Movatterモバイル変換

Cyclops

Cyclops is part of theHADES.

Introduction

Cyclops (Cyclic coordinate descent for logistic, Poisson and survivalanalysis) is an R package for performing large scale regularizedregressions.

Features

• Regression of very large problems: up to millions of observations,millions of variables
• Supports (conditional) logistic regression, (conditional) Poissonregression, as well as (conditional) Cox regression
• Uses a sparse representation of the independent variables whenappropriate
• Supports using no prior, a normal prior or a Laplace prior
• Supports automatic selection of hyperparameter throughcross-validation
• Efficient estimation of confidence intervals for a single variableusing a profile-likelihood for that variable

Examples

library(Cyclops)  cyclopsData<-createCyclopsDataFrame(formula)  cyclopsFit<-fitCyclopsModel(cyclopsData)

Technology

Cyclops in an R package, with most functionality implemented in C++.Cyclops uses cyclic coordinate descent to optimize the likelihoodfunction, which makes use of the sparse nature of the data.

System Requirements

Requires R (version 3.1.0 or higher). Compilation on Windows requiresRTools >=3.4.

Installation

In R, to install the latest stable version, install from CRAN:

install.packages("Cyclops")

To install the latest development version, install from GitHub. Notethat this will require RTools to be installed.

install.packages("devtools")devtools::install_github("OHDSI/Cyclops")

User Documentation

Documentation can be found on thepackage website.

PDF versions of the documentation are also available: * Packagemanual:Cyclopsmanual

Support

• Developer questions/comments/feedback:OHDSI Forum
• We use theGitHubissue tracker for all bugs/issues/enhancements

Contributing

Readherehow you can contribute to this package.

License

Cyclops is licensed under Apache License 2.0. Cyclops contains theTinyThread libray.

The TinyThread library is licensed under thezlib/libpng license asdescribedhere.

Development

Cyclops is being developed in R Studio.

Acknowledgements

• This project is supported in part through the National ScienceFoundation grants IIS 1251151 and DMS 1264153.