philipp-baumann

################################################################################
## Task: Example script to visualize spectra in simplerspec framework
################################################################################

# Remove all R objects from memory
rm(list = ls())

# Load packages
pkgs <- c("tidyverse", "simplerspec")
lapply(pkgs, library, character.only = TRUE)

philipp-baumann

################################################################################
## Task: Example script to predict spectra in simplerspec framework
################################################################################

# Remove all R objects from memory
rm(list = ls())

# Load packages
pkgs <- c("tidyverse", "simplerspec")
lapply(pkgs, library, character.only = TRUE)

philipp-baumann

################################################################################
## Task: Select reference samples for soil refence analyses by using
##   Kennard-Stones
##   sampling algorithm on preprocessed spectra in PCA space
################################################################################

# Load packages
library("tidyverse")
library("simplerspec")

philipp-baumann

pkgs <- c("mlbench", "Cubist")
lapply(pkgs, library, character.only = TRUE)
# Example data set
data(BostonHousing)

# Test with only 2 factorial predictors
boston_housing <- BostonHousing[, c("crim", "zn", "medv")]
# Convert numeric `crim` and `zn` to factors
boston_housing$zn <- as.factor(boston_housing$zn)
boston_housing$crim <- as.factor(boston_housing$crim)

philipp-baumann

# Pull docker image (includes RStudio server)
FROM rocker/rstudio:3.6.0

RUN apt-get update \
  && apt-get install -y --no-install-recommends \
  libz-dev \
  libxml2-dev

ENV RENV_VERSION 0.7.0-111
RUN R -e "install.packages('remotes', repos = c(CRAN = 'https://cloud.r-project.org'))"

philipp-baumann

{
  "renv": {
    "Version": "0.6.0-61"
  },
  "R": {
    "Version": "3.6.1",
    "Repositories": [
      {
        "Name": "CRAN",
        "URL": "https://cloud.r-project.org"

philipp-baumann

{
  "R": {
    "Version": "3.6.1",
    "Repositories": [
      {
        "Name": "CRAN",
        "URL": "https://cloud.r-project.org"
      }
    ]
  },

philipp-baumann

## Load packages
pkgs <- c("here", "drake", "tidyverse", "data.table",
  "simplerspec", "caret", "Cubist", "rsample", "nls.multstart",
  "broom", # modeling
  "future", "future.apply", "doParallel", "doFuture", # asynchronous computation
  "gghighlight", "grid", "gridExtra", "cowplot", # graphics
  "xtable") # tables
purrr::walk(pkgs, library, character.only = TRUE)

funs <- list(

philipp-baumann

## Wrangle results of nested group k-fold cross-validation =====================

# Add additional grouping IDs
cubist_nested_results_ids <- cubist_nested_add_ids(
  object = cubist_nested_results_repgroupcv, x_vars = "spc_pre",
  id_cols = c("site_id", "depth_cm"),
  y_vars = param_names,
  custom_spc_averaging = FALSE)

# Get predicted and observed values for each outer resample assessment set

philipp-baumann

#' @title Average spectra in list-column by entries in grouping column
#' @description Average spectra in list-column of spectra tibble (`spc_tbl`) by
#' groups given in group column.
#' @param spc_tbl Tibble data frame containing at least the grouping column
#' given in argument `by` and input spectra given in list-column `column_in`.
#' @param by Character vector of length 1L or name/symbol that specifies the
#' column by which groups of spectra are averaged. Default is `"sample_id"`.
#' @param column_in Character vector of length 1L or or name/symbol that
#' specifies the list-column that contains the inputs spectra to be averaged.
#' Default is `"spc_rs"`, which are resampled spectra (i.e., resulting after