pyuncertainnumber.propagation.cauchy_deviate

Functions

cauchy_deviate_method(→ pyuncertainnumber.Interval)

Cauchy Deviate Method for interval propagation

cauchy_deviate_raw(→ tuple)

Raw implementation of the Cauchy Deviate Method

Module Contents

pyuncertainnumber.propagation.cauchy_deviate.cauchy_deviate_method(func, input_vector_interval: list[pyuncertainnumber.Interval], n_sam: int = 200) → pyuncertainnumber.Interval

Cauchy Deviate Method for interval propagation

Parameters:

  • func – The function, vectorised style, to be evaluated.

  • input_vector_interval – The input vector of intervals.

  • n_sam – The number of samples to draw from each Cauchy distribution.

Note

The function must be vectorised, i.e. it must be able to take in a 2D array of shape (n, d) and return a 1D array of shape (n,).

pyuncertainnumber.propagation.cauchy_deviate.cauchy_deviate_raw(func, nominal_measurement: numpy.ndarray, scalar_param: numpy.ndarray, n_sam: int = 200) → tuple

Raw implementation of the Cauchy Deviate Method

Parameters:

  • func – The function, vectorised style, to be evaluated.

  • nominal_measurement – The nominal measurement values, i.e. x tilda.

  • scalar_param – The scalar parameters for each component Cauchy distribution, i.e. Delta.

  • n_sam – The number of samples to draw from each Cauchy distribution.

Returns:

mean_y and Delta_y