# 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 <- "d16"
dir_source <- "../raw_data/data/d16"
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("Hogg.1992")
)
)## mass remaining
samples3 <-
dplyr::bind_rows(
readRDS(paste0(dir_source, "/raw/caldat/Hogg.1992-Fig2a"))$processed_data %>%
dplyr::mutate(
sample_treatment = "flooded"
),
readRDS(paste0(dir_source, "/raw/caldat/Hogg.1992-Fig2b"))$processed_data %>%
dplyr::mutate(
sample_treatment = "drained"
)
) %>%
dplyr::mutate(
temperature =
id %>%
stringr::str_extract(pattern = "\\d+$") %>%
as.numeric() %>%
magrittr::add(273.15),
water_table_depth =
dplyr::case_when(
sample_treatment == "flooded" ~ 0,
TRUE ~ NA_real_
),
sample_depth_lower =
dplyr::case_when(
stringr::str_detect(id ,pattern = "layer1") ~ 10,
stringr::str_detect(id ,pattern = "layer2") ~ 20,
stringr::str_detect(id ,pattern = "layer4") ~ 40
),
sample_depth_upper =
dplyr::case_when(
stringr::str_detect(id ,pattern = "layer1") ~ 0,
stringr::str_detect(id ,pattern = "layer2") ~ 10,
stringr::str_detect(id ,pattern = "layer4") ~ 30
),
sample_type = "peat",
incubation_duration = 125,
mass_absolute = NA_real_,
mass_relative_mass = (100 - mean)/100,
mass_remaining_error = error/100,
mass_remaining_error_type = "se",
mass_remaining_sample_size = n,
comments_samples = "Peat samples are formed by Sphagnum or Pleurozium or wood remains.",
sampling_longitude = NA_real_,
sampling_latitude = NA_real_,
id_dataset = datasets$id_dataset[[1]],
is_incubated = TRUE,
incubation_environment = "container",
experimental_design =
paste0(as.numeric(as.factor(sample_treatment)), "_", as.numeric(as.factor(temperature)))
)
# initial samples
samples2 <-
samples3 %>%
dplyr::mutate(
mass_relative_mass = 1,
incubation_duration = 0
)
# initial samples during collection
samples1 <-
samples2 %>%
dplyr::filter(!duplicated(sample_depth_upper)) %>%
dplyr::mutate(
is_incubated = FALSE,
id_sample = seq_len(nrow(.)) + id_last$id_sample,
id_sample_origin = id_sample,
id_sample_parent = id_sample,
id_sample_incubation_start = NA_integer_,
sample_microhabitat = "lawn",
sample_treatment = "control",
experimental_design = NA_character_,
sampling_longitude =
"115°07'W" %>%
sp::char2dms(chd = "°", chm = "'", chs = "''") %>%
as.numeric(),
sampling_latitude =
"53°40'N" %>%
sp::char2dms(chd = "°", chm = "'", chs = "''") %>%
as.numeric(),
incubation_environment = NA_character_,
sampling_date = as.Date("1988-10-31"),
sampling_year = lubridate::year(sampling_date),
sampling_month = lubridate::month(sampling_date),
comments_samples = "Only approximate coordinates for the location are given. Peat samples are formed by Sphagnum or Pleurozium or wood remains."
)
# assign ids
samples2 <-
samples2 %>%
dplyr::mutate(
id_sample = seq_len(nrow(.)) + max(samples1$id_sample),
id_sample_origin =
dplyr::left_join(
samples2 %>% dplyr::select(sample_depth_upper),
samples1 %>% dplyr::select(id_sample ,sample_depth_upper),
by = "sample_depth_upper"
) %>%
dplyr::pull(id_sample),
id_sample_incubation_start = id_sample,
id_sample_parent = id_sample_origin
)
samples3 <-
samples3 %>%
dplyr::mutate(
id_sample = seq_len(nrow(.)) + max(samples2$id_sample),
id_sample_origin = samples2$id_sample_origin,
id_sample_parent = samples2$id_sample,
id_sample_incubation_start = samples2$id_sample
)
# peat element contents and bulk density before incubation and pH value of flooded treatments after 120 days of incubation
samples1 <-
dplyr::left_join(
samples1,
readODS::read_ods(paste0(dir_source, "/derived/Hogg.1992-Tab1_4.ods")) %>%
dplyr::filter(treatment == "control") %>%
dplyr::select(dplyr::all_of(c("sample_depth_upper", "bulk_density", "ash_content", "C", "N", "P", "K"))) %>%
dplyr::rename_with(.cols = dplyr::all_of(c("C", "N", "P", "K")), .fn = function(.x) paste0(.x, "_relative_mass")) %>%
dplyr::rename(
ash_mass_relative_mass = "ash_content"
) %>%
dplyr::mutate(
dplyr::across(
dplyr::all_of(paste0(c("C", "N", "P", "K", "ash_mass"), "_relative_mass")),
function(.x) .x/100
),
C_absolute = NA_real_,
N_absolute = NA_real_,
P_absolute = NA_real_,
K_absolute = NA_real_,
ash_mass_absolute = NA_real_
),
by = "sample_depth_upper"
)
## combine
samples <-
dplyr::bind_rows(
db_template_tables$samples,
samples1 %>%
dplyr::mutate(
type = "samples1"
),
samples2 %>%
dplyr::mutate(
type = "samples2"
),
samples3 %>%
dplyr::mutate(
type = "samples3"
)
)samples_to_samples <-
samples %>%
dplyr::filter(! id_sample %in% id_sample_origin) %>%
dplyr::mutate(
transition_description =
dplyr::case_when(
type %in% c("samples2") ~ "translocate",
type %in% c("samples3") ~ "wait",
TRUE ~ NA_character_
)
) %>%
dplyr::select(id_sample_parent, id_sample, transition_description) %>%
dplyr::rename(
id_sample_child = "id_sample"
)d1 <-
samples1 %>%
tidyr::pivot_longer(
cols = dplyr::all_of(c("mass_absolute", "bulk_density", "ash_mass_relative_mass", "ash_mass_absolute", "P_relative_mass", "N_relative_mass", "K_relative_mass", "C_relative_mass", "P_absolute", "N_absolute", "K_absolute", "C_absolute")),
names_to = "attribute_name",
values_to = "value"
) %>%
dplyr::mutate(
id_measurement = seq_len(nrow(.)) + id_last$id_measurement,
id_measurement_numerator =
purrr::map_int(seq_len(nrow(.)), function(i) {
switch(
attribute_name[[i]],
"mass_relative_mass" = {
id_measurement[id_sample == id_sample[[i]] & attribute_name == "mass_absolute"]
},
"P_relative_mass" =,
"N_relative_mass" =,
"K_relative_mass" =,
"C_relative_mass" =,
"ash_mass_relative_mass" = {
id_measurement[id_sample == id_sample[[i]] & attribute_name == paste0(stringr::str_remove(attribute_name[[i]], "_relative_mass$"), "_absolute")]
},
NA_integer_
)
}),
id_measurement_denominator =
purrr::map_int(seq_len(nrow(.)), function(i) {
switch(
attribute_name[[i]],
"mass_relative_mass" =,
"P_relative_mass" =,
"N_relative_mass" =,
"K_relative_mass" =,
"C_relative_mass" =,
"ash_mass_relative_mass" = {
id_measurement[id_sample == id_sample[[i]] & attribute_name == "mass_absolute"]
},
NA_integer_
)
}),
value_type = "mean",
sample_size =
dplyr::case_when(
attribute_name %in% c("mass_relative_mass") ~ 6L,
TRUE ~ NA_integer_
)
)
d2 <-
samples2 %>%
tidyr::pivot_longer(
cols = dplyr::all_of(c("mass_absolute", "mass_relative_mass", "temperature", "water_table_depth")),
names_to = "attribute_name",
values_to = "value"
) %>%
dplyr::mutate(
id_measurement = seq_len(nrow(.)) + max(d1$id_measurement),
id_measurement_numerator =
purrr::map_int(seq_len(nrow(.)), function(i) {
switch(
attribute_name[[i]],
"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]],
"mass_relative_mass" = {
id_measurement[id_sample == id_sample[[i]] & attribute_name == "mass_absolute"]
},
NA_integer_
)
}),
value_type =
dplyr::case_when(
attribute_name %in% c("mass_relative_mass", "mass_absolute") ~ "mean",
TRUE ~ "point"
),
sample_size =
dplyr::case_when(
attribute_name %in% c("mass_relative_mass", "mass_absolute") ~ 6L,
TRUE ~ NA_integer_
)
)
d3 <-
samples3 %>%
tidyr::pivot_longer(
cols = dplyr::all_of(c("mass_absolute", "mass_relative_mass", "temperature", "water_table_depth")),
names_to = "attribute_name",
values_to = "value"
) %>%
dplyr::mutate(
id_measurement = seq_len(nrow(.)) + max(d2$id_measurement),
id_measurement_numerator =
purrr::map_int(seq_len(nrow(.)), function(i) {
switch(
attribute_name[[i]],
"mass_relative_mass" = {
id_measurement[id_sample == id_sample[[i]] & attribute_name == "mass_absolute"]
},
NA_integer_
)
}),
id_measurement_denominator =
purrr::map_int(seq_len(nrow(.)), function(i) {
switch(
attribute_name[[i]],
"mass_relative_mass" = {
d2$id_measurement[d2$id_sample == id_sample_incubation_start[[i]] & d2$attribute_name == "mass_absolute"]
},
NA_integer_
)
}),
value_type =
dplyr::case_when(
attribute_name %in% c("mass_relative_mass", "mass_absolute") ~ "mean",
TRUE ~ "point"
),
sample_size =
dplyr::case_when(
attribute_name %in% c("mass_relative_mass", "mass_absolute") ~ 6L,
TRUE ~ NA_integer_
)
) %>%
dplyr::select(-error)
d3_error <-
samples3 %>%
tidyr::pivot_longer(
cols = dplyr::all_of("error"),
names_to = "attribute_name",
values_to = "error"
) %>%
dplyr::mutate(
attribute_name = "mass_relative_mass"
) %>%
dplyr::select(id_sample, attribute_name, error)
d3 <-
d3 %>%
dplyr::mutate(
error =
dplyr::left_join(d3, d3_error, by = c("id_sample", "attribute_name")) %>%
dplyr::pull(error),
error_type =
dplyr::case_when(
is.na(error) ~ NA_character_,
TRUE ~ "se"
)
)
# combine
d <-
dplyr::bind_rows(
db_template_tables$data,
d1,
d2,
d3
) %>%
dplyr::select(dplyr::all_of(colnames(db_template_tables$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`: A label for the moisture conditions. `temperature`: The temperature [K]."
)
# 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, temperature)
# 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)