rapids/src/data/translate_usernames_into_participants_data.R

source("renv/activate.R")
source("src/data/streams/aware_postgresql/container.R")

library(RPostgres)
library(magrittr)
library(tidyverse)
library(lubridate)

prepare_participants_file <- function() {

  username_list_csv_location <- snakemake@input[["username_list"]]

  data_configuration <- snakemake@params[["data_configuration"]]
  participants_container <- snakemake@params[["participants_table"]]
  device_id_container <- snakemake@params[["device_id_table"]]
  start_end_date_container <- snakemake@params[["start_end_date_table"]]

  output_data_file <- snakemake@output[["participants_file"]]

  platform <- "android"
  pid_format <- "p%03d"
  datetime_format <- "%Y-%m-%d %H:%M:%S"

  participant_data <- read_csv(username_list_csv_location, col_types = "cc", progress = FALSE)
  usernames <- participant_data$label

  participant_ids <- pull_participants_ids(data_configuration, usernames, participants_container)
  participant_data %<>%
    left_join(participant_ids, by = c("label" = "username")) %>%
    rename(participant_id = id)

  device_ids <- pull_participants_device_ids(data_configuration, participant_data$participant_id, device_id_container)
  device_ids %<>%
    filter(device_id != "") %>%
    group_by(participant_id) %>%
    summarise(device_ids = list(unique(device_id)))
  participant_data %<>%
    left_join(device_ids, by = "participant_id")

  start_end_datetimes <- pull_participants_start_end_dates(data_configuration, participant_data$participant_id, start_end_date_container)
  participant_data %<>%
    left_join(start_end_datetimes, by = "participant_id")

  participant_data %<>%
  mutate(
    pid = sprintf(pid_format, participant_id),
    start_date = strftime(datetime_start, format=datetime_format, tz = "UTC", usetz = FALSE), #TODO Check what timezone is expected
    end_date = strftime(datetime_end, format=datetime_format, tz = "UTC", usetz = FALSE),
    device_id = map_chr(device_ids, str_c, collapse = ";"),
    number_of_devices = map_int(device_ids, length),
    fitbit_id = ""
    ) %>%
  rowwise() %>%
  mutate(platform = str_c(replicate(number_of_devices, platform), collapse = ";")) %>%
  ungroup() %>%
  arrange(pid) %>%
  select(pid, label, start_date, end_date, empatica_id, device_id, platform, fitbit_id)

  write_csv(participant_data, output_data_file)
}

prepare_participants_file()