cor_diss: Correlation and moving correlation dissimilarity measurements...
In resemble: Memory-Based Learning in Spectral Chemometrics

View source: R/cor_diss.R

cor_diss

R Documentation

Correlation and moving correlation dissimilarity measurements (cor_diss)

Description

\loadmathjax

Computes correlation and moving correlation dissimilarity matrices.

Usage

cor_diss(Xr, Xu = NULL, ws = NULL,
         center = TRUE, scale = FALSE)

Arguments

`Xr`	a matrix.
`Xu`	an optional matrix containing data of a second set of observations.
`ws`	for moving correlation dissimilarity, an odd integer value which specifies the window size. If `ws = NULL`, then the window size will be equal to the number of variables (columns), i.e. instead moving correlation, the normal correlation will be used. See details.
`center`	a logical indicating if the spectral data `Xr` (and `Xu` if specified) must be centered. If `Xu` is provided, the data is scaled on the basis of \mjeqnXr \cup XuXr U Xu.
`scale`	a logical indicating if `Xr` (and `Xu` if specified) must be scaled. If `Xu` is provided the data is scaled on the basis of \mjeqnXr \cup XuXr U Xu.

Details

The correlation dissimilarity \mjeqndd between two observations \mjeqnx_ix_i and \mjeqnx_jx_j is based on the Perason's correlation coefficient (\mjeqn\rho\rho) and it can be computed as follows:

\mjdeqn

d(x_i, x_j) = \frac12((1 - \rho(x_i, x_j)))d(x_i, x_j) = 1/2 (1 - \rho(x_i, x_j))

The above formula is used when ws = NULL. On the other hand (when ws != NULL) the moving correlation dissimilarity between two observations \mjeqnx_ix_i and \mjeqnx_jx_j is computed as follows:

\mjdeqn

d(x_i, x_j; ws) = \frac12 ws\sum_k=1^p-ws1 - \rho(x_i,(k:k+ws), x_j,(k:k+ws))d(x_i, x_j) = 1/(2 ws)\sum_(k=1)^p-ws(1 - \rho(x_(i,k:k+ws), x_(j,k:k+ws)))

where \mjeqnwsws represents a given window size which rolls sequentially from 1 up to \mjeqnp - wsp - ws and \mjeqnpp is the number of variables of the observations.

The function does not accept input data containing missing values.

Value

a matrix of the computed dissimilarities.

Author(s)

Antoine Stevens and Leonardo Ramirez-Lopez

Examples


library(prospectr)
data(NIRsoil)

Xu <- NIRsoil$spc[!as.logical(NIRsoil$train), ]
Xr <- NIRsoil$spc[as.logical(NIRsoil$train), ]

cor_diss(Xr = Xr)

cor_diss(Xr = Xr, Xu = Xu)

cor_diss(Xr = Xr, ws = 41)

cor_diss(Xr = Xr, Xu = Xu, ws = 41)

resemble documentation built on April 21, 2023, 1:13 a.m.