Learn R Programming

walkr (version 0.4.0)

Random Walks in the Intersection of Hyperplanes and the N-Simplex

Description

Consider the intersection of two spaces: the complete solution space to Ax = b and the N-simplex. The intersection of these two spaces is a non-negative convex polytope. The package walkr samples from this intersection using two Monte-Carlo Markov Chain (MCMC) methods: hit-and-run and Dikin walk. walkr also provide tools to examine sample quality. The package implements Dikin walk specified in Sachdeva (2016) .

Copy Link

Version

Install

install.packages('walkr')

Monthly Downloads

2

Version

0.4.0

License

GPL-3

Issues

Pull Requests

Stars

Forks

Maintainer

Andy Yao

Last Published

June 29th, 2019

Functions in walkr (0.4.0)

rcppeigen_fdet

Fast Matrix Determinant
rcppeigen_fprod

Fast Matrix Product
calc_rhat

R hat
complete_solution

Complete Solution
dikin_walk

Dikin Walk
walkr

The walkr package.
explore_walkr

Explore Walkr
rcppeigen_fsolve

Fast Matrix Inverse
hit_and_run

Hit and Run
rcppeigen_ftcrossprod

Fast Matrix T-Cross-Product
rcppeigen_fcrossprod

Fast Matrix Cross-Product
rcppeigen_ftrans

Fast Matrix Transpose
start_point

start point