blkbox v1.0

0

Monthly downloads

0th

Percentile

Data Exploration with Multiple Machine Learning Algorithms

Allows data to be processed by multiple machine learning algorithms at the same time, enables feature selection of data by single a algorithm or combinations of multiple. Easy to use tool for k-fold cross validation and nested cross validation.

Readme

blkbox

##Data Exploration with Multiple Machine Learning Algorithms

###Introduction

Machine learning (ML) is a powerful tool to create supervised models that can distinguish between classes and facilitate biomarker selection in high-dimensional datasets, including RNA Sequencing (RNA-Seq). However, identifying the best performing ML algorithm(s) for a specific dataset is time consuming. blkbox is a software package including a shiny frontend, that integrates nine ML algorithms to select the best performing classifier for a specific dataset. blkbox accepts a simple abundance matrix as input, includes extensive visualization, and also provides an easy to use feature selection step to enable convenient and rapid potential biomarker selection, all without requiring parameter optimization. Results: Feature selection makes blkbox computationally inexpensive while multi-functionality, including nested cross-fold validation (NCV), ensures robust results. blkbox identifies algorithms outperforming prior published ML results. Applying NCV identifies features which are utilized to gain high accuracy. Availability: The code is available as a CRAN R package and github (https://github.com/gboris/blkbox).

###Installation

R-package blkbox can be installed:

library(devtools)
install_github("gboris/blkbox")

After installation, the package can be loaded into R.

library(blkbox)

Details of how to use this package, please see the vignette.

Package: blkbox

Type: Package

Title: Data exploration with multiple machine learning algorithms

Version: 1.0

Date: 2016-08-05

Author: Zachary Davies, Boris Guennewig

Maintainer: Boris Guennewig b.guennewig@garvan.org.au

Description: Allows data to be processed by multiple machine learning algorithms at the same time, enables feature selection of data by single a algorithm or combinations of multiple. Easy to use tool for k-fold cross validation and nested cross validation.

License: GPL (>= 2)

LazyData: TRUE

NeedsCompilation: no

Packaged: 2016-08-05 22:19:09 UTC; Guennewig

Built: R 3.2.5; ; 2016-08-05 00:49:44 UTC; unix

Functions in blkbox

Name Description
blkboxROC ROC plots for blkbox
ncv.plot Nested Crossfold Validation Performance Plot.
cv.plot Crossfold Validation Performance Plot.
blkbox Train and Test datasets.
Partition blkbox paritioning
Performance blkbox Performance.
blkboxCV k-fold cross validation with blkbox.
blkboxUI blkbox User Interface
blkboxNCV Nested cross fold validation with blkbox.
No Results!

Vignettes of blkbox

Name
blkbox_vignette.Rmd
blkboxui_1.png
blkboxui_2.png
cv_barplot.png
cv_venn.png
ncv_boxplot.png
ncv_venn.png
roc_cv.png
roc_repeats_cv.png
shiny_interface.png
No Results!

Last month downloads

Details

Type Package
Date 2016-08-05
License GPL (>= 2)
LazyData TRUE
RoxygenNote 5.0.1
NeedsCompilation no
Packaged 2016-08-07 23:44:48 UTC; boris
VignetteBuilder knitr
Additional_repositories http://zacdav.github.io/drat/
Repository CRAN
Date/Publication 2016-08-08 02:37:07

Include our badge in your README

[![Rdoc](http://www.rdocumentation.org/badges/version/blkbox)](http://www.rdocumentation.org/packages/blkbox)