81 lines
2.6 KiB
R
81 lines
2.6 KiB
R
#' Select the n most recent files
|
|
#'
|
|
#' @param data_folder The folder in which data files are located.
|
|
#' @param n The number of files to return. Defaults to 4.
|
|
#'
|
|
#' @details This function return the n most recent files and returns a
|
|
#' warning if the number wanted `n` is larger than the number of files.
|
|
#'
|
|
#' @return A vector of size `n` with the file path.
|
|
get_recent_files <- function(data_folder, n = 4, pattern = NULL) {
|
|
files_info <- file.info(file.path(data_folder, list.files(data_folder,
|
|
include.dirs = FALSE, pattern = pattern
|
|
)))
|
|
files_info[["filepath"]] <- file.path(data_folder, list.files(data_folder,
|
|
include.dirs = FALSE, pattern = pattern
|
|
))
|
|
files_info <- sort_by(files_info, files_info[["ctime"]], decreasing = TRUE)
|
|
if (n > nrow(files_info)) {
|
|
warning(
|
|
"n = ", n,
|
|
" is too large ! It should be at most ",
|
|
nrow(files_info)
|
|
)
|
|
}
|
|
return(head(files_info[["filepath"]], n = n))
|
|
}
|
|
|
|
#' Identify models
|
|
identify_models <- function(files_vec, pattern = "(iid|pirho|pi|rho)") {
|
|
names(files_vec) <- stringr::str_extract(
|
|
string = files_vec,
|
|
pattern = pattern
|
|
)
|
|
return(files_vec)
|
|
}
|
|
|
|
build_graph_size_dataframe <- function(collection_list) {
|
|
if (!is.list(collection_list)) {
|
|
return(data.frame(
|
|
collection_id = factor(1L),
|
|
M = collection_list[["M"]],
|
|
net_id = factor(collection_list[["net_id"]]),
|
|
nr = collection_list[["n"]][[1]],
|
|
nc = collection_list[["n"]][[2]],
|
|
Qr = collection_list[["Q"]][[1]],
|
|
Qc = collection_list[["Q"]][[2]]
|
|
))
|
|
}
|
|
do.call("rbind", lapply(seq_len(length(collection_list)), function(idx) {
|
|
collection <- collection_list[[idx]]
|
|
data.frame(
|
|
collection_id = factor(idx),
|
|
M = collection[["M"]],
|
|
net_id = factor(collection[["net_id"]]),
|
|
nr = collection[["n"]][[1]],
|
|
nc = collection[["n"]][[2]],
|
|
Qr = collection[["Q"]][[1]],
|
|
Qc = collection[["Q"]][[2]]
|
|
)
|
|
}))
|
|
}
|
|
|
|
extract_clustering <- function(clustering) {
|
|
partition <- colSBM::extract_best_partition(
|
|
l = clustering,
|
|
unnest = TRUE
|
|
)
|
|
if (!is.list(partition)) {
|
|
partition <- list(partition)
|
|
}
|
|
out <- unlist(sapply(seq_len(length(partition)), function(idx) {
|
|
clust_vec <- rep(idx, partition[[idx]][["M"]])
|
|
names(clust_vec) <- partition[[idx]][["net_id"]]
|
|
clust_vec
|
|
}))
|
|
if (is.matrix(out)) {
|
|
nm <- rownames(out)
|
|
out <- setNames(c(out), nm)
|
|
}
|
|
return(out)
|
|
}
|