boso

Bilevel Optimization Selector of Operators

https://github.com/lvalcarcel/boso

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (7.5%) to scientific vocabulary

Keywords

feature-selection machine-learning
Last synced: 5 months ago · JSON representation

Repository

Bilevel Optimization Selector of Operators

Basic Info
  • Host: GitHub
  • Owner: lvalcarcel
  • License: gpl-3.0
  • Language: R
  • Default Branch: main
  • Homepage:
  • Size: 318 MB
Statistics
  • Stars: 2
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 1
Topics
feature-selection machine-learning
Created over 4 years ago · Last pushed over 1 year ago
Metadata Files
Readme License

README.md

Introduction to BOSO

We present BOSO, an R package to perform feature selection in a linear regression problem. It implements a Bilevel Optimization Selector Operator.

Installation

BOSO can be installed from CRAN repository:

{r} install.packages("BOSO")

Alternatively, it can be downloaded and installed from github:

{r} library(devtools) install_github(repo="lvalcarcel/BOSO", subdir="BOSO")

Introduction

The package package has been prepared to work like 'glmnet' and 'lasso', presented in the BestSubset package.

``` r library(BOSO)

Load the data prepared for this test

data("sim.xy", package = "BOSO")

Xtr <- sim.xy[['high-5']]$x Ytr <- sim.xy[['high-5']]$y Xval <- sim.xy[['high-5']]$xval Yval <- sim.xy[['high-5']]$yval

Perform BOSO

time <- Sys.time() obj <- BOSO(x = Xtr, y = Ytr, xval = Xval, yval = Yval, IC = 'eBIC', nlambda=100, intercept= 0, standardize = 0, Threads=4, timeLimit = 60, verbose = 3, seed = 2021) time <- as.numeric(Sys.time() - time)

```

obj is a BOSO object, which have the following associated functions:

  • coef(obj) returns the coefficients (betas) of the linear regression.
  • predict(obj, xnew) returns the predicted outcome with a new X matrix.

``` r betas <- coef(obj) print(betas[betas!=0])

Ytrpredicted <- predict(obj, Xtr) print(paste0("MSE for training set is ", round(mean((Ytrpredicted-Ytr)^2),5)))

Yvalpredicted <- predict(obj, Xval) print(paste0("MSE for validation set is ", round(mean((Yvalpredicted-Yval)^2),5))) ```

Owner

  • Name: Luis V. Valcárcel
  • Login: lvalcarcel
  • Kind: user

GitHub Events

Total
Last Year

Packages

  • Total packages: 1
  • Total downloads:
    • cran 314 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 0
  • Total versions: 2
  • Total maintainers: 1
cran.r-project.org: BOSO

Bilevel Optimization Selector Operator

  • Versions: 2
  • Dependent Packages: 0
  • Dependent Repositories: 0
  • Downloads: 314 Last month
Rankings
Dependent packages count: 29.8%
Dependent repos count: 35.5%
Average: 43.0%
Downloads: 63.7%
Maintainers (1)
Last synced: over 1 year ago

Dependencies

BOSO/DESCRIPTION cran
  • R >= 4.0 depends
  • MASS * imports
  • Matrix * imports
  • methods * imports
  • BiocStyle * suggests
  • bestsubset * suggests
  • cplexAPI * suggests
  • devtools * suggests
  • dplyr * suggests
  • ggplot2 * suggests
  • ggpubr * suggests
  • glmnet * suggests
  • kableExtra * suggests
  • knitr * suggests
  • rmarkdown * suggests
  • testthat * suggests