https://github.com/tidymodels/brulee

High-Level Modeling Functions with 'torch'
https://github.com/tidymodels/brulee

Last synced: 3 days ago
JSON representation

High-Level Modeling Functions with 'torch'

• Host: GitHub
• URL: https://github.com/tidymodels/brulee
• Owner: tidymodels
• License: other
• Created: 2020-08-19T21:34:01.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2024-10-21T19:22:46.000Z (22 days ago)
• Last Synced: 2024-10-31T22:03:14.592Z (12 days ago)
• Language: R
• Homepage: https://brulee.tidymodels.org/
• Size: 7.71 MB
• Stars: 67
• Watchers: 9
• Forks: 7
• Open Issues: 9
• Metadata Files:
  • Readme: README.Rmd
  • Changelog: NEWS.md
  • License: LICENSE
  • Code of conduct: .github/CODE_OF_CONDUCT.md

Awesome Lists containing this project

README

        
---

output: github_document

---

```{r, include = FALSE}

knitr::opts_chunk$set(

  collapse = TRUE,

  comment = "#>",

  fig.path = "man/figures/README-",

  out.width = "100%"

)

```

# brulee 

[![R-CMD-check](https://github.com/tidymodels/brulee/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/tidymodels/brulee/actions/workflows/R-CMD-check.yaml)

[![Codecov test coverage](https://codecov.io/gh/tidymodels/brulee/branch/main/graph/badge.svg)](https://app.codecov.io/gh/tidymodels/brulee?branch=main)

[![Lifecycle: experimental](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://lifecycle.r-lib.org/articles/stages.html)

The R `brulee` package contains several basic modeling functions that use the `torch` package infrastructure, such as:

* [neural networks](https://brulee.tidymodels.org/reference/brulee_mlp.html)

* [linear regression](https://brulee.tidymodels.org/reference/brulee_linear_reg.html)

* [logistic regression](https://brulee.tidymodels.org/reference/brulee_logistic_reg.html)

* [multinomial regression](https://brulee.tidymodels.org/reference/brulee_multinomial_reg.html)

## Installation

You can install the released version of brulee from [CRAN](https://CRAN.R-project.org) with:

``` r

install.packages("brulee")

```

And the development version from [GitHub](https://github.com/tidymodels/brulee) with:

``` r

# install.packages("pak")

pak::pak("tidymodels/brulee")

```

## Example

`brulee` has formula, x/y, and recipe user interfaces for each function. For example:

```{r load, include = FALSE}

library(brulee)

library(yardstick)

library(recipes)

```

```{r class-fit-form}

library(brulee)

library(recipes)

library(yardstick)

data(bivariate, package = "modeldata")

set.seed(20)

nn_log_biv <- brulee_mlp(Class ~ log(A) + log(B), data = bivariate_train, 

                         epochs = 150, hidden_units = 3)

# We use the tidymodels semantics to always return a tibble when predicting

predict(nn_log_biv, bivariate_test, type = "prob") %>% 

  bind_cols(bivariate_test) %>% 

  roc_auc(Class, .pred_One)

```

A recipe can also be used if the data require some sort of preprocessing (e.g., indicator variables, transformations, or standardization): 

```{r class-fit-rec}

library(recipes)

rec <- 

  recipe(Class ~ ., data = bivariate_train) %>%  

  step_YeoJohnson(all_numeric_predictors()) %>% 

  step_normalize(all_numeric_predictors())

set.seed(20)

nn_rec_biv <- brulee_mlp(rec, data = bivariate_train, 

                         epochs = 150, hidden_units = 3)

# A little better

predict(nn_rec_biv, bivariate_test, type = "prob") %>% 

  bind_cols(bivariate_test) %>% 

  roc_auc(Class, .pred_One)

```

## Code of Conduct

  

Please note that the brulee project is released with a [Contributor Code of Conduct](https://contributor-covenant.org/version/2/0/CODE_OF_CONDUCT.html). By contributing to this project, you agree to abide by its terms.