roses

ROSES (R pythOn Statistical tEstS) is a package to use statistical tests from R to Python


Keywords
python, r, statistical-tests
License
MIT
Install
pip install roses==0.3.9

Documentation

ROSES

ROSES (R pythOn Statistical tEstS) is a package to use statistical tests from R to Python for multiple algorithms in multiple problems.

PyPI License PyPI Python version DOI

This package was created due to differences in the precision from other Python packages for statistical tests. As R is a programming language with excellent libraries for statistical, ROSES was created as a bridge (parses) to use them.

Table of Contents

Requirements

Install Python:

sudo apt install python3-dev python3-setuptools python3-tk python-dev

Install R:

sudo apt install r-base

To compile the R libraries:

sudo apt install gfortran libcurl4-openssl-dev

To install the following R libraries, otherwhise a warning will be handled:

install.packages('devtools')
devtools::install_github("b0rxa/scmamp")
install.packages('PMCMR')
install.packages("https://cran.r-project.org/src/contrib/Archive/mvtnorm/mvtnorm_1.0-8.tar.gz", repos=NULL)
install.packages('PMCMRplus')
install.packages("https://cran.r-project.org/src/contrib/Archive/rgdal/rgdal_1.3-6.tar.gz", repos=NULL)
install.packages('pgirmess')

If you received warnings to install the R libraries, try some the commands as follow:

sudo apt install  libevent-dev  libreadline-dev 
sudo apt install libudunits2-dev libgdal-dev libgeos-dev libproj-dev
sudo apt install libgmp3-dev libmpfr-dev

Installation

To download ROSE just clone the Git repository hosted in GitHub:

git clone https://github.com/jacksonpradolima/ROSE.git
python setup.py install

Alternatively, you can install it with pip:

pip install roses

Usage

Examples of configuring and running all the included algorithms are located in the test folders roses folder.

Features

The current release of ROSES (v0.2) contains the following tests:

  • Kruskal-Wallis with Post-hoc when necessary (comparing p-value)
  • Friedman with Critical Distance plot and Post-hoc when necessary (comparing p-value)
  • Varghas and Delaney (effect size)

License

This project is licensed under the terms of the MIT - see the LICENSE file for details.

Citation

If this package contributes to a project which leads to a scientific publication, I would appreciate a citation.

@misc{roses,
  author       = {Prado Lima, Jackson Antonio do},
  title        = {{ROSES (R pythOn Statistical tEstS)}},
  month        = sep,
  year         = 2019,
  doi          = {10.5281/zenodo.3444187},
  url          = {https://doi.org/10.5281/zenodo.3444187}
}