update doc; no slicing in `plot_spc()`

DESCRIPTION

@@ -38,6 +38,6 @@ Imports:
     broom
 License: GPL-2
 LazyData: TRUE
-RoxygenNote: 7.1.0
+RoxygenNote: 7.2.3
 Roxygen: list(markdown = TRUE)
 Encoding: UTF-8

NAMESPACE

@@ -51,4 +51,5 @@ importFrom(purrr,modify_depth)
 importFrom(rlang,ensym)
 importFrom(rlang,quo_name)
 importFrom(rlang,set_names)
+importFrom(stringr,str_replace)
 importFrom(tidyselect,one_of)

R/plot_spc.R

@@ -32,10 +32,6 @@
 #' \code{expression(paste("Wavenumber [", cm^-1, "]"))}.
 #' @param ylab Character string or mathematical expression
 #' (use \code{expression}) for the y axis title. Default is \code{"absorbance"}.
-#' @param slice Logical whether to slice the data sets (select rows by position).
-#' Default is \code{TRUE}.
-#' This argument will soon be supported to group spectra based id variables present
-#' in spc_tbl such as the `sample_id` and slicing the data set prior to plotting.
 #' @param alpha Double in between 0 and 1. Sets the transparency for the plotted
 #' spectra lines.
 #' @param legend Logical whether to plot a legend for the spectra describing
@@ -56,17 +52,12 @@ plot_spc <- function(spc_tbl, spc_tbl_2 = NULL,
                      graph_id_1 = "Set 1", graph_id_2 = "Set 2",
                      graph_id_1_col = "black", graph_id_2_col = "red",
                      xlab = expression(paste("Wavenumber [", cm^-1, "]")),
-                     ylab = "Absorbance", slice = TRUE, alpha = 0.2,
+                     ylab = "Absorbance", alpha = 0.2,
                      legend = TRUE) {
 
   # Fix `R CMD check NOTE`: "no visible binding for global variable ‘...‘"
   graph_id <- id <- variable <- value <- NULL
 
-  # (0) Slice spectra tibble to remove triplicate spectra (reps)
-  # only sample_id level
-  if(slice == TRUE) {
-    spc_tbl <- dplyr::slice(spc_tbl)
-  }
   # (1) Gather spectra into one data.table
   if(!is.null(spc_tbl_2)) {
     if(y == "spc") {

R/select-spc.R

@@ -7,7 +7,7 @@
 #' @param lcol_xvalues List-column containing x-values, specified with
 #' column name as symbols or 1L character vector.
 #' @param every Every n-th spectral positions to keep as 1L integer vector.
-#' @return
+#' @return a spectral tibble
 #' @export
 select_spc_vars <- function(spc_tbl,
                             lcol_spc = "spc_pre",

man/assess_multimodels.Rd

@@ -4,15 +4,19 @@
 \alias{assess_multimodels}
 \title{Assess multiple pairs of measured and predicted values}
 \usage{
-assess_multimodels(data, ..., .metrics = c("simplerspec", "yardstick"),
-  .model_name = "model")
+assess_multimodels(
+  data,
+  ...,
+  .metrics = c("simplerspec", "yardstick"),
+  .model_name = "model"
+)
 }
 \arguments{
 \item{data}{Data frame with all measured (observed) and predicted variables.}
 
 \item{...}{Multiple arguments with observed (measured)-predicted pairs,
 specified with \code{dplyr::vars(o = <column_name>, p = <column_name>)}.
-Column names can strings or symbols. The arguments in `...` need to be named.}
+Column names can strings or symbols. The arguments in \code{...} need to be named.}
 
 \item{.metrics}{Character vector with package used for metrics calculation.
 Default is \code{"simplerspec"}, which uses

man/fit_pls.Rd

@@ -5,32 +5,62 @@
 \alias{pls_ken_stone}
 \title{Calibration sampling, model tuning, and PLS regression}
 \usage{
-fit_pls(spec_chem, response, variable = NULL, center = TRUE, scale = TRUE,
-  evaluation_method = "test_set", validation = TRUE,
-  split_method = "ken_stone", ratio_val = 1/3, ken_sto_pc = 2, pc,
-  invert = TRUE, tuning_method = "resampling",
-  resampling_method = "kfold_cv", cv = NULL, resampling_seed = 123,
-  pls_ncomp_max = 20, ncomp_fixed = 5, print = TRUE,
-  env = parent.frame())
-
-pls_ken_stone(spec_chem, response, variable = NULL, center = TRUE,
-  scale = TRUE, evaluation_method = "test_set", validation = TRUE,
-  split_method = "ken_stone", ratio_val = 1/3, ken_sto_pc = 2, pc,
-  invert = TRUE, tuning_method = "resampling",
-  resampling_method = "kfold_cv", cv = NULL, resampling_seed = 123,
-  pls_ncomp_max = 20, ncomp_fixed = 5, print = TRUE,
-  env = parent.frame())
+fit_pls(
+  spec_chem,
+  response,
+  variable = NULL,
+  center = TRUE,
+  scale = TRUE,
+  evaluation_method = "test_set",
+  validation = TRUE,
+  split_method = "ken_stone",
+  ratio_val = 1/3,
+  ken_sto_pc = 2,
+  pc,
+  invert = TRUE,
+  tuning_method = "resampling",
+  resampling_method = "kfold_cv",
+  cv = NULL,
+  resampling_seed = 123,
+  pls_ncomp_max = 20,
+  ncomp_fixed = 5,
+  print = TRUE,
+  env = parent.frame()
+)
+
+pls_ken_stone(
+  spec_chem,
+  response,
+  variable = NULL,
+  center = TRUE,
+  scale = TRUE,
+  evaluation_method = "test_set",
+  validation = TRUE,
+  split_method = "ken_stone",
+  ratio_val = 1/3,
+  ken_sto_pc = 2,
+  pc,
+  invert = TRUE,
+  tuning_method = "resampling",
+  resampling_method = "kfold_cv",
+  cv = NULL,
+  resampling_seed = 123,
+  pls_ncomp_max = 20,
+  ncomp_fixed = 5,
+  print = TRUE,
+  env = parent.frame()
+)
 }
 \arguments{
 \item{spec_chem}{Tibble that contains spectra, metadata and chemical
 reference as list-columns. The tibble to be supplied to \code{spec_chem} can
-be generated by the `join_chem_spc() function`}
+be generated by the \verb{join_chem_spc() function}}
 
 \item{response}{Response variable as symbol or name
 (without quotes, no character string). The provided response symbol needs to be
 a column name in the \code{spec_chem} tibble.}
 
-\item{variable}{Depreciated and replaced by `response`}
+\item{variable}{Depreciated and replaced by \code{response}}
 
 \item{center}{Logical whether to perform mean centering of each spectrum column
 (e.g. wavenumber or wavelength) after common spectrum preprocessing. Default is
@@ -66,7 +96,7 @@ Kennard-Stone algorithm.
 Default is \code{ken_sto_pc = 2}, which will use the first two PCA
 components.}
 
-\item{pc}{Depreciated; renamed argument is `ken_sto_pc`.}
+\item{pc}{Depreciated; renamed argument is \code{ken_sto_pc}.}
 
 \item{invert}{Logical}
 

man/fit_rf.Rd

@@ -4,22 +4,35 @@
 \alias{fit_rf}
 \title{Calibration sampling, and random forest model tuning and evaluation}
 \usage{
-fit_rf(spec_chem, response, variable = NULL, evaluation_method = "test_set",
-  validation = NULL, split_method = "ken_stone", ratio_val,
-  ken_sto_pc = 2, pc = NULL, invert = TRUE,
-  tuning_method = "resampling", resampling_seed = 123, cv = NULL,
-  ntree_max = 500, print = TRUE, env = parent.frame())
+fit_rf(
+  spec_chem,
+  response,
+  variable = NULL,
+  evaluation_method = "test_set",
+  validation = NULL,
+  split_method = "ken_stone",
+  ratio_val,
+  ken_sto_pc = 2,
+  pc = NULL,
+  invert = TRUE,
+  tuning_method = "resampling",
+  resampling_seed = 123,
+  cv = NULL,
+  ntree_max = 500,
+  print = TRUE,
+  env = parent.frame()
+)
 }
 \arguments{
 \item{spec_chem}{Tibble that contains spectra, metadata and chemical
 reference as list-columns. The tibble to be supplied to \code{spec_chem} can
-be generated by the `join_chem_spc() function`}
+be generated by the \verb{join_chem_spc() function}}
 
 \item{response}{Response variable as symbol or name
 (without quotes, no character string). The provided response symbol needs to be
 a column name in the \code{spec_chem} tibble.}
 
-\item{variable}{Depreciated and replaced by `response`}
+\item{variable}{Depreciated and replaced by \code{response}}
 
 \item{evaluation_method}{Character string stating evaluation method.
 Either \code{"test_set"} (default) or \code{"resampling"}. \code{"test_set"}
@@ -47,7 +60,7 @@ Kennard-Stone algorithm.
 Default is \code{ken_sto_pc = 2}, which will use the first two PCA
 components.}
 
-\item{pc}{Depreciated; renamed argument is `ken_sto_pc`.}
+\item{pc}{Depreciated; renamed argument is \code{ken_sto_pc}.}
 
 \item{invert}{Logical}
 

man/merge_dts.Rd

@@ -5,8 +5,13 @@
 \title{Merge list-columns of spectra, x-axis values, metadata and additional
 measured variables into a single long form data.table}
 \usage{
-merge_dts(spc_tbl, lcols_spc = c("spc", "spc_pre"), lcol_measure = NULL,
-  spc_id = "unique_id", group_id = "sample_id")
+merge_dts(
+  spc_tbl,
+  lcols_spc = c("spc", "spc_pre"),
+  lcol_measure = NULL,
+  spc_id = "unique_id",
+  group_id = "sample_id"
+)
 }
 \arguments{
 \item{spc_tbl}{Tibble data frame containing spectra, x-axis values, metadata

man/merge_dts_l.Rd

@@ -5,8 +5,13 @@
 \title{Wrapper function around \code{merge_dts()} for list of tibbles to
 aggregate data for plotting.}
 \usage{
-merge_dts_l(spc_tbl_l, lcols_spc = c("spc", "spc_pre"), lcol_measure = NULL,
-  spc_id = "unique_id", group_id = "sample_id")
+merge_dts_l(
+  spc_tbl_l,
+  lcols_spc = c("spc", "spc_pre"),
+  lcol_measure = NULL,
+  spc_id = "unique_id",
+  group_id = "sample_id"
+)
 }
 \arguments{
 \item{spc_tbl_l}{List of spectral tibbles (data frames).}

man/plot_spc.Rd

@@ -57,11 +57,6 @@ set. Default is \code{"red"}.}
 \item{ylab}{Character string or mathematical expression
 (use \code{expression}) for the y axis title. Default is \code{"absorbance"}.}
 
-\item{slice}{Logical whether to slice the data sets (select rows by position).
-Default is \code{TRUE}.
-This argument will soon be supported to group spectra based id variables present
-in spc_tbl such as the `sample_id` and slicing the data set prior to plotting.}
-
 \item{alpha}{Double in between 0 and 1. Sets the transparency for the plotted
 spectra lines.}
 

man/plot_spc_ext.Rd

@@ -4,13 +4,27 @@
 \alias{plot_spc_ext}
 \title{ggplot2 wrapper for extended spectra plotting}
 \usage{
-plot_spc_ext(spc_tbl, spc_tbl_l = NULL, lcols_spc = "spc",
-  lcol_measure = NULL, lcol_measure_col_palette = "Spectral",
-  lcol_measure_col_direction = -1, spc_id = "unique_id",
-  group_id = "sample_id", group_id_order = TRUE, group_color = TRUE,
-  group_color_palette = NULL, group_panel = TRUE, group_legend = FALSE,
-  ncol = NULL, relabel_spc = TRUE, ylab = "Spectrum value", alpha = 0.5,
-  line_width = 0.2, ...)
+plot_spc_ext(
+  spc_tbl,
+  spc_tbl_l = NULL,
+  lcols_spc = "spc",
+  lcol_measure = NULL,
+  lcol_measure_col_palette = "Spectral",
+  lcol_measure_col_direction = -1,
+  spc_id = "unique_id",
+  group_id = "sample_id",
+  group_id_order = TRUE,
+  group_color = TRUE,
+  group_color_palette = NULL,
+  group_panel = TRUE,
+  group_legend = FALSE,
+  ncol = NULL,
+  relabel_spc = TRUE,
+  ylab = "Spectrum value",
+  alpha = 0.5,
+  line_width = 0.2,
+  ...
+)
 }
 \arguments{
 \item{spc_tbl}{Tibble data frame containing spectra, x-axis values, metadata
@@ -27,14 +41,14 @@ of the measure columns. This argument is optional. Default is \code{NULL},
 which does not extract an additional measure column.}
 
 \item{lcol_measure_col_palette}{Palette value supplied to
-`ggplot::scale_colour_brewer()`. Default is `"Spectral"`, but you can set
-it to the default argument `1` (will use
-`scale_colour_brewer(..., palette = 1)`).}
+\code{ggplot::scale_colour_brewer()}. Default is \code{"Spectral"}, but you can set
+it to the default argument \code{1} (will use
+\code{scale_colour_brewer(..., palette = 1)}).}
 
 \item{lcol_measure_col_direction}{Sets the the order of colours in the scale
 that is based on a measure column. Default is \code{-1} which reverses the
-scale. Argument is passed on to the function `ggplot2::sclae_colour_brewer()`
-as argument `direction`.}
+scale. Argument is passed on to the function \code{ggplot2::sclae_colour_brewer()}
+as argument \code{direction}.}
 
 \item{spc_id}{Character vector denoting column name for a unique spectrum ID.
 Default is \code{"unique_id"}.}
@@ -51,8 +65,8 @@ numbers. Default is \code{TRUE}.}
 specified by \code{group_id}.}
 
 \item{group_color_palette}{Character (1L) defining the diverging colour
-scales from colorbrewer.org; see `?scale_colour_brewer` for supported
-diverging colur types (`palette` argument).}
+scales from colorbrewer.org; see \code{?scale_colour_brewer} for supported
+diverging colur types (\code{palette} argument).}
 
 \item{group_panel}{Logical defining whether spectra are arranged into panels
 by groups specified in \code{group_id}. Default is \code{TRUE}.}

man/preprocess_spc.Rd

@@ -4,8 +4,7 @@
 \alias{preprocess_spc}
 \title{Preprocess spectra}
 \usage{
-preprocess_spc(spc_tbl, select, column_in = "spc_mean",
-  custom_function = NULL)
+preprocess_spc(spc_tbl, select, column_in = "spc_mean", custom_function = NULL)
 }
 \arguments{
 \item{spc_tbl}{Tibble that contains spectra to be preprocessed within
@@ -24,7 +23,7 @@ in \code{select}.}
 
 \item{custom_function}{A character string of a custom processing function
 that is later parsed (produces expression in a list) and evaluated within
- the function \code{preprocess_spc}.
+the function \code{preprocess_spc}.
 The character vector argument of \code{custom_function}
 needs to contain \code{"spc_raw"}, which is the single data table of spectra
 that results from binding a list of data.tables (spectra to preprocess)

man/read_asd.Rd

@@ -14,7 +14,7 @@ remaining columns are sample spectra referred by an ID name provided in the
 first row of these columns.}
 }
 \value{
-Spectra data in tibble data frame (class `tbl_df`) that contains
+Spectra data in tibble data frame (class \code{tbl_df}) that contains
 columns \code{sample_id} (derived from 2nd and following column names of
 tab delimited ASD exported text file),
 \code{spc} (list-column of spectral matrices)

man/read_opus_univ.Rd

@@ -16,7 +16,7 @@ Possible values are: "spc" (AB block in Bruker Opus software), "spc_nocomp"
 correction has been set in Opus), "ScSm" (Single channel spectrum of the
 sample), "ScRf" (Single channel spectrum of the sample), "IgSm" (Interferogram
 of the sample), "IgRf" (Interferogram of the reference). Default is
- \code{extract = c("spc")}.}
+\code{extract = c("spc")}.}
 
 \item{parallel}{Logical (\code{TRUE} or \code{FALSE} indicating whether
 files are read in parallel (multiple processors or multiple cores)).

man/remove_outliers.Rd

@@ -19,20 +19,20 @@ If \code{rm = FALSE}, there will be no outlier removal}
 \value{
 Returns list \code{spectra_out} that contains:
 \itemize{
- \item \code{MIR_mean}: Outlier removed MIR spectra as
- data.frame object. If \code{remove = FALSE},
- the function will
- return almost identical list identical to \code{list_spectra},
- except that the first \code{indices} column of the spectral
- data frame \code{MIR_mean} is removed
- (This is done for both options
- \code{remove = TRUE} and \code{remove = FALSE}).
- \item \code{data_meta}: metadata data.frame, identical
- as in the \code{list_spectra} input list.
- \item \code{plot_out}: (optional) ggplot2 graph
- that shows all spectra (absorbance on x-axis and wavenumber
- on y-axis) with outlier marked, if
- \code{remove = TRUE}.
+\item \code{MIR_mean}: Outlier removed MIR spectra as
+data.frame object. If \code{remove = FALSE},
+the function will
+return almost identical list identical to \code{list_spectra},
+except that the first \code{indices} column of the spectral
+data frame \code{MIR_mean} is removed
+(This is done for both options
+\code{remove = TRUE} and \code{remove = FALSE}).
+\item \code{data_meta}: metadata data.frame, identical
+as in the \code{list_spectra} input list.
+\item \code{plot_out}: (optional) ggplot2 graph
+that shows all spectra (absorbance on x-axis and wavenumber
+on y-axis) with outlier marked, if
+\code{remove = TRUE}.
 }
 }
 \description{

man/select_spc_vars.Rd

@@ -24,7 +24,7 @@ column name as symbols or 1L character vector.}
 \item{every}{Every n-th spectral positions to keep as 1L integer vector.}
 }
 \value{
-
+a spectral tibble
 }
 \description{
 Select every n-th spectral variable for all spectra and x-values in spectral

man/slice_xvalues.Rd

@@ -4,8 +4,12 @@
 \alias{slice_xvalues}
 \title{Slice spectra into defined x-axis ranges}
 \usage{
-slice_xvalues(spc_tbl, xunit_lcol = "wavenumbers", spc_lcol = "spc",
-  xvalues_cut = NULL)
+slice_xvalues(
+  spc_tbl,
+  xunit_lcol = "wavenumbers",
+  spc_lcol = "spc",
+  xvalues_cut = NULL
+)
 }
 \arguments{
 \item{spc_tbl}{Spectral data in a tibble object (classes "tibble_df", "tbl"