DimensionRed: Generic Dimensionallity Reduction Function

In PredPsych: Predictive Approaches in Psychology

Description

A simple function to perform dimensionality reduction

Usage

DimensionRed(Data, method = "MDS", selectedCols, outcome = NA,
  plot = FALSE, silent = FALSE, ...)

Arguments

Data	(dataframe) a data frame with variable/feature columns
method	(optional) (character) Dimensionality reduction method to be used
selectedCols	(optional)(numeric) which columns should be treated as data(features/columns) (defaults to all columns)
outcome	(optional)(vector) optional vector for visualising plots
plot	(optional)(logical) To plot or not to plot
silent	(optional) (logical) whether to print messages or not
...	(optional) additional arguments for the function

Details

Dimensionality Reduction is the process of reducing the dimensions of the dataset. Multivariate data, even though are useful in getting an overall understanding of the underlying phenomena, do not permit easy interpretability. Moreover, variables in such data often are correlated with each other .For these reasons, it might be imperative to reduce the dimensions of the data. Various models have been developed for such dimensionality reduction. Of these, MDS and PCA has been demonstrated in the current implementation.

Value

Data frame with Results

Author(s)

Atesh Koul, C'MON unit, Istituto Italiano di Tecnologia

[e-mail]

References

Bishop, C. M. (2006). Pattern Recognition and Machine Learning. (M. Jordan, J. Kleinberg, & B. Scholkopf, Eds.) (1st ed.). Springer-Verlag New York.

Cox, T. F., & Cox, M. A. A. (2000). Multidimensional scaling (Second ed.). Chapman & Hall/CRC.

Examples

# reducing dimension of Grip aperture from 10 to 2
GripAperture <- DimensionRed(KinData,selectedCols = 12:21,
outcome = KinData[,"Object.Size"],plot = TRUE)

PredPsych documentation built on July 23, 2019, 9:04 a.m.