inst/doc/library-builder.R

In OpenSpecy: Analyze, Process, Identify, and Share Raman and (FT)IR Spectra

## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  warning = FALSE
)

data.table::setDTthreads(2)

## ----setup--------------------------------------------------------------------
library(OpenSpecy)

## ----mini-library-read--------------------------------------------------------
mini_files <- c(
  read_extdata("raman_hdpe.csv"),
  read_extdata("ftir_ldpe_soil.asp"),
  read_extdata("raman_atacamit.spc")
)

mini_sources <- lapply(mini_files, read_any)
mini_sources <- lapply(mini_sources, function(x) {
  x$metadata$intensity_units <- "absorbance"
  attr(x, "intensity_unit") <- "absorbance"
  x
})
mini_raw <- c_spec(mini_sources, range = "common", res = 6)

check_OpenSpecy(mini_raw)
dim(mini_raw$spectra)
mini_raw$metadata[, "file_name", with = FALSE]

## ----mini-library-template----------------------------------------------------
template <- make_lib_lookup_template(
  mini_raw,
  columns = "file_name",
  add = c("material", "material_type")
)

template

## ----mini-library-join--------------------------------------------------------
lookup <- data.table::data.table(
  file_name = basename(mini_files),
  library_type = c("example", "example", "example"),
  spectrum_type = c("raman", "ftir", "raman"),
  material = c("hdpe", "ldpe in soil", "atacamite")
)

hierarchy <- data.table::data.table(
  material = c("hdpe", "ldpe in soil", "atacamite"),
  material_class = c("polyethylene", "polyethylene", "copper mineral"),
  material_type = c("plastic", "plastic", "mineral")
)

join_lib_metadata(mini_raw, lookup, by = "file_name",
                  require_complete = TRUE)$metadata[
  , c("file_name", "library_type", "spectrum_type", "material"),
  with = FALSE
]

## ----metadata-name-lookup-----------------------------------------------------
name_lookup <- lib_metadata_name_lookup(
  project_code = c("campaign id", "study code"),
  regex = list(instrument_mode = "^method_[0-9]+$")
)
name_lookup[
  canonical_name %in% c("material_color", "number_of_accumulations")
]
lib_clean_name(c("User Name", "Laser (%)", "Method...3"))

## ----mini-library-build-------------------------------------------------------
mini_libs <- build_lib(
  mini_files,
  recipes = list(
    raw = list(),
    derivative = list(
      conform_spec = FALSE,
      smooth_intens = TRUE,
      smooth_intens_args = list(window = 15, derivative = 1),
      make_rel = TRUE
    ),
    nobaseline = list(
      conform_spec = FALSE,
      smooth_intens = FALSE,
      subtr_baseline = TRUE,
      make_rel = TRUE
    )
  ),
  metadata_lookups = lookup,
  material_hierarchy = hierarchy,
  clean_metadata_values = TRUE,
  convert_intensity = FALSE,
  assess = TRUE,
  dedupe = FALSE
)

names(mini_libs)
check_OpenSpecy(mini_libs$raw)
check_OpenSpecy(mini_libs$derivative)
attr(mini_libs$derivative, "derivative_order")
attr(mini_libs$nobaseline, "baseline")
mini_libs$raw$metadata[
  , .(file_name, material, material_class, material_type, sn,
      assessment_flag, assessment_checks)
]

## ----mini-library-prune-------------------------------------------------------
pruned <- prune_lib(
  mini_libs$derivative,
  min_n = 1,
  return = "report",
  progress = FALSE
)
pruned$summary
pruned$schedule
pruned$excluded_classes

## ----cross-class-prune-policy, eval=FALSE-------------------------------------
# prune_lib(
#   reference_library,
#   cross_class = TRUE,
#   cross_class_threshold = 0.9
# )

## ----official-call-shape, eval=FALSE------------------------------------------
# reference_library_build <- build_lib(
#   files,
#   output_dir = output_dir,
#   previous_library_dir = "system",
#   remove_other = TRUE
# )

## ----downstream-rebuild-shape, eval=FALSE-------------------------------------
# updated_reference_library_build <- rebuild_lib_artifacts(
#   completed_build_dir,
#   output_dir = downstream_output_dir,
#   previous_library_dir = "system"
# )