframe([ignore_nan])	Convert result to DataFrame using traces_da.
traces()	Return traces DataFrame using traces_da.