# 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 <- "d17"
dir_source <- "../raw_data/data/d17"
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("Sanger.1994")
)
)## mass remaining
samples2 <-
dplyr::bind_rows(
readRDS(paste0(dir_source, "/raw/caldat/Sanger.1994-Fig7a"))$processed_data %>%
dplyr::mutate(
taxon_rank_value = "Eriophorum angustifolium"
),
readRDS(paste0(dir_source, "/raw/caldat/Sanger.1994-Fig7b"))$processed_data %>%
dplyr::mutate(
taxon_rank_value = "Calluna vulgaris"
)
) %>%
dplyr::mutate(
id_replicate =
stringr::str_extract(id, pattern = "\\d+$") %>%
as.numeric(),
site_name = rep(c("Strathwaich", "Gisla", "Mharcaidh", "Waterhead", "Malham", "Chartley", "Glen Dye", "High Muffles", "Hatfield"), 8)
) %>%
dplyr::arrange(taxon_rank_value, site_name, dplyr::desc(id_replicate)) %>%
dplyr::mutate(
mass_remaining = c(y[-length(y)] - y[-1], y[[length(y)]]),
mass_remaining =
dplyr::case_when(
id_replicate == 1 ~ y,
TRUE ~ mass_remaining
),
mass_remaining = mass_remaining/2,
mass_relative_mass = mass_remaining,
incubation_duration =
lubridate::dmonths(12) %>%
lubridate::time_length(unit = "days"),
sampling_longitude = -2.115605, #---note: location of no special point in Aberdeen (location of the greenhouse)
sampling_latitude = 57.146018, #---note: location of no special point in Aberdeen (location of the greenhouse)
sampling_date = NA,
taxon_rank_name = "species",
sample_type = "vegetation",
taxon_organ = "leaves",
mesh_size = 1,
mass_absolute = NA_real_,
is_incubated = TRUE,
incubation_environment = "peat",
experimental_design = paste0(as.numeric(as.factor(site_name)), "_", id_replicate),
id_dataset = datasets$id_dataset[[1]],
comments_samples = "Only approximate coordinates for the location are given."
)
# initial masses
samples1 <-
samples2 %>%
dplyr::mutate(
is_incubated = FALSE,
id_sample = seq_len(nrow(.)) + id_last$id_sample,
id_sample_origin = id_sample,
id_sample_parent = id_sample,
id_sample_incubation_start = id_sample,
incubation_duration = 0,
mass_relative_mass = 1
)
# assign ids
samples2 <-
samples2 %>%
dplyr::mutate(
id_sample = seq_len(nrow(.)) + max(samples1$id_sample),
id_sample_origin =
dplyr::left_join(
samples2 %>% dplyr::select(taxon_rank_value, site_name, id_replicate),
samples1 %>% dplyr::select(taxon_rank_value, site_name, id_replicate, id_sample),
by = c("taxon_rank_value", "site_name", "id_replicate")
) %>%
dplyr::pull(id_sample),
id_sample_parent = id_sample_origin,
id_sample_incubation_start = id_sample_origin
)
## combine
samples <-
dplyr::bind_rows(
db_template_tables$samples,
samples1 %>%
dplyr::mutate(
type = "samples1"
),
samples2 %>%
dplyr::mutate(
type = "samples2"
)
)samples_to_samples <-
samples %>%
dplyr::filter(! id_sample %in% id_sample_origin) %>%
dplyr::mutate(
transition_description =
dplyr::case_when(
type %in% c("samples2") ~ "wait",
TRUE ~ NA_character_
)
) %>%
dplyr::select(id_sample_parent, id_sample, transition_description) %>%
dplyr::rename(
id_sample_child = "id_sample"
)d1 <-
samples1 %>%
tidyr::pivot_longer(
cols = dplyr::all_of(c("mass_absolute", "mass_relative_mass")),
names_to = "attribute_name",
values_to = "value"
) %>%
dplyr::mutate(
id_measurement = seq_len(nrow(.)) + id_last$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$"), "_absolute")]
},
NA_integer_
)
}),
id_measurement_denominator =
purrr::map_int(seq_len(nrow(.)), function(i) {
switch(
attribute_name[[i]],
"mass_relative_mass" =,
"P_relative_mass" =,
"N_relative_mass" =,
"K_relative_mass" =,
"C_relative_mass" =,
"ash_mass_relative_mass" = {
id_measurement[id_sample == id_sample[[i]] & attribute_name == "mass_absolute"]
},
NA_integer_
)
}),
value_type = "point",
sample_size = 1L
)
d2 <-
samples2 %>%
tidyr::pivot_longer(
cols = dplyr::all_of(c("mass_absolute", "mass_relative_mass")),
names_to = "attribute_name",
values_to = "value"
) %>%
dplyr::mutate(
id_measurement = seq_len(nrow(.)) + max(d1$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" = {
d1$id_measurement[d1$id_sample == id_sample_origin[[i]] & d1$attribute_name == "mass_absolute"]
},
NA_integer_
)
}),
value_type = "point",
sample_size = 1L
)
# combine
d <-
dplyr::bind_rows(
db_template_tables$data,
d1,
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$id_dataset + 1L, "/experimental_design_format.csv"),
experimental_design_description = "`site_name`: Name of the site. `id_replicate`: An identifier for the litterbag replicate."
)
# csv file to export
experimental_design_format2 <-
samples %>%
dplyr::filter(! is.na(experimental_design)) %>%
dplyr::filter(! duplicated(experimental_design)) %>%
dplyr::select(experimental_design, site_name, id_replicate)
# export
write.csv(experimental_design_format2, paste0(dir_target, "/experimental_design_format.csv"), row.names = FALSE)# list all tables
dm_insert_in <-
list(
datasets =
datasets %>%
dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$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)