Skip to main content

emulators.results

emulators.results

EmulationResults class for standardized emulator output handling.

Classes

Name Description
EmulationResults Standardized container for emulator prediction results.
PredictionBounds Cheap bounds on what predict would return, for screening candidates.

EmulationResults

emulators.results.EmulationResults(mean, std, additional_data=None, index=None)

Standardized container for emulator prediction results.

Provides clean access to mean and standard deviation predictions, with optional additional data for emulator-specific outputs.

Methods

Name Description
get_additional_data Get additional emulator-specific data.
get_ci Get confidence intervals assuming normal distribution.
get_mean Get predicted means.
get_std Get predicted standard deviations.
get_variance Get predicted variances (computed from std).
get_additional_data
emulators.results.EmulationResults.get_additional_data()

Get additional emulator-specific data.

get_ci
emulators.results.EmulationResults.get_ci(confidence_level=0.95)

Get confidence intervals assuming normal distribution.

Parameters
Name Type Description Default
confidence_level float Confidence level (0.95 = 95%) 0.95
Returns
Name Type Description
Tuple[pd.Series, pd.Series] Tuple of (lower_bound, upper_bound) Series
get_mean
emulators.results.EmulationResults.get_mean()

Get predicted means.

get_std
emulators.results.EmulationResults.get_std()

Get predicted standard deviations.

get_variance
emulators.results.EmulationResults.get_variance()

Get predicted variances (computed from std).

PredictionBounds

emulators.results.PredictionBounds()

Cheap bounds on what predict would return, for screening candidates.

Returned by BaseEmulator.predict_bounds. At every point, the mean predict(x).get_mean() lies within mean ± mean_tol and the variance predict(x).get_variance() lies within [var_lo, var_hi]. All four are arrays of shape (len(x),).