Merge pull request #23 from l-ramirez-lopez/v0.2.1

Version 0.2.1 available on CRAN

.Rbuildignore

@@ -1,22 +1,14 @@
 ^.*\.Rproj$
 ^\.Rproj\.user$
-^README\.md
-.Rhistory
 .gitignore
-figure
-whittaker.r
-logo_prospectr.xcf
-prospectr-intro\.html
-prospectr-intro\.bib
-prospectr-intro\.md
-^.*\.tex
-^.*\.pdf
-code_ex.R
+.Rhistory
 .travis.yml
+^appveyor\.yml$
+cran-comments.md
+code_ex.R
+^Rscript*
 ^packrat/
 ^\.Rprofile$c  
 TODO
-^appveyor\.yml$
-cran-comments.md
-^doc$
-^Meta$
+epo.R
+

.gitignore

@@ -16,3 +16,4 @@ prospectr-intro\.html
 prospectr-intro\.md
 doc
 Meta
+vignettes/prospectr.html

DESCRIPTION

@@ -3,11 +3,11 @@ Type: Package
 Title: Miscellaneous Functions for Processing 
        and Sample Selection of Spectroscopic Data
 Version: 0.2.1
-Date: 2020-09-24
+Date: 2020-10-23
 Author: 
-    Antoine Stevens [aut, cre], 
-    Leonardo Ramirez-Lopez [aut, cre],
-    Guillaume Hans [ctb]
+    Antoine Stevens [aut, cre] (<https://orcid.org/0000-0002-1588-7519>), 
+    Leonardo Ramirez-Lopez [aut, cre] (<https://orcid.org/0000-0002-5369-5120>),
+    Guillaume Hans [ctb] (<https://orcid.org/0000-0002-6503-5760>)
 Maintainer: 
     Leonardo Ramirez-Lopez <[email protected]>
 BugReports: 
@@ -21,7 +21,8 @@ Suggests:
     knitr,
     rmarkdown,
     formatR,
-    testthat
+    testthat,
+    bookdown
 LinkingTo: 
     Rcpp, 
     RcppArmadillo
@@ -32,13 +33,12 @@ Imports:
     iterators,
     Rcpp (>= 1.0.1),
     mathjaxr (>= 1.0), 
-    lifecycle (>= 0.2.0),
-RdMacros: 
-    mathjaxr,
-    lifecycle
+    lifecycle (>= 0.2.0)
+RdMacros: mathjaxr
 RoxygenNote: 7.1.1
 NeedsCompilation: yes
 LazyData: true
+LazyDataCompression: xz
 Repository: CRAN
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)

NAMESPACE

@@ -25,6 +25,8 @@ export(standardNormalVariate)
 import(Rcpp)
 import(foreach)
 import(iterators)
+import(lifecycle)
+import(mathjaxr)
 importFrom(grDevices,chull)
 importFrom(graphics,legend)
 importFrom(graphics,matplot)

R/AAA.R

@@ -2,9 +2,16 @@
 
 .onAttach <- function(lib, pkg) {
   # assign("gpclib", FALSE, envir=.prospectr_CACHE)
-  prospectr.v <- read.dcf(file = system.file("DESCRIPTION", package = pkg), fields = "Version")
+  prospectr.v <- read.dcf(
+    file = system.file("DESCRIPTION", package = pkg),
+    fields = "Version"
+  )
   packageStartupMessage(paste(pkg, "version", prospectr.v, "-- 'seville'"))
-  packageStartupMessage("check the github repository at http://github.com/l-ramirez-lopez/prospectr")
+  mss2 <- paste0(
+    "check the github repository at: ",
+    "http://github.com/l-ramirez-lopez/prospectr"
+  )
+  packageStartupMessage(mss2)
 }
 
 # .onUnload <- function(libpath) {

R/Cul.R

@@ -1,7 +1,6 @@
 #' @title Cochran C critical value
 #'
 #' @description
-#' \lifecycle{stable}
 #' Upper limit critical value Cul for one-sided test on balanced design
 #' @usage
 #' Cul(a,n,N)

R/RcppExports.R

@@ -1,23 +1,6 @@
 # Generated by using Rcpp::compileAttributes() -> do not edit by hand
 # Generator token: 10BE3573-1514-4C36-9D1C-5A225CD40393
 
-#' @title Resample to given band position and fwhm
-#' @description
-#' Resample, written in C++
-#' @param X matrix to resample
-#' @param wav a numeric \code{vector} giving the original band positions
-#' @param new_wav a numeric \code{vector} giving the new band positions
-#' @param fwhm numeric \code{vector} giving the full width half maximums of the new band positions.
-#' @keywords internal
-#' @useDynLib prospectr
-resample_fwhm <- function(X, wav, new_wav, fwhm) {
-    .Call('_prospectr_resample_fwhm', PACKAGE = 'prospectr', X, wav, new_wav, fwhm)
-}
-
-resample_fwhm_vec <- function(X, wav, new_wav, fwhm) {
-    .Call('_prospectr_resample_fwhm_vec', PACKAGE = 'prospectr', X, wav, new_wav, fwhm)
-}
-
 #' @title bitwise operations 
 #' @description
 #' bitwise operations  in C++
@@ -87,6 +70,23 @@ get_msc_coeff <- function(X, reference_spc) {
     .Call('_prospectr_get_msc_coeff', PACKAGE = 'prospectr', X, reference_spc)
 }
 
+#' @title Resample to given band position and fwhm
+#' @description
+#' Resample, written in C++
+#' @param X matrix to resample
+#' @param wav a numeric \code{vector} giving the original band positions
+#' @param new_wav a numeric \code{vector} giving the new band positions
+#' @param fwhm numeric \code{vector} giving the full width half maximums of the new band positions.
+#' @keywords internal
+#' @useDynLib prospectr
+resample_fwhm <- function(X, wav, new_wav, fwhm) {
+    .Call('_prospectr_resample_fwhm', PACKAGE = 'prospectr', X, wav, new_wav, fwhm)
+}
+
+resample_fwhm_vec <- function(X, wav, new_wav, fwhm) {
+    .Call('_prospectr_resample_fwhm_vec', PACKAGE = 'prospectr', X, wav, new_wav, fwhm)
+}
+
 residLm <- function(Yr, Xr) {
     .Call('_prospectr_residLm', PACKAGE = 'prospectr', Yr, Xr)
 }

R/binning.R

@@ -1,49 +1,55 @@
 #' @title Signal binning
 #' @description
-#' \lifecycle{stable}
 #' Compute average values of a signal in pre-determined bins (col-wise subsets).
-#' The bin size can be determined either directly or by specifying the number of bins.
-#' Sometimes called boxcar transformation in signal processing
+#' The bin size can be determined either directly or by specifying the number of 
+#' bins. Sometimes called boxcar transformation in signal processing
 #' @usage
 #' binning(X, bins, bin.size)
-#' @param X a numeric matrix or vector to process (optionally a data frame that can
-#' be coerced to a numerical matrix).
+#' @param X a numeric matrix or vector to process (optionally a data frame that 
+#' can be coerced to a numerical matrix).
 #' @param bins the number of bins.
 #' @param bin.size the desired size of the bins.
-#' @author Antoine Stevens & Leonardo Ramirez-Lopez
+#' @author Antoine Stevens & \href{https://orcid.org/0000-0002-5369-5120}{Leonardo Ramirez-Lopez}
 #' @examples
 #' data(NIRsoil)
 #' wav <- as.numeric(colnames(NIRsoil$spc))
 #'
 #' # 5 first spectra
 #' matplot(wav, t(NIRsoil$spc[1:5, ]),
-#'         type = "l",
-#'         xlab = "Wavelength /nm",
-#'         ylab = "Absorbance")
-#'         
+#'   type = "l",
+#'   xlab = "Wavelength /nm",
+#'   ylab = "Absorbance"
+#' )
+#'
 #' NIRsoil$spc_binned <- binning(NIRsoil$spc, bin.size = 20)
 #'
 #' # bin means
-#' matpoints(as.numeric(colnames(NIRsoil$spc_binned)), 
-#'           t(NIRsoil$spc_binned[1:5, ]), 
-#'           pch = 1:5)
+#' matpoints(as.numeric(colnames(NIRsoil$spc_binned)),
+#'   t(NIRsoil$spc_binned[1:5, ]),
+#'   pch = 1:5
+#' )
 #'
 #' NIRsoil$spc_binned <- binning(NIRsoil$spc, bins = 20)
 #' dim(NIRsoil$spc_binned) # 20 bins
 #'
 #' # 5 first spectra
-#' matplot(wav, 
-#'         t(NIRsoil$spc[1:5, ]),
-#'         type = "l",
-#'         xlab = "Wavelength /nm",
-#'         ylab = "Absorbance")
-#'         
+#' matplot(wav,
+#'   t(NIRsoil$spc[1:5, ]),
+#'   type = "l",
+#'   xlab = "Wavelength /nm",
+#'   ylab = "Absorbance"
+#' )
+#'
 #' # bin means
 #' matpoints(as.numeric(colnames(NIRsoil$spc_binned)),
-#'           t(NIRsoil$spc_binned[1:5, ]),
-#'           pch = 1:5)
-#' @return a matrix or vector with average values per bin.
-#' @seealso \code{\link{savitzkyGolay}}, \code{\link{movav}},
+#'   t(NIRsoil$spc_binned[1:5, ]),
+#'   pch = 1:5
+#' )
+#' 
+#' @return
+#' a matrix or vector with average values per bin.
+#' @seealso 
+#' \code{\link{savitzkyGolay}}, \code{\link{movav}},
 #' \code{\link{gapDer}}, \code{\link{continuumRemoval}}
 #' @export
 #'

R/blockNorm.R

@@ -1,31 +1,38 @@
 #' @title Sum of squares block weighting
 #' @description
-#' \lifecycle{stable}
 #' Sum of squares block weighting: allows to scale blocks of variables,
 #' but keeping the relative weights of the variables inside a block.
 #' @usage
 #' blockNorm(X, targetnorm = 1)
 #' @param X a numeric matrix to transform (optionally a data frame that can
 #' be coerced to a numerical matrix).
-#' @param targetnorm desired sum of squares for a block of variables (default = 1)
-#' @return a list with components `Xscaled`, the scaled matrix and `f`, the scaling factor
+#' @param targetnorm desired sum of squares for a block of variables 
+#' (default = 1)
+#' @return a list with components `Xscaled`, the scaled matrix and `f`, the 
+#' scaling factor
 #' @author Antoine Stevens
 #' @examples
 #' X <- matrix(rnorm(100), ncol = 10)
 #' # Block normalize to sum of square equals to 1
 #' res <- blockNorm(X, targetnorm = 1)
 #' sum(res$Xscaled^2) # check
-#' @seealso \code{\link{blockScale}}, \code{\link{standardNormalVariate}},
+#' 
+#' @seealso 
+#' \code{\link{blockScale}}, \code{\link{standardNormalVariate}},
 #' \code{\link{detrend}}
-#' @references Eriksson, L., Johansson, E., Kettaneh, N., Trygg, J.,
+#' @references 
+#' Eriksson, L., Johansson, E., Kettaneh, N., Trygg, J.,
 #' Wikstrom, C., and Wold, S., 2006. Multi- and Megavariate Data Analysis.
 #' MKS Umetrics AB.
-#' @details The function computes a scaling factor, which, multiplied by the
+#' @details 
+#' The function computes a scaling factor, which, multiplied by the
 #' input matrix,
 #' produces a matrix with a pre--determined sum of squares.
 #' @note
 #' This is a \R port of the \file{MBnorm.m} function of the MB matlab toolbox
-#' by Fran van den Berg (<http://www.models.life.ku.dk/~courses/MBtoolbox/mbtmain.htm>)
+#' by Fran van den Berg which can be found at:
+#' \href{http://www.models.life.ku.dk/~courses/MBtoolbox/mbtmain.htm}{http://www.models.life.ku.dk/~courses/MBtoolbox/mbtmain.htm}
+#' 
 #' @export
 blockNorm <- function(X, targetnorm = 1) {
   if (!any(class(X) %in% c("matrix", "data.frame"))) {

R/blockScale.R

@@ -1,7 +1,6 @@
 #' @title Hard or soft block scaling
 #'
 #' @description
-#' \lifecycle{stable}
 #' Hard or soft block scaling of a spectral matrix to constant group variance.
 #' In multivariate calibration, block scaling is used to down-weight variables,
 #' when one block of variables dominates other blocks.
@@ -11,20 +10,23 @@
 #' root of the number of variables in a particular block.
 #' @usage
 #' blockScale(X, type = 'hard', sigma2 = 1)
-#' @param X a numeric matrix or vector to process (optionally a data frame that can
-#' be coerced to a numerical matrix).
+#' @param X a numeric matrix or vector to process (optionally a data frame that 
+#' can be coerced to a numerical matrix).
 #' @param type the type of block scaling: 'hard' or 'soft'.
 #' @param sigma2 the desired total variance of a block (ie sum of the variances
 #' of all variables, default = 1), applicable when `type = 'hard'`.
-#' @return a `list` with `Xscaled`, the scaled matrix and `f`, the scaling factor.
+#' @return a `list` with `Xscaled`, the scaled matrix and `f`, the scaling 
+#' factor.
 #' @author Antoine Stevens
 #' @examples
 #' X <- matrix(rnorm(100), ncol = 10)
 #' # Hard block scaling
 #' res <- blockScale(X)
 #' # sum of column variances == 1
 #' apply(res$Xscaled, 2, var)
-#' @seealso \code{\link{blockNorm}}, \code{\link{standardNormalVariate}},
+#' 
+#' @seealso 
+#' \code{\link{blockNorm}}, \code{\link{standardNormalVariate}},
 #' \code{\link{detrend}}
 #' @references Eriksson, L., Johansson, E., Kettaneh, N., Trygg, J.,
 #' Wikstrom, C., and Wold, S., 2006. Multi- and Megavariate Data Analysis.

R/cochranTest.R

@@ -1,6 +1,5 @@
 #' @title Cochran *C* Test
 #' @description
-#' \lifecycle{stable}
 #' \loadmathjax
 #' Detects and removes replicate outliers in data series based on the Cochran
 #' *C* test for homogeneity in variance.
@@ -19,14 +18,14 @@
 #'  \item{'`outliers`'}{ numeric vector giving the row indices of the input
 #'  data that have been flagged as outliers}
 #' }
-#' 
+#'
 #' @details
 #' The Cochran *C* test is test whether a single estimate of variance is
 #' significantly larger than a a group of variances.
 #' It can be computed as:
-#' 
+#'
 #' \mjdeqn{RMSD = \sqrt{\frac{1}{n} \sum_{i=1}^n {(y_i - \ddot{y}_i)^2}}}{RMSD = sqrt{{1}/{n} sum (y_i - ddot{y}_i)^2}}
-#' 
+#'
 #' where \mjeqn{y_i}{y_i} is the value of the side variable of the \mjeqn{i}{i}th sample,
 #' \mjeqn{\ddot{y}_i}{\ddot{y}_i} is the value of the side variable of the nearest neighbor
 #' of the \mjeqn{i}{i}th sample and \mjeqn{n}{n} is the total number of observations.