# packages
library(metaDigitise)
library(magrittr)
library(tibble)
library(dplyr)
library(lubridate)
library(dpeatdecomposition)
library(dm)
library(RMariaDB)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 <- "d40"
dir_source <- "../raw_data/data/d40"
dir_target <- paste0("../derived_data/", id_last$id_dataset + 1L)
if(!dir.exists(dir_target)) {
dir.create(dir_target)
}datasets <-
tibble::tibble(
id_dataset = id_last$id_dataset + 1L
)citations_to_datasets <-
dplyr::bind_rows(
db_template_tables$citations_to_datasets,
tibble::tibble(
id_dataset = datasets$id_dataset,
id_citation = c("Trinder.2009")
)
)# mass remaining
samples3 <-
dplyr::bind_cols(
readRDS(paste0(dir_source, "/raw/caldat/Trinder.2009-Fig1a"))$processed_data %>%
dplyr::rename(
mass_relative_mass = "mean",
mass_relative_mass_error = "error"
),
readRDS(paste0(dir_source, "/raw/caldat/Trinder.2009-Fig1b"))$processed_data %>%
dplyr::select(mean, error) %>%
dplyr::rename(
C_relative_mass = "mean",
C_relative_mass_error = "error"
),
readRDS(paste0(dir_source, "/raw/caldat/Trinder.2009-Fig1c"))$processed_data %>%
dplyr::select(mean, error) %>%
dplyr::rename(
N_relative_mass = "mean",
N_relative_mass_error = "error"
),
readRDS(paste0(dir_source, "/raw/caldat/Trinder.2009-Fig1d"))$processed_data %>%
dplyr::select(mean, error) %>%
dplyr::rename(
P_relative_mass = "mean",
P_relative_mass_error = "error"
)
) %>%
dplyr::mutate(
sample_type = "litter",
taxon_rank_name = "species",
taxon_rank_value =
dplyr::case_when(
stringr::str_detect(id, "whatCallunavulgaris") ~ "Calluna vulgaris",
stringr::str_detect(id, "whatEriophorumangustifolium") ~ "Eriophorum angustifolium",
stringr::str_detect(id, "whatEriophorumvaginatum") ~ "Eriophorum vaginatum",
stringr::str_detect(id, "whatSphagnumauriculatum") ~ "Sphagnum auriculatum"
),
sample_type2 =
dplyr::case_when(
taxon_rank_value == "Calluna vulgaris" ~ "Senesced Calluna vulgaris leaves and branches",
taxon_rank_value == "Eriophorum angustifolium" ~ "Senesced Eriophorum angustifolium leaves and shoots",
taxon_rank_value == "Eriophorum vaginatum" ~ "Senesced Eriophorum vaginatum leaves and shoots",
taxon_rank_value == "Sphagnum auriculatum" ~ "Sphagnum auriculatum shoots without Capitulum (upper 1 cm)"
),
taxon_organ =
dplyr::case_when(
taxon_rank_value == "Calluna vulgaris" ~ "branches,leaves",
taxon_rank_value == "Eriophorum angustifolium" ~ "leaves,shoots",
taxon_rank_value == "Eriophorum vaginatum" ~ "leaves,shoots",
taxon_rank_value == "Sphagnum auriculatum" ~ "shoots"
),
sample_treatment =
dplyr::case_when(
stringr::str_detect(id, "incubationwithCallunavulgaris") ~ "Priming by Calluna vulgaris",
stringr::str_detect(id, "incubationwithEriophorumangustifolium") ~ "Priming by Eriophorum angustifolium",
stringr::str_detect(id, "incubationwithEriophorumvaginatum") ~ "Priming by Eriophorum vaginatum",
stringr::str_detect(id, "incubationwithcontrol") ~ "control"
),
mesh_size_absolute = 0.5,
sample_depth_upper = 0,
sample_depth_lower = 6,
incubation_duration = 365,
sampling_year = NA,
sampling_month = NA,
sampling_day = NA,
mass_relative_mass_error_type = "se",
C_relative_mass_error_type = "se",
N_relative_mass_error_type = "se",
P_relative_mass_error_type = "se",
mass_relative_mass_sample_size = 5L,
C_relative_mass_sample_size = 5L,
N_relative_mass_sample_size = 5L,
P_relative_mass_sample_size = 5L,
dplyr::across(dplyr::starts_with(c("C", "N", "P")) & !dplyr::ends_with("_sample_size") & where(is.numeric), function(.x) .x/1000),
dplyr::across(dplyr::any_of(c("mass_relative_mass", "mass_relative_mass_error")), function(.x) .x/100),
sampling_longitude = -2.129655,
sampling_latitude = 57.140269,
origin_sampling_longitude = -2.158629,
origin_sampling_latitude = 57.596976,
origin_site_name = "Middlemuir Moss",
water_table_depth = 19, #---note: mean water table depth in text
mass_absolute = NA_real_,
C_absolute = NA_real_,
N_absolute = NA_real_,
P_absolute = NA_real_,
is_incubated = TRUE,
incubation_environment = "container with peat",
id_dataset = datasets$id_dataset[[1]],
experimental_design =
paste0(
as.numeric(as.factor(sample_treatment))
),
site_label = origin_site_name
) %>%
dplyr::select(-id, -n, -variable)
# initial mass
samples2 <-
samples3 %>%
dplyr::mutate(
incubation_duration = 0,
mass_relative_mass = 1,
mass_relative_mass_error = 0,
dplyr::across(dplyr::any_of(c("C", "N", "P", "C_error", "N_error", "P_error", "C_error_type", "N_error_type", "P_error_type", "C_sample_size", "N_sample_size", "P_sample_size")), function(.x) NA)
)
# litter collection
samples1 <-
samples2 %>%
dplyr::filter(!duplicated(paste0(taxon_rank_value, "_", taxon_organ))) %>%
dplyr::mutate(
id_sample = seq_len(nrow(.)) + id_last$id_sample,
id_sample_origin = id_sample,
id_sample_parent = id_sample,
id_sample_incubation_start = NA_integer_,
site_label = origin_site_name,
site_name = site_label,
sampling_longitude = origin_sampling_longitude,
sampling_latitude = origin_sampling_latitude,
sample_treatment = "control",
experimental_design = NA_character_,
is_incubated = FALSE,
incubation_environment = NA_character_,
sample_depth_upper = NA_real_,
sample_depth_lower = NA_real_,
sampling_date = NA_real_,
sampling_year = NA_real_,
sampling_month = NA_real_,
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$id_sample),
id_sample_origin =
dplyr::left_join(
samples2 %>% dplyr::select(origin_site_name, taxon_rank_value, taxon_organ),
samples1 %>% dplyr::select(origin_site_name, taxon_rank_value, taxon_organ, id_sample),
by = c("origin_site_name", "taxon_rank_value", "taxon_organ")
) %>%
dplyr::pull(id_sample),
id_sample_incubation_start =
purrr::map_int(seq_len(nrow(.)), function(i) {
index <- paste0(taxon_rank_value, "_", site_label, "_", taxon_organ) == paste0(taxon_rank_value, "_", site_label, "_", taxon_organ)[[i]] & experimental_design == experimental_design[[i]] & incubation_duration == 0.0
id_sample[index]
}),
id_sample_parent =
purrr::map_int(seq_len(nrow(.)), function(i) {
index <- paste0(taxon_rank_value, "_", site_label, "_", taxon_organ) == paste0(taxon_rank_value, "_", site_label, "_", taxon_organ)[[i]] & experimental_design == experimental_design[[i]] & incubation_duration < incubation_duration[[i]]
if(! any(index)) {
id_sample_origin[[i]]
} else {
target_incubation_duration <- max(incubation_duration[index])
index <- index & incubation_duration == target_incubation_duration
id_sample[index]
}
})
) %>%
dplyr::mutate(
sample_type = "litter"
)
## combine
samples <-
dplyr::bind_rows(
db_template_tables$samples,
samples1 %>%
dplyr::mutate(
type = "samples1"
),
samples2
)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"
)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", "C_absolute", "N_absolute", "P_absolute", "water_table_depth")),
names_to = "attribute_name",
values_to = "value"
) %>%
dplyr::mutate(
id_measurement = seq_len(nrow(.)) + id_last$id_measurement,
id_measurement_numerator =
purrr::map_int(seq_len(nrow(.)), function(i) {
switch(
attribute_name[[i]],
"N_relative_mass" = ,
"C_relative_mass" = ,
"P_relative_mass" = {
id_measurement[id_sample == id_sample[[i]] & attribute_name == stringr::str_replace(attribute_name[[i]], "_relative_mass2?", "_absolute")]
},
"mass_relative_mass" = {
id_measurement[id_sample == id_sample[[i]] & attribute_name == "mass_absolute"]
},
NA_integer_
)
}),
id_measurement_denominator =
purrr::map_int(seq_len(nrow(.)), function(i) {
switch(
attribute_name[[i]],
"C_relative_mass" = ,
"N_relative_mass" = ,
"P_relative_mass" = {
id_measurement[id_sample == id_sample[[i]] & attribute_name == "mass_absolute"]
},
"mass_relative_mass" = {
id_measurement[id_sample == id_sample_incubation_start[[i]] & attribute_name == "mass_absolute"]
},
NA_integer_
)
}),
value_type =
dplyr::case_when(
attribute_name == "mesh_size_absolute" ~ "point",
TRUE ~ "mean"
),
comments_measurements =
dplyr::case_when(
attribute_name == "water_table_depth" ~ "Average water table depth during the experiment"
)
)
d2_sample_size <-
samples2 %>%
tidyr::pivot_longer(
cols = dplyr::ends_with("_sample_size"),
names_to = "attribute_name",
values_to = "sample_size"
) %>%
dplyr::mutate(
attribute_name =
attribute_name %>%
stringr::str_remove(pattern = "_sample_size$")
) %>%
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)
)
# combine
d <-
dplyr::bind_rows(
db_template_tables$data,
d2
) %>%
dplyr::select(dplyr::all_of(colnames(db_template_tables$data)))experimental_design_format <-
tibble::tibble(
id_dataset = datasets$id_dataset,
file = paste0(id_last$id_dataset + 1L, "/experimental_design_format.csv"),
experimental_design_description = "`sample_treatment`: Description of the treatment (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, sample_treatment)
# export
write.csv(experimental_design_format2, paste0(dir_target, "/experimental_design_format.csv"), row.names = FALSE)# 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)