d37 - extraction

# packages
library(metaDigitise)
library(magrittr)
library(tibble)
library(dplyr)
library(lubridate)
library(dpeatdecomposition)
library(dm)
library(RMariaDB)
library(sp)
library(readODS)

1 Preparations

Connect to database

# connect to database
con <-
  RMariaDB::dbConnect(
    drv = RMariaDB::MariaDB(),
    dbname = "dpeatdecomposition",
    default.file = "~/my.cnf"
  )

# get database as dm object
dm_dpeatdecomposition <-
  dpeatdecomposition::dp_get_dm(con, learn_keys = TRUE)

Get most current IDs

id_last <- 
  list(
    id_dataset = 
      dm_dpeatdecomposition %>%
      dm::pull_tbl(datasets) %>%
      dplyr::pull(id_dataset) %>%
      tail(1),
    id_sample = 
      dm_dpeatdecomposition %>%
      dm::pull_tbl(samples) %>%
      dplyr::pull(id_sample) %>%
      tail(1),
    id_measurement = 
      dm_dpeatdecomposition %>%
      dm::pull_tbl(data) %>%
      dplyr::pull(id_measurement) %>%
      tail(1)
    ) %>%
  purrr::map(function(.x) {
    if(length(.x) == 0) {
      0L
    } else {
      .x
    }
  })

Create directories

dir_name <- "d37"
dir_source <- "../raw_data/data/d37"
dir_target <- paste0("../derived_data/", id_last$id_dataset + 1L)

if(!dir.exists(dir_target)) {
  dir.create(dir_target)
}

2 Data wrangling

2.1 dataset

datasets <- 
  tibble::tibble(
    id_dataset = id_last$id_dataset + 1L
  )

2.2 citations_to_datasets

citations_to_datasets <- 
  dplyr::bind_rows(
    db_template_tables$citations_to_datasets,
    tibble::tibble(
      id_dataset = datasets$id_dataset,
      id_citation = c("Breeuwer.2008") 
    )
  )

2.3 samples

# mass remaining
samples3 <- 
  dplyr::bind_rows(
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig2a"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig2b"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig2c"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig2d"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig3a"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig3b"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig3c"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig3d"))$processed_data
  ) %>%
  dplyr::select(id, mean, error) %>%
  dplyr::rename(
    mass_relative_mass = "mean",
    mass_relative_mass_error = "error",
  ) %>%
  dplyr::mutate(
    dplyr::across(dplyr::starts_with("mass_relative_mass"), function(.x) .x/100),
    mass_relative_mass_error_type = "se",
    taxon_rank_value =
      dplyr::case_when(
        stringr::str_detect(id, "whatEriophorum") ~ "Eriophorum vaginatum",
        stringr::str_detect(id, "balticum") ~ "Sphagnum balticum",
        stringr::str_detect(id, "fuscum") ~ "Sphagnum fuscum"
      ),
    taxon_rank_name = "species",
    mass_relative_mass_sample_size = 
      dplyr::case_when(
        stringr::str_detect(id, "Eriophorum") ~ 8L, #---note: the text gives only ranges across all data for one taxon. I here assume the smallest values for any point, even though this is not true in all cases
        stringr::str_detect(id, "Sphagnum") ~ 9L
      ),
    taxon_organ =
      dplyr::case_when(
        stringr::str_detect(id, "leaves") ~ "leaves,stems",
        stringr::str_detect(id, "capitula") ~ "capitula",
        stringr::str_detect(id, "organstems") ~ "stems"
      ),
    incubation_site_name =
      dplyr::case_when(
        stringr::str_detect(id, "incubatedinNS") ~ "Lappmyran",
        stringr::str_detect(id, "incubatedinCS") ~ "Akerlänna Römosse",
        stringr::str_detect(id, "incubatedinSS") ~ "Saxnäs mosse",
        stringr::str_detect(id, "incubatedinGE") ~ "Barschpfuhl",
      ),
    site_name = incubation_site_name,
    site_label = incubation_site_name,
    sampling_longitude =
      dplyr::case_when(
        stringr::str_detect(id, "incubatedinNS") ~ "19°35'E",
        stringr::str_detect(id, "incubatedinCS") ~ "17°22'E",
        stringr::str_detect(id, "incubatedinSS") ~ "13°28'E",
        stringr::str_detect(id, "incubatedinGE") ~ "13°51'E",
      ) %>%
        sp::char2dms(chd = "°", chm = "'", chs = "''") %>%
        as.numeric(),
    sampling_latitude =
      dplyr::case_when(
        stringr::str_detect(id, "incubatedinNS") ~ "64°10'N",
        stringr::str_detect(id, "incubatedinCS") ~ "60°01'N",
        stringr::str_detect(id, "incubatedinSS") ~ "56°51'N",
        stringr::str_detect(id, "incubatedinGE") ~ "53°03'N",
      ) %>%
        sp::char2dms(chd = "°", chm = "'", chs = "''") %>%
        as.numeric(),
    origin_site_name =
      dplyr::case_when(
        stringr::str_detect(id, "originNS") ~ "Lappmyran",
        stringr::str_detect(id, "originCS") ~ "Akerlänna Römosse",
        stringr::str_detect(id, "originSS") ~ "Saxnäs mosse",
        stringr::str_detect(id, "originGE") ~ "Barschpfuhl",
      ),
    origin_sampling_longitude =
      dplyr::case_when(
        stringr::str_detect(id, "originNS") ~ "19°35'E",
        stringr::str_detect(id, "originCS") ~ "17°22'E",
        stringr::str_detect(id, "originSS") ~ "13°28'E",
        stringr::str_detect(id, "originGE") ~ "13°51'E",
      ) %>%
        sp::char2dms(chd = "°", chm = "'", chs = "''") %>%
        as.numeric(),
    origin_sampling_latitude =
      dplyr::case_when(
        stringr::str_detect(id, "originNS") ~ "64°10'N",
        stringr::str_detect(id, "originCS") ~ "60°01'N",
        stringr::str_detect(id, "originSS") ~ "56°51'N",
        stringr::str_detect(id, "originGE") ~ "53°03'N",
      ) %>%
        sp::char2dms(chd = "°", chm = "'", chs = "''") %>%
        as.numeric(),
    incubation_duration =
      dplyr::case_when(
        stringr::str_detect(id, "sampling1") & stringr::str_detect(id, "Eriophorum") ~ 1,
        stringr::str_detect(id, "sampling2") & stringr::str_detect(id, "Eriophorum") ~ 2,
        stringr::str_detect(id, "sampling3") & stringr::str_detect(id, "Eriophorum") ~ 3,
        stringr::str_detect(id, "sampling1") & stringr::str_detect(id, "Sphagnum") ~ 0.25,
        stringr::str_detect(id, "sampling2") & stringr::str_detect(id, "Sphagnum") ~ 1,
        stringr::str_detect(id, "sampling3") & stringr::str_detect(id, "Sphagnum") ~ 2,
      ),
    sampling_date =
      dplyr::case_when(
        stringr::str_detect(id, "Eriophorum") ~ as.Date("2003-08-15"),
        stringr::str_detect(id, "Sphagnum") ~ as.Date("2004-05-15")
      ) %>%
      magrittr::add(lubridate::dyears(incubation_duration)) %>%
      as.Date(),
    sampling_year = lubridate::year(sampling_date),
    sampling_month = lubridate::month(sampling_date),
    sampling_day = NA_real_,
    mesh_size_absolute = 0.1,
    sample_microhabitat = "lawn or low hummock",
    sample_depth_upper = 5,
    sample_depth_lower = 10,
    mass_absolute = NA_real_,
    is_incubated = TRUE,
    incubation_environment = "peat",
    id_dataset = datasets$id_dataset[[1]],
    experimental_design = 
      paste0(
        as.numeric(as.factor(origin_site_name)), "_",
        as.numeric(as.factor(incubation_site_name))
      ),
    sample_type =
      dplyr::case_when(
        stringr::str_detect(id, "Sphagnum") & taxon_organ == "capitula" ~ "vegetation",
        TRUE ~ "litter"
      ),
    comments_samples = "Coordinates are only the approximate location of the study site, but not sampling points."
  )


# initial mass
samples2 <- 
  samples3 %>%
  dplyr::filter(!duplicated(paste0(taxon_rank_value, "_", taxon_organ, "_", origin_site_name, "_", incubation_site_name, "_"))) %>%
  dplyr::mutate(
    incubation_duration = 0,
    sampling_date =
      dplyr::case_when(
        stringr::str_detect(id, "Eriophorum") ~ as.Date("2003-08-15"),
        stringr::str_detect(id, "Sphagnum") ~ as.Date("2004-05-15")
      ) %>%
      magrittr::add(lubridate::dyears(incubation_duration)) %>%
      as.Date(),
    sampling_year = lubridate::year(sampling_date),
    sampling_month = lubridate::month(sampling_date),
    sampling_day = NA_real_,
    mass_relative_mass = 1.0,
    mass_relative_mass_error = 0.0,
    sampling_date = as.Date("1997-09-15"),
    sampling_year = lubridate::year(sampling_date),
    sampling_month = lubridate::month(sampling_date),
    sampling_day = NA_real_
  )

# litter collection
samples1 <- 
  samples2 %>%
  dplyr::filter(!duplicated(paste0(origin_site_name, "_", taxon_rank_value, "_", taxon_organ))) %>%
  dplyr::mutate(
    id_sample = seq_len(nrow(.)) + id_last$id_sample,
    id_sample_origin = id_sample,
    id_sample_parent = id_sample,
    id_sample_incubation_start = NA_integer_,
    sample_treatment = "control",
    experimental_design = NA_character_,
    is_incubated = FALSE,
    incubation_environment = NA_character_,
    site_name = origin_site_name,
    site_label = origin_site_name,
    sampling_longitude = origin_sampling_longitude,
    sampling_latitude = origin_sampling_latitude,
    sample_depth_upper = 
      dplyr::case_when(
        stringr::str_detect(taxon_rank_value, "Sphagnum") & taxon_organ == "capitula" ~ 0,
        stringr::str_detect(taxon_rank_value, "Sphagnum") & taxon_organ == "stems" ~ 1,
        TRUE ~ NA_real_
      ),
    sample_depth_lower = 
      dplyr::case_when(
        stringr::str_detect(taxon_rank_value, "Sphagnum") & taxon_organ == "capitula" ~ 1,
        stringr::str_detect(taxon_rank_value, "Sphagnum") & taxon_organ == "stems" ~ 4,
        TRUE ~ NA_real_
      ),
    sampling_date =
      dplyr::case_when(
        stringr::str_detect(taxon_rank_value, "Sphagnum") ~ "2003-08-15",
        TRUE ~ "2003-05-15"
      ) %>%
      as.Date(),
    sampling_year = lubridate::year(sampling_date),
    sampling_month = lubridate::month(sampling_date),
    sampling_day = NA_real_
  )

# add missing ids
samples2 <- 
  dplyr::bind_rows(
    samples2 %>%
      dplyr::mutate(
        type = "samples2"
      ), 
    samples3 %>%
      dplyr::mutate(
        type = "samples3"
      )
  )

samples2 <- 
  samples2 %>%
  dplyr::mutate(
    id_sample = seq_len(nrow(.)) + max(samples1$id_sample),
    id_sample_origin = 
      dplyr::left_join(
        samples2 %>% dplyr::select(origin_site_name, taxon_rank_value, taxon_organ),
        samples1 %>% dplyr::select(origin_site_name, taxon_rank_value, taxon_organ, id_sample),
        by = c("origin_site_name", "taxon_rank_value", "taxon_organ")
      ) %>%
      dplyr::pull(id_sample),
    id_sample_incubation_start = 
      purrr::map_int(seq_len(nrow(.)), function(i) {
        index <- paste0(taxon_rank_value, "_", site_label, "_", taxon_organ) == paste0(taxon_rank_value, "_", site_label, "_", taxon_organ)[[i]] & experimental_design == experimental_design[[i]] & incubation_duration == 0.0
        id_sample[index]
      }),
    id_sample_parent = 
      purrr::map_int(seq_len(nrow(.)), function(i) {
        index <- paste0(taxon_rank_value, "_", site_label, "_", taxon_organ) == paste0(taxon_rank_value, "_", site_label, "_", taxon_organ)[[i]] & experimental_design == experimental_design[[i]] & incubation_duration < incubation_duration[[i]]
        if(! any(index)) {
          id_sample_origin[[i]]
        } else {
          target_incubation_duration <- max(incubation_duration[index])
          index <- index & incubation_duration == target_incubation_duration
          id_sample[index]
        }
      })
  ) %>%
  dplyr::mutate(
    sample_type = "litter",
    incubation_duration = 
      incubation_duration %>%
      lubridate::dyears() %>%
      lubridate::time_length(unit = "days")
  )


# litter chemistry
d37_litter_chemistry <- 
  readODS::read_ods(paste0(dir_source, "/derived/Breeuwer.2008-Tab2.ods")) %>%
  setNames(
    nm = 
      colnames(.) %>% 
      stringr::str_replace(pattern = "^K", replacement = "K_relative_mass") %>%
      stringr::str_replace(pattern = "^N", replacement = "N_relative_mass") %>%
      stringr::str_replace(pattern = "^P", replacement = "P_relative_mass") %>%
      stringr::str_replace(pattern = "^CN", replacement = "C_to_N")
    ) %>%
  dplyr::mutate(
    dplyr::across(dplyr::starts_with(c("K", "N", "P")) & where(is.numeric) & ! dplyr::ends_with("_sample_size"), function(.x) .x/1000),
    C_absolute = NA_real_,
    C_relative_mass = NA_real_,
    N_absolute = NA_real_,
    P_absolute = NA_real_,
    K_absolute = NA_real_
  )

# N dynamics
d37_N <- 
  dplyr::bind_rows(
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig4a"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig4b"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig4c"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig4d"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig5a"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig5b"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig5c"))$processed_data,
    readRDS(paste0(dir_source, "/raw/caldat/Breeuwer.2008-Fig5d"))$processed_data
  ) %>%
  dplyr::select(id, mean, error) %>%
  dplyr::rename(
    N_relative_mass2 = "mean",
    N_relative_mass2_error = "error",
  ) %>%
  dplyr::mutate(
    dplyr::across(dplyr::starts_with("N_relative_mass2"), function(.x) .x/100),
    N_relative_mass2_error_type = "se",
    taxon_rank_value =
      dplyr::case_when(
        stringr::str_detect(id, "whatEriophorum") ~ "Eriophorum vaginatum",
        stringr::str_detect(id, "balticum") ~ "Sphagnum balticum",
        stringr::str_detect(id, "fuscum") ~ "Sphagnum fuscum"
      ),
    N_relative_mass2_sample_size = 
      dplyr::case_when(
        stringr::str_detect(id, "Eriophorum") ~ 8L, #---note: the text gives only ranges across all data for one taxon. I here assume the smallest values for any point, even though this is not true in all cases
        stringr::str_detect(id, "Sphagnum") ~ 9L
      ),
    taxon_organ =
      dplyr::case_when(
        stringr::str_detect(id, "leaves") ~ "leaves,stems",
        stringr::str_detect(id, "capitula") ~ "capitula",
        stringr::str_detect(id, "organstems") ~ "stems"
      ),
    incubation_site_name =
      dplyr::case_when(
        stringr::str_detect(id, "incubatedinNS") ~ "Lappmyran",
        stringr::str_detect(id, "incubatedinCS") ~ "Akerlänna Römosse",
        stringr::str_detect(id, "incubatedinSS") ~ "Saxnäs mosse",
        stringr::str_detect(id, "incubatedinGE") ~ "Barschpfuhl",
      ),
    origin_site_name =
      dplyr::case_when(
        stringr::str_detect(id, "originNS") ~ "Lappmyran",
        stringr::str_detect(id, "originCS") ~ "Akerlänna Römosse",
        stringr::str_detect(id, "originSS") ~ "Saxnäs mosse",
        stringr::str_detect(id, "originGE") ~ "Barschpfuhl",
      ),
    incubation_duration =
      dplyr::case_when(
        stringr::str_detect(id, "sampling1") & stringr::str_detect(id, "Eriophorum") ~ 1,
        stringr::str_detect(id, "sampling2") & stringr::str_detect(id, "Eriophorum") ~ 2,
        stringr::str_detect(id, "sampling3") & stringr::str_detect(id, "Eriophorum") ~ 3,
        stringr::str_detect(id, "sampling1") & stringr::str_detect(id, "Sphagnum") ~ 0.25,
        stringr::str_detect(id, "sampling2") & stringr::str_detect(id, "Sphagnum") ~ 1,
        stringr::str_detect(id, "sampling3") & stringr::str_detect(id, "Sphagnum") ~ 2,
      )
  )

d37_N <- 
  dplyr::bind_rows(
    d37_N,
    d37_N %>%
      dplyr::filter(!duplicated(paste0(taxon_rank_value, "_", taxon_organ, "_", origin_site_name, "_", incubation_site_name, "_"))) %>%
      dplyr::mutate(
        N_relative_mass2 = 1,
        N_relative_mass2_error = 0,
        incubation_duration = 0
      )
  ) %>%
  dplyr::select(-id)

# add to samples2
samples2 <- 
  dplyr::left_join(
    samples2,
    d37_litter_chemistry %>%
      dplyr::mutate(
        origin_site_name = site_name,
        incubation_duration = 0.0
      ) %>%
      dplyr::select(dplyr::all_of(c("origin_site_name", "taxon_rank_value", "taxon_organ", "incubation_duration")) | dplyr::starts_with(c("C_", "N_", "P_", "K_"))),
    by = c("origin_site_name", "taxon_rank_value", "taxon_organ", "incubation_duration")
  ) %>%
  dplyr::left_join(
    d37_N, 
    by = c("origin_site_name", "incubation_site_name", "taxon_rank_value", "taxon_organ", "incubation_duration")
  ) %>%
  dplyr::mutate(
    C_absolute = NA_real_,
    N_absolute = NA_real_,
    P_absolute = NA_real_,
    K_absolute = NA_real_
  )


## combine
samples <- 
  dplyr::bind_rows(
    db_template_tables$samples,
    samples1 %>%
      dplyr::mutate(
        type = "samples1"
      ),
    samples2
  )

2.4 samples_to_samples

samples_to_samples <- 
  samples %>%
  dplyr::filter(! id_sample %in% id_sample_origin) %>%
  dplyr::mutate(
    transition_description =
      dplyr::case_when(
        type %in% c("samples2") ~ "translocate",
        type %in% c("samples3") ~ "wait",
        TRUE ~ NA_character_
      )
  ) %>%
  dplyr::select(id_sample_parent, id_sample, transition_description) %>%
  dplyr::rename(
    id_sample_child = "id_sample"
  )

2.5 data

d2 <- 
  samples2 %>%
  tidyr::pivot_longer(
    cols = dplyr::all_of(c("mass_absolute", "mass_relative_mass", "mesh_size_absolute", "N_relative_mass", "C_relative_mass", "P_relative_mass", "K_relative_mass", "N_relative_mass2", "C_absolute", "N_absolute", "P_absolute", "K_absolute")),
    names_to = "attribute_name",
    values_to = "value"
  ) %>%
  dplyr::mutate(
    id_measurement = seq_len(nrow(.)) + id_last$id_measurement,
    id_measurement_numerator =
      purrr::map_int(seq_len(nrow(.)), function(i) {
        switch(
          attribute_name[[i]],
          "C_relative_mass" = ,
          "N_relative_mass" = ,
          "P_relative_mass" = ,
          "K_relative_mass" = ,
          "N_relative_mass2" = {
            id_measurement[id_sample == id_sample[[i]] & attribute_name == stringr::str_replace(attribute_name[[i]], "_relative_mass2?", "_absolute")]
          },
          "mass_relative_mass" = {
            id_measurement[id_sample == id_sample[[i]] & attribute_name == "mass_absolute"]
          },
          NA_integer_
        )
      }),
    id_measurement_denominator =
      purrr::map_int(seq_len(nrow(.)), function(i) {
        switch(
          attribute_name[[i]],
          "C_relative_mass" = ,
          "N_relative_mass" = ,
          "P_relative_mass" = ,
          "K_relative_mass" = {
            id_measurement[id_sample == id_sample[[i]] & attribute_name == "mass_absolute"]
          },
          "N_relative_mass2" = {
            id_measurement[id_sample == id_sample_incubation_start[[i]] & attribute_name == stringr::str_replace(attribute_name[[i]], "_relative_mass2?", "_absolute")]
          },
          "mass_relative_mass" = {
            id_measurement[id_sample == id_sample_incubation_start[[i]] & attribute_name == "mass_absolute"]
          },
          NA_integer_
        )
      }),
    value_type = 
      dplyr::case_when(
        attribute_name == "mesh_size_absolute" ~ "point", 
        TRUE ~ "mean"
      )
  )

d2_sample_size <- 
  samples2 %>%
  tidyr::pivot_longer(
    cols = dplyr::ends_with("_sample_size"),
    names_to = "attribute_name",
    values_to = "sample_size"
  ) %>%
  dplyr::mutate(
    attribute_name = 
      attribute_name %>%
      stringr::str_remove(pattern = "_sample_size$")
  ) %>%
  dplyr::select(id_sample, attribute_name, sample_size)

d2_error <- 
  samples2 %>%
  tidyr::pivot_longer(
    cols = dplyr::ends_with(c("_error")),
    names_to = "attribute_name",
    values_to = "error"
  ) %>%
  dplyr::mutate(
    attribute_name = 
      attribute_name %>%
      stringr::str_remove(pattern = "_error$")
  ) %>%
  dplyr::select(id_sample, attribute_name, error)

d2_error_type <- 
  samples2 %>%
  tidyr::pivot_longer(
    cols = dplyr::ends_with(c("_error_type")),
    names_to = "attribute_name",
    values_to = "error_type"
  ) %>%
  dplyr::mutate(
    attribute_name = 
      attribute_name %>%
      stringr::str_remove(pattern = "_error_type$")
  ) %>%
  dplyr::select(id_sample, attribute_name, error_type)

d2 <- 
  d2 %>%
  dplyr::mutate(
    error =
      dplyr::left_join(d2, d2_error, by = c("id_sample", "attribute_name")) %>%
      dplyr::pull(error),
    error_type =
      dplyr::left_join(d2, d2_error_type, by = c("id_sample", "attribute_name")) %>%
      dplyr::pull(error_type),
    sample_size =
      dplyr::left_join(d2, d2_sample_size, by = c("id_sample", "attribute_name")) %>%
      dplyr::pull(sample_size)
  )

# correct attribute names
d2 <- 
  d2 %>%
  dplyr::mutate(
    attribute_name =
      dplyr::case_when(
        attribute_name %in% c("C_relative_mass2", "N_relative_mass2", "P_relative_mass2") ~ stringr::str_remove(attribute_name, "2$"),
        TRUE ~ attribute_name
      )
  )


# combine
d <- 
  dplyr::bind_rows(
    db_template_tables$data,
    d2,
  ) %>%
  dplyr::select(dplyr::all_of(colnames(db_template_tables$data)))

2.6 experimental_design_format

experimental_design_format <- 
  tibble::tibble(
    id_dataset = datasets$id_dataset,
    file = paste0(id_last$id_dataset + 1L, "/experimental_design_format.csv"),
    experimental_design_description = "`origin_site_name`: Name of the site where the sample was collected (see the article for details). `incubation_site_name`: Name of the site where the sample was incubated (see the article for details)."
  )

# csv file to export
experimental_design_format2 <- 
  samples %>%
  dplyr::filter(! is.na(experimental_design)) %>%
  dplyr::filter(! duplicated(experimental_design)) %>%
  dplyr::select(experimental_design, origin_site_name, incubation_site_name)

# export
write.csv(experimental_design_format2, paste0(dir_target, "/experimental_design_format.csv"), row.names = FALSE)

3 Export to database

# list all tables
dm_insert_in <-
  list(
    datasets = 
      datasets %>% 
      dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$datasets))),
    samples = 
      samples %>% 
      dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$samples))),
    data = 
      d %>% 
      dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$data))),
    samples_to_samples = 
      samples_to_samples %>% 
      dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$samples_to_samples))),
    citations_to_datasets = 
      citations_to_datasets %>% 
      dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$citations_to_datasets))),
    experimental_design_format = 
      experimental_design_format %>% 
      dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$experimental_design_format)))
  )

# check whether all column names as present in table attributes
all_column_names <- 
  purrr::map(dm_insert_in, colnames) %>%
  unlist() %>%
  unique()

if(! all(all_column_names %in% (dm_dpeatdecomposition %>% dm::pull_tbl(attributes) %>% dplyr::pull(attribute_name)))) {
  cond <- purrr::map_lgl(all_column_names, function(.x) ! .x %in% (dm_dpeatdecomposition %>% dm::pull_tbl(attributes) %>% dplyr::pull(attribute_name)))
  RMariaDB::dbDisconnect(con)
  stop(paste0("New `attribute_name`s discovered: ", paste(all_column_names[cond], collapse = ", ")))
}

all_data_attributes <- unique(dm_insert_in$data$attribute_name)

if(! all(all_data_attributes %in% (dm_dpeatdecomposition %>% dm::pull_tbl(attributes) %>% dplyr::pull(attribute_name)))) {
  RMariaDB::dbDisconnect(con)
  cond <- purrr::map_lgl(all_data_attributes, function(.x) ! .x %in% (dm_dpeatdecomposition %>% dm::pull_tbl(attributes) %>% dplyr::pull(attribute_name)))
  stop(paste0("New `attribute_name`s discovered: ", paste(all_data_attributes[cond], collapse = ", ")))
}


# filter empty tables
dm_insert_in_check <-
  dm_insert_in[purrr::map_lgl(dm_insert_in, function(x) nrow(x) > 0)] %>%
  dm::as_dm() %>%
  dp_dm_add_keys(dm_dpeatdecomposition)

# copy into dm_pmird
for(i in seq_along(dm_insert_in)) {
  RMariaDB::dbAppendTable(con, name = names(dm_insert_in)[[i]], value = dm_insert_in[[i]])
}

RMariaDB::dbDisconnect(con)

4 Notes