Movatterモバイル変換

[0]ホーム
URL:

bundle

R-CMD-checkCRAN statusLifecycle: stableCodecov test coverage

Typically, models in R exist in memory and can be saved as.rds files. However, some models store information inlocations that cannot be saved usingsave() orsaveRDS() directly. The goal of bundle is to provide acommon interface to capture this information, situate it within aportable object, and restore it for use in new settings.

Installation

You can install the released version of bundle fromCRAN with:

install.packages("bundle")

And the development version fromGitHub with:

# install.packages("pak")pak::pak("rstudio/bundle")

Overview

We often imagine a trained model as a somewhat “standalone” Robject—given some new data, the R object can generate predictions on itsown. In reality, some types of model objects also make use ofreferences to generate predictions. A reference is a piece ofinformation that a model object refers to that isn’t part of the objectitself; this could be anything from a connection with a server to aninternal function in the package used to train the model. When we callpredict(), model objects know where to look to retrievethat data, but saving model objects can sometimes disrupt thosereferences. Thus, if we want to train a model, save it, re-load it intomemory in a production setting, and generate predictions with it, we mayrun into issues because those references do not exist in the newcomputational environment.

We need some way to preserve access to those references. The bundlepackage provides a consistent interface forbundling modelobjects with their references so that they can be safely saved andre-loaded in production:

A diagram showing a rectangle, labeled model object, and another rectangle, labeled predictions. The two are connected by an arrow from model object to predictions, with the label 'predict'. There are two boxes labeled reference, connected to the arrow labeled predict with dotted arrows, to show that, most of the time, we don't need to think about including them in our workflow. There are two boxes, labeled R Session number one, and R session number two. In focus is the arrow from the model object, in R Session number one, to a model object in R session number two. This arrow connecting the model object in R session one and the model object in R session two is connected by a verb called bundle. The bundle function outputs an object called a bundle.

For more on this diagram, see themain bundlevignette.

When you’re ready to save your model,bundle() it first.Once you’ve loaded it in a new setting,unbundle() it!

Example

The bundle package prepares model objects so that they can beeffectively saved and re-loaded for use in new R sessions. Todemonstrate using bundle, we will train a boosted tree model usingXGBoost, bundle it, and thenpass the bundle into another R session to generate predictions on newdata.

First, load needed packages:

library(bundle)library(parsnip)library(callr)library(waldo)

Fit the boosted tree model:

# fit an boosted tree with xgboost via parsnipmod<-boost_tree(trees =5,mtry =3)|>set_mode("regression")|>set_engine("xgboost")|>fit(mpg~ .,data = mtcars[1:25, ])mod#> parsnip model object#>#> ##### xgb.Booster#> call:#>   xgboost::xgb.train(params = list(eta = 0.3, max_depth = 6, gamma = 0,#>     colsample_bytree = 1, colsample_bynode = 0.3, min_child_weight = 1,#>     subsample = 1, nthread = 1, objective = "reg:squarederror"),#>     data = x$data, nrounds = 5, evals = x$watchlist, verbose = 0)#> # of features: 10#> # of rounds:  5#> callbacks:#>    evaluation_log#> evaluation_log:#>   iter training_rmse#>  <int>         <num>#>      1      4.655552#>      2      3.648086#>      3      2.877980#>      4      2.302021#>      5      1.850090

Note that simply saving and loading the model results in changes tothe fitted model:

temp_file<-tempfile()saveRDS(mod, temp_file)mod2<-readRDS(temp_file)compare(mod, mod2,ignore_formula_env =TRUE)#> `old$fit$ptr` is <pointer: 0x11a0cf990>#> `new$fit$ptr` is <pointer: 0x10bed38a0>

Saving and reloadingmod2 didn’t preserve XGBoost’sreference to itspointer, which may result in failureslater in the modeling process.

We thus need to prepare the fitted model to be saved before passingit to another R session. We can do so by bundling it:

# bundle the modelbundled_mod<-bundle(mod)bundled_mod#> bundled model_fit object.

Passing the model to another R session and generating predictions onnew data:

# load the model in a fresh R session and predict on new datar(func =function(bundled_mod) {library(bundle)library(parsnip)    unbundled_mod<-unbundle(bundled_mod)predict(unbundled_mod,new_data = mtcars[26:32, ])  },args =list(bundled_mod = bundled_mod  ))#> # A tibble: 7 × 1#>   .pred#>   <dbl>#> 1  28.6#> 2  25.8#> 3  25.8#> 4  16.7#> 5  20.2#> 6  15.3#> 7  21.2

For a more in-depth demonstration of the package, see themainvignette withvignette("bundle").

Contributing

This project is released with aContributorCode of Conduct. By contributing to this project, you agree to abideby its terms.

[8]ページ先頭
©2009-2025 Movatter.jp