# 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 <- "d63"
dir_source <- "../raw_data/data/d63"
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("Golovatskaya.2017")
)
)# mass remaining
samples3 <-
readRDS(paste0(dir_source, "/raw/caldat/Golovatskaya.2017-Fig2a"))$processed_data %>%
dplyr::select(id, mean, error) %>%
dplyr::rename(
mass_relative_mass = "mean",
mass_relative_mass_error = "error"
) %>%
dplyr::mutate(
mass_relative_mass_sample_size = 5L,
mass_absolute = NA_real_,
mesh_size_absolute = NA_real_,
id_dataset = datasets$id_dataset[[1]],
taxon_rank_name = "species",
taxon_rank_value =
dplyr::case_when(
stringr::str_detect(id, "angustifolium") ~ "Sphagnum angustifolium",
stringr::str_detect(id, "fuscum") ~ "Sphagnum fuscum"
),
taxon_organ = "whole plant",
site_name =
id %>%
stringr::str_extract(pattern = "site[A-Za-z]+_") %>%
stringr::str_remove(pattern = "^site") %>%
stringr::str_remove(pattern = "_$"),
is_incubated = TRUE,
incubation_duration =
id %>%
stringr::str_extract(pattern = "time\\d+$") %>%
stringr::str_remove(pattern = "^time") %>%
as.numeric() %>%
lubridate::dmonths() %>%
lubridate::time_length(unit = "days"),
incubation_environment = "peat",
sample_type = "litter",
sample_treatment = "control",
sample_depth_upper = 10,
sample_depth_lower = 10,
sampling_longitude =
dplyr::case_when(
site_name == "Bakcharskoe" ~ 82.075551,
TRUE ~ 85.004164
),
sampling_latitude =
dplyr::case_when(
site_name == "Bakcharskoe" ~ 57.021004,
TRUE ~ 56.506168
),
comments_samples = "Coordinates are only the approximate location of the site, but not the exact sampling point.",
sampling_date =
as.Date("2008-09-15") + lubridate::ddays(incubation_duration),
sampling_year = lubridate::year(sampling_date),
sampling_month = lubridate::month(sampling_date),
sampling_day = NA_real_,
experimental_design =
paste0(
as.numeric(as.factor(site_name))
)
)
# initial mass
samples2 <-
samples3 %>%
dplyr::filter(incubation_duration == 243.50) %>%
dplyr::mutate(
incubation_duration = 0.0,
mass_relative_mass = 1.0,
mass_relative_mass_error = 0.0,
sampling_date = as.Date("2008-09-15"),
sampling_year = lubridate::year(sampling_date),
sampling_month = lubridate::month(sampling_date),
sampling_day = NA_real_,
experimental_design =
paste0(
as.numeric(as.factor(site_name))
)
)
# litter collection
samples1 <-
samples2 %>%
dplyr::mutate(
id_sample = seq_len(nrow(.)) + id_last$id_sample,
id_sample_parent = id_sample,
id_sample_origin = id_sample,
is_incubated = FALSE,
incubation_environment = NA_character_,
mass_relative_mass = NA_real_,
mass_relative_mass_error = NA_real_,
sample_type = "vegetation",
sample_depth_upper = 0,
sample_depth_lower = 10,
sampling_date = as.Date("2008-09-15"),
sampling_year = lubridate::year(sampling_date),
sampling_month = lubridate::month(sampling_date),
sampling_day = NA_real_,
experimental_design =
paste0(
as.numeric(as.factor(site_name))
)
)
# add missing ids
samples2 <-
dplyr::bind_rows(
samples2 %>%
dplyr::mutate(
type = "samples2"
),
samples3 %>%
dplyr::mutate(
type = "samples3"
)
)
samples2 <-
samples2 %>%
dplyr::mutate(
id_sample = seq_len(nrow(.)) + max(samples1$id_sample),
id_sample_origin =
dplyr::left_join(
samples2 %>%
dplyr::select(site_name, taxon_rank_value),
samples1 %>% dplyr::select(site_name, taxon_rank_value, id_sample),
by = c("site_name", "taxon_rank_value")
) %>%
dplyr::pull(id_sample),
id_sample_incubation_start =
purrr::map_int(seq_len(nrow(.)), function(i) {
index <- paste0(taxon_rank_value, "_", site_name, "_", taxon_organ, "_", sample_depth_upper) == paste0(taxon_rank_value, "_", site_name, "_", taxon_organ, "_", sample_depth_upper)[[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_name, "_", taxon_organ, "_", sample_depth_upper) == paste0(taxon_rank_value, "_", site_name, "_", taxon_organ, "_", sample_depth_upper)[[i]] & experimental_design == experimental_design[[i]] & incubation_duration < (incubation_duration[[i]] - 10)
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]
}
})
)
# litter chemistry
d63_litter_chemistry <-
dplyr::left_join(
readRDS(paste0(dir_source, "/raw/caldat/Golovatskaya.2017-Fig3a"))$processed_data %>%
dplyr::rename(
C_relative_mass2 = "mean",
C_relative_mass2_error = "error"
) %>%
dplyr::mutate(
C_relative_mass2_sample_size = 5L,
C_relative_mass2_error_type = "se"
) %>%
dplyr::select(-n, -variable),
readRDS(paste0(dir_source, "/raw/caldat/Golovatskaya.2017-Fig3b"))$processed_data %>%
dplyr::rename(
N_relative_mass2 = "mean",
N_relative_mass2_error = "error"
) %>%
dplyr::mutate(
N_relative_mass2_sample_size = 5L,
N_relative_mass2_error_type = "se"
) %>%
dplyr::select(-n, -variable),
by = "id"
) %>%
dplyr::full_join(
readRDS(paste0(dir_source, "/raw/caldat/Golovatskaya.2017-Fig4"))$processed_data %>%
dplyr::rename(
ash_mass_relative_mass = "mean",
ash_mass_relative_mass_error = "error"
) %>%
dplyr::mutate(
ash_mass_relative_mass_sample_size = 5L,
ash_mass_relative_mass_error_type = "se"
) %>%
dplyr::select(-n, -variable),
by = "id"
) %>%
dplyr::mutate(
taxon_rank_value =
dplyr::case_when(
stringr::str_detect(id, "angustifolium") ~ "Sphagnum angustifolium",
stringr::str_detect(id, "fuscum") ~ "Sphagnum fuscum"
),
site_name =
id %>%
stringr::str_extract(pattern = "site[A-Za-z]+_") %>%
stringr::str_remove(pattern = "^site") %>%
stringr::str_remove(pattern = "_$"),
incubation_duration =
id %>%
stringr::str_extract(pattern = "time\\d+$") %>%
stringr::str_remove(pattern = "^time") %>%
as.numeric() %>%
lubridate::dmonths() %>%
lubridate::time_length(unit = "days"),
dplyr::across(
dplyr::contains("relative_mass2") & where(is.numeric),
function(.x) .x/100
)
) %>%
dplyr::select(-id)
d63_litter_chemistry <-
dplyr::bind_rows(
d63_litter_chemistry,
readODS::read_ods(paste0(dir_source, "/derived/Golovatskaya.2017-Tab3.ods")) %>%
dplyr::select(-is_incubated, -comments_measurements) %>%
dplyr::mutate(
dplyr::across(
dplyr::contains("relative_mass") & where(is.numeric),
function(.x) .x/100
)
)
) %>%
dplyr::mutate(
C_absolute = NA_real_,
N_absolute = NA_real_,
ash_mass_absolute = NA_real_
)
# bind to samples2
samples2 <-
dplyr::left_join(
samples2,
d63_litter_chemistry,
by = c("site_name", "incubation_duration", "taxon_rank_value")
)
# water table depth
samples4 <-
readRDS(paste0(dir_source, "/raw/caldat/Golovatskaya.2017-Fig1"))$processed_data %>%
dplyr::rename(
water_table_depth = "mean",
water_table_depth_error = "error"
) %>%
dplyr::mutate(
water_table_depth = water_table_depth * (-1),
water_table_depth_error_type = "sd",
id_dataset = datasets$id_dataset,
id_sample = seq_len(nrow(.)) + max(samples2$id_sample),
id_sample_parent = id_sample,
id_sample_origin = id_sample,
is_incubated = FALSE,
incubation_duration = 0.0,
sample_type = "peat",
sample_treatment = "control",
sample_depth_upper = 0,
sample_depth_lower = 0,
comments_samples = "Coordinates are only the approximate location of the site, but not the exact sampling point.",
site_name =
id %>%
stringr::str_extract(pattern = "site[A-Za-z]+_") %>%
stringr::str_remove(pattern = "^site") %>%
stringr::str_remove(pattern = "_$"),
sampling_month =
id %>%
stringr::str_extract(pattern = "month\\d+$") %>%
stringr::str_remove(pattern = "^month") %>%
as.numeric(),
sampling_day = NA_real_,
sampling_year = NA_real_
) %>%
dplyr::left_join(
samples1 %>%
dplyr::filter(!duplicated(site_name)) %>%
dplyr::select(site_name, sampling_longitude, sampling_latitude, experimental_design),
by = "site_name"
)
## combine
samples <-
dplyr::bind_rows(
db_template_tables$samples,
samples1 %>%
dplyr::mutate(
type = "samples1"
),
samples2,
samples4 %>%
dplyr::mutate(
type = "samples4"
)
)samples_to_samples <-
samples %>%
dplyr::filter(! id_sample %in% id_sample_origin) %>%
dplyr::mutate(
transition_description =
dplyr::case_when(
type %in% c("samples2") ~ "translocate",
type %in% c("samples3") ~ "wait",
TRUE ~ NA_character_
)
) %>%
dplyr::select(id_sample_parent, id_sample, transition_description) %>%
dplyr::rename(
id_sample_child = "id_sample"
)d2 <-
samples2 %>%
tidyr::pivot_longer(
cols = dplyr::any_of(c("mass_absolute", "mass_relative_mass", "mesh_size_absolute",
paste0(PeriodicTable:::periodicTable$symb, "_relative_mass"),
paste0(PeriodicTable:::periodicTable$symb, "_relative_mass2"),
paste0(PeriodicTable:::periodicTable$symb, "_absolute"), "ash_mass_relative_mass", "ash_mass_absolute", "C_to_N")),
names_to = "attribute_name",
values_to = "value"
) %>%
dplyr::mutate(
id_measurement = seq_len(nrow(.)) + id_last$id_measurement,
id_measurement_numerator =
purrr::map_int(seq_len(nrow(.)), function(i) {
if(attribute_name[[i]] == "mass_relative_mass") {
id_measurement[id_sample == id_sample[[i]] & attribute_name == "mass_absolute"]
} else if (stringr::str_detect(attribute_name[[i]], pattern = "_relative_mass$")) {
id_measurement[id_sample == id_sample[[i]] & attribute_name == stringr::str_replace(attribute_name[[i]], "_relative_mass2?", "_absolute")]
} else if (attribute_name[[i]] == "C_to_N") {
id_measurement[id_sample == id_sample[[i]] & attribute_name == "C_absolute"]
} else {
NA_integer_
}
}),
id_measurement_denominator =
purrr::map_int(seq_len(nrow(.)), function(i) {
if(attribute_name[[i]] == "mass_relative_mass") {
id_measurement[id_sample == id_sample_incubation_start[[i]] & attribute_name == "mass_absolute"]
} else if (stringr::str_detect(attribute_name[[i]], pattern = "_relative_mass$")) {
id_measurement[id_sample == id_sample[[i]] & attribute_name == "mass_absolute"]
} else if (attribute_name[[i]] == "C_to_N") {
id_measurement[id_sample == id_sample[[i]] & attribute_name == "N_absolute"]
} else {
NA_integer_
}
}),
value_type =
dplyr::case_when(
attribute_name %in% c("mesh_size_absolute") ~ "point",
TRUE ~ "mean"
),
comments_measurements = "`error_type`: Guessed. `sample_size`: Guessed based on text (five litterbags per sampling time)."
)
d2_sample_size <-
samples2 %>%
tidyr::pivot_longer(
cols = dplyr::ends_with("_sample_size"),
names_to = "attribute_name",
values_to = "sample_size"
) %>%
dplyr::mutate(
attribute_name =
attribute_name %>%
stringr::str_remove(pattern = "_sample_size$")
) %>%
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)
)
# update attribute_name
d2 <-
d2 %>%
dplyr::mutate(
attribute_name =
dplyr::case_when(
attribute_name == "C_relative_mass2" ~ "C_relative_mass",
attribute_name == "N_relative_mass2" ~ "N_relative_mass",
TRUE ~ attribute_name
)
)
# water table depth
d4 <-
samples4 %>%
tidyr::pivot_longer(
cols = dplyr::any_of("water_table_depth"),
names_to = "attribute_name",
values_to = "value"
) %>%
dplyr::mutate(
id_measurement = seq_len(nrow(.)) + max(d2$id_measurement),
value_type =
dplyr::case_when(
attribute_name %in% c("mesh_size_absolute") ~ "point",
TRUE ~ "mean"
),
comments_measurements = "`error_type`: Guessed."
)
d4_error <-
samples4 %>%
tidyr::pivot_longer(
cols = dplyr::ends_with(c("_error")),
names_to = "attribute_name",
values_to = "error"
) %>%
dplyr::mutate(
attribute_name =
attribute_name %>%
stringr::str_remove(pattern = "_error$")
) %>%
dplyr::select(id_sample, attribute_name, error)
d4_error_type <-
samples4 %>%
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$")
) %>%
dplyr::select(id_sample, attribute_name, error_type)
d4 <-
d4 %>%
dplyr::mutate(
error =
dplyr::left_join(d4, d4_error, by = c("id_sample", "attribute_name")) %>%
dplyr::pull(error),
error_type =
dplyr::left_join(d4, d4_error_type, by = c("id_sample", "attribute_name")) %>%
dplyr::pull(error_type)
)
# combine
d <-
dplyr::bind_rows(
db_template_tables$data,
d2,
d4
) %>%
dplyr::select(dplyr::all_of(colnames(db_template_tables$data)))experimental_design_format <-
tibble::tibble(
id_dataset = datasets$id_dataset,
file = paste0(id_last$id_dataset + 1L, "/experimental_design_format.csv"),
experimental_design_description = "`site_name`: Name of the site where the samples were incubated."
)
# csv file to export
experimental_design_format2 <-
samples %>%
dplyr::filter(! is.na(experimental_design)) %>%
dplyr::filter(! duplicated(experimental_design)) %>%
dplyr::select(experimental_design, site_name)
# export
write.csv(experimental_design_format2, paste0(dir_target, "/experimental_design_format.csv"), row.names = FALSE)# list all tables
dm_insert_in <-
list(
datasets =
datasets %>%
dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$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)))) {
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 = ", ")))
RMariaDB::dbDisconnect(con)
}
# 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)