In pachoning/bigmds: Multidimensional Scaling for Big Data

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%"
)

bigmds

MDS is a statistic tool for reduction of dimensionality, using as input a distance matrix of dimensions n × n. When n is large, classical algorithms suffer from computational problems and MDS configuration can not be obtained. With this package, we address these problems by means of six algorithms, being two of them original proposals:

Landmark MDS proposed by De Silva V. and JB. Tenenbaum (2004).
Interpolation MDS proposed by Delicado P. and C. Pachón-García (2021) (original proposal).
Reduced MDS proposel by Paradis E (2018).
Pivot MDS prposed by Brandes U. and C. Pich (2007)
Divide-and-conquer MDS proposed by Delicado P. and C. Pachón-García (2021) (original proposal).
Fast MDS, proposed by Yang, T., J. Liu, L. McMillan and W. Wang (2006).

To obtain more information, please read this paper.

Installation

You can install the development version of bigmds from GitHub with:

# install.packages("devtools")
devtools::install_github("pachoning/bigmds")

Example

This is a basic example which shows you how to solve a common problem:

library(bigmds)
x <- matrix(data = rnorm(4 * 10000), nrow = 10000) %*% diag(c(9, 4, 1, 1))

landmark_mds_conf <- landmark_mds(x = x, num_landmarks = 200, r = 2)
head(landmark_mds_conf$points)
landmark_mds_conf$eigen

interpolation_mds_conf <- interpolation_mds(x = x, l = 200, r = 2, n_cores = 1)
head(interpolation_mds_conf$points)
interpolation_mds_conf$eigen

reduced_mds_conf <- reduced_mds(x = x, l = 200, r = 2, n_cores = 1)
head(reduced_mds_conf$points)
reduced_mds_conf$eigen

pivot_mds_conf <- pivot_mds(x = x, num_pivots = 200, r = 2)
head(pivot_mds_conf$points)
pivot_mds_conf$eigen

divide_mds_conf <- divide_conquer_mds(x = x, l = 200, c_points = 5 * 2, r = 2, n_cores = 1)
head(divide_mds_conf$points)
divide_mds_conf$eigen

fast_mds_conf <- fast_mds(x = x, l = 200, s_points = 2*2, r = 2, n_cores = 1)
head(fast_mds_conf$points)
fast_mds_conf$eigen