A RetroSearch Logo

Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Search Query:

Showing content from https://github.com/ModelOriented/auditor below:

ModelOriented/auditor: Model verification, validation, and error analysis

Model verification, validation, and error analysis

Package auditor is a tool for model-agnostic validation. Implemented techniques facilitate assessing and comparing the goodness of fit and performance of models. In addition, they may be used for the analysis of the similarity of residuals and for the identification of outliers and influential observations. The examination is carried out by diagnostic scores and visual verification. Due to the flexible and consistent grammar, it is simple to validate models of any classes.

An up-to-date paper about auditor and a shorter version in The R-Journal.

auditor is a part of DrWhy collection of tools for Visual Exploration, Explanation and Debugging of Predictive Models.

auditor’s pipeline: model %>% DALEX::explain() %>% plot(type=…)

Stable version from CRAN:

install.packages("auditor")

Developer version from GitHub:

source("https://install-github.me/ModelOriented/auditor")

# or with the devtools package
devtools::install_github("ModelOriented/auditor")

Run the code below or try the auditor.

library(auditor)
library(randomForest)
data(mtcars)

# fitting models
model_lm <- lm(mpg ~ ., data = mtcars)
set.seed(123)
model_rf <- randomForest(mpg ~ ., data = mtcars)

# creating objects with 'explain' function from the package DALEX
# that contains all necessary components required for further processing
exp_lm <- DALEX::explain(model_lm, data = mtcars, y = mtcars$mpg,  verbose = FALSE)
exp_rf <- DALEX::explain(model_rf, data = mtcars, y = mtcars$mpg, label = "rf", verbose = FALSE)

# create explanation  objects
mr_lm <- model_residual(exp_lm)
mr_rf <- model_residual(exp_rf)

# generating plots
plot_residual(mr_lm, mr_rf, variable = "wt", smooth = TRUE)

Column type contains character that should be passed to parameter type= when using plot() function. Regr and Class columns indicate whether plot can be used for regression and classification models.

Work on this package was financially supported by the NCN Opus grant 2016/21/B/ST6/02176.


RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4