Description
Model and Learner Summaries for 'mlr3'.
Description
Concise and interpretable summaries for machine learning models and learners of the 'mlr3' ecosystem. The package takes inspiration from the summary function for (generalized) linear models but extends it to non-parametric machine learning models, based on generalization performance, model complexity, feature importances and effects, and fairness metrics.
README.md
mlr3summary
Concise, informative summaries of machine learning models. Based on mlr3. Inspired by the summary output of (generalized) linear models.
Installation
You can install the development version of mlr3summary:
remotes::install_github("mlr-org/mlr3summary")
If you want to get started with mlr3 (the basis of mlr3summary), we recommend installing the mlr3verse meta-package which installs mlr3 and some of the most important extension packages:
install.packages("mlr3verse")
library(mlr3verse)
Example
Load data and create a task
library(mlr3summary)
data("credit", package = "mlr3summary")
task = TaskClassif$new(id = "credit", backend = credit, target = "risk", positive = "good")
Fit a model and resampling strategy
set.seed(12005L)
rf = lrn("classif.ranger", predict_type = "prob")
rf$train(task)
cv3 = rsmp("cv", folds = 3L)
rr = resample(task = task, learner = rf, resampling = cv3, store_models = TRUE)
rr$aggregate(msrs(list("classif.acc", "classif.auc")))
Apply the summary function
summary(object = rf, resample_result = rr)
More examples can be found in demo/.
Citation
If you use mlr3summary, please cite:
Dandl S, Becker M, Bischl B, Casalicchio G, Bothmann L (2024).
mlr3summary: Model and learner summaries for 'mlr3'.
R package version 0.1.0.
A BibTeX entry for LaTeX users is
@Manual{,
title = {mlr3summary: Model and learner summaries for 'mlr3'},
author = {Susanne Dandl and Marc Becker and Bernd Bischl and Giuseppe Casalicchio and Ludwig Bothmann},
year = {2024},
note = {R package version 0.1.0},
}