surv_lime: Helper functions for 'predict_parts.R'

In survex: Explainable Machine Learning in Survival Analysis

Helper functions for predict_parts.R

Description

Helper functions for predict_parts.R

Usage

surv_lime(
  explainer,
  new_observation,
  ...,
  N = 100,
  distance_metric = "euclidean",
  kernel_width = NULL,
  sampling_method = "gaussian",
  sample_around_instance = TRUE,
  max_iter = 10000,
  categorical_variables = NULL,
  k = 1 + 1e-04
)

Arguments

explainer	an explainer object - model preprocessed by the explain() function
new_observation	a new observation for which predictions need to be explained
...	additional parameters, passed to internal functions
N	a positive integer, number of observations generated in the neighbourhood
distance_metric	character, name of the distance metric to be used, only "euclidean" is implemented
kernel_width	a numeric, parameter used for calculating weights, by default it's sqrt(ncol(data)*0.75)
sampling_method	character, name of the method of generating neighbourhood, only "gaussian" is implemented
sample_around_instance	logical, if the neighbourhood should be generated with the new observation as the center (default), or should the mean of the whole dataset be used as the center
max_iter	a numeric, maximal number of iteration for the optimization problem
categorical_variables	character vector, names of variables that should be treated as categories (factors are included by default)
k	a small positive number > 1, added to chf before taking log, so that weigths aren't negative

Value

A list, with the SurvLIME result in the ⁠$result⁠ field.

References

• [1] Kovalev, Maxim S., et al. "SurvLIME: A method for explaining machine learning survival models." Knowledge-Based Systems 203 (2020): 106164.

survex documentation built on Oct. 25, 2023, 1:06 a.m.