This model fitting tool incorporates cyclic coordinate descent and
majorization-minimization approaches to fit a variety of regression models
found in large-scale observational healthcare data. Implementations focus
on computational optimization and fine-scale parallelization to yield
efficient inference in massive datasets. Please see:
Suchard, Simpson, Zorych, Ryan and Madigan (2013)
Cyclops is part of the OHDSI Methods Library.
Cyclops (Cyclic coordinate descent for logistic, Poisson and survival analysis) is an R package for performing large scale regularized regressions.
library(Cyclops) cyclopsData <- createCyclopsDataFrame(formula) cyclopsFit <- fitCyclopsModel(cyclopsData)
Cyclops in an R package, with most functionality implemented in C++. Cyclops uses cyclic coordinate descent to optimize the likelihood function, which makes use of the sparse nature of the data.
Requires R (version 3.1.0 or higher). Compilation on Windows requires RTools >= 3.4.
In R, to install the latest stable version, install from CRAN:
install.packages("Cyclops")
To install the latest development version, install from GitHub. Note that this will require RTools to be installed.
install.packages("devtools")devtools::install_github("ohdsi/Cyclops")
Cyclops is licensed under Apache License 2.0. Cyclops contains the TinyThread libray.
The TinyThread library is licensed under the zlib/libpng license as described here.
Cyclops is being developed in R Studio.
Beta
Changes:
RNGversion("3.5.0")
in unit-tests to reproduce old RNG behaviorChanges:
ModelData.cpp
and ModelSpecifics.hpp
Changes:
RcppParallel
(until TBB is again R-compliant)Changes:
MASS
and microbenchmarks
Changes:
Changes:
<complex>
header, needed for R
3.5 buildspragma
statements used to quiet RcppEigen
and RcppParallel
Changes:
.checkCovariates
when excluding covariates from regularizationChanges:
Changes:
predict
error with ff.data.frame
with size == 0Changes:
solaris
build errorsChanges: initial submission to CRAN