light_ice {flashlight}

Individual Conditional Expectation (ICE)

Description

Generates Individual Conditional Expectation (ICE) profiles. An ICE profile shows how the prediction of an observation changes if one or multiple variables are systematically changed across its ranges, holding all other values fixed (see the reference below for details). The curves can be centered in order to increase visibility of interaction effects.

Usage

light_ice(x, ...)

## Default S3 method:
light_ice(x, ...)

## S3 method for class 'flashlight'
light_ice(
  x,
  v = NULL,
  data = x$data,
  by = x$by,
  evaluate_at = NULL,
  breaks = NULL,
  grid = NULL,
  n_bins = 27L,
  cut_type = c("equal", "quantile"),
  indices = NULL,
  n_max = 20L,
  seed = NULL,
  use_linkinv = TRUE,
  center = c("no", "first", "middle", "last", "mean", "0"),
  ...
)

## S3 method for class 'multiflashlight'
light_ice(x, ...)

Arguments

x

An object of class "flashlight" or "multiflashlight".

...

Further arguments passed to or from other methods.

v

The variable name to be profiled.

data

An optional data.frame.

by

An optional vector of column names used to additionally group the results.

evaluate_at

Vector with values of v used to evaluate the profile.

breaks

Cut breaks for a numeric v. Used to overwrite automatic binning via n_bins and cut_type. Ignored if v is not numeric or if grid or evaluate_at are specified.

grid

A data.frame with evaluation grid. For instance, can be generated by expand.grid().

n_bins

Approximate number of unique values to evaluate for numeric v. Ignored if v is not numeric or if breaks, grid or evaluate_at are specified.

cut_type

Should a numeric v be cut into "equal" or "quantile" bins? Ignored if v is not numeric or if breaks, grid or evaluate_at are specified.

indices

A vector of row numbers to consider.

n_max

If indices is not given, maximum number of rows to consider. Will be randomly picked from data if necessary.

seed

An integer random seed.

use_linkinv

Should retransformation function be applied? Default is TRUE.

center

How should curves be centered?

• Default is "no".

• Choose "first", "middle", or "last" to 0-center at specific evaluation points.

• Choose "mean" to center all profiles at the within-group means.

• Choose "0" to mean-center curves at 0.

Details

There are two ways to specify the variable(s) to be profiled.

1. Pass the variable name via v and an optional vector with evaluation points evaluate_at (or breaks). This works for dependence on a single variable.

2. More general: Specify any grid as a data.frame with one or more columns. For instance, it can be generated by a call to expand.grid().

The minimum required elements in the (multi-)flashlight are "predict_function", "model", "linkinv" and "data", where the latest can be passed on the fly.

Which rows in data are profiled? This is specified by indices. If not given and n_max is smaller than the number of rows in data, then row indices will be sampled randomly from data. If the same rows should be used for all flashlights in a multiflashlight, there are two options: Either pass a seed or a vector of indices used to select rows. In both cases, data should be the same for all flashlights considered.

Value

An object of class "light_ice" with the following elements:

• data A tibble containing the results. Can be used to build fully customized visualizations. Column names can be controlled by options(flashlight.column_name).

• by Same as input by.

• v The variable(s) evaluated.

• center How centering was done.

Methods (by class)

• light_ice(default): Default method not implemented yet.

• light_ice(flashlight): ICE profiles for a flashlight object.

• light_ice(multiflashlight): ICE profiles for a multiflashlight object.

References

Goldstein, A. et al. (2015). Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation. Journal of Computational and Graphical Statistics, 24:1 <doi.org/10.1080/10618600.2014.907095>.

See Also

light_profile(), plot.light_ice()

Examples

fit <- lm(Sepal.Length ~ ., data = iris)
fl <- flashlight(model = fit, label = "lm", data = iris)
light_ice(fl, v = "Species")