light_performance: Model Performance of Flashlight

View source: R/light_performance.R

light_performanceR Documentation

Model Performance of Flashlight

Description

Calculates performance of a flashlight with respect to one or more performance measure.

Usage

light_performance(x, ...)

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

## S3 method for class 'flashlight'
light_performance(
  x,
  data = x$data,
  by = x$by,
  metrics = x$metrics,
  use_linkinv = FALSE,
  ...
)

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

Arguments

x

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

...

Arguments passed from or to other functions.

data

An optional data.frame.

by

An optional vector of column names used to additionally group the results. Will overwrite x$by.

metrics

An optional named list with metrics. Each metric takes at least four arguments: actual, predicted, case weights w and ....

use_linkinv

Should retransformation function be applied? Default is FALSE.

Details

The minimal required elements in the (multi-) flashlight are "y", "predict_function", "model", "data" and "metrics". The latter two can also directly be passed to light_performance(). Note that by default, no retransformation function is applied.

Value

An object of class "light_performance" 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.

Methods (by class)

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

  • light_performance(flashlight): Model performance of flashlight object.

  • light_performance(multiflashlight): Model performance of multiflashlight object.

See Also

plot.light_performance()

Examples

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

flashlight documentation built on May 31, 2023, 6:19 p.m.