junos
/
rapids
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Add parameters to yaml file. 

And use these in the prepare_participants_file function.
labels
junos 2021-11-29 16:57:50 +01:00
parent 39bd244511
commit 181e4f0118
2 changed files with 16 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
rules/preprocessing.smk
View File

@ -7,6 +7,11 @@ rule create_example_participant_files:
rule prepare_participants_csv: rule prepare_participants_csv:
input: input:
username_list = config["CREATE_PARTICIPANT_FILES"]["USERNAMES_CSV"] username_list = config["CREATE_PARTICIPANT_FILES"]["USERNAMES_CSV"]
params:
data_configuration = config["PHONE_DATA_STREAMS"][config["PHONE_DATA_STREAMS"]["USE"]],
participants_table = "participants",
device_id_table = "light_sensor",
start_end_date_table = "esm"
output: output:
participants_file = config["CREATE_PARTICIPANT_FILES"]["CSV_FILE_PATH"] participants_file = config["CREATE_PARTICIPANT_FILES"]["CSV_FILE_PATH"]
script: script:

39
src/data/translate_usernames_into_participants_data.R
View File

@ -3,46 +3,29 @@ library(magrittr)
library(tidyverse) library(tidyverse)
library(lubridate) library(lubridate)
load_container_script <- function(stream_container){
language <- if_else(endsWith(tolower(stream_container), "py"), "python", "r")
if(language == "python"){
library(reticulate)
container <- import_from_path(gsub(pattern = "\\.py$", "", basename(stream_container)), path = dirname(stream_container))
if(!py_has_attr(container, "pull_data"))
stop(paste0("The following container.py script does not have a pull_data function: ", stream_container))
if(!py_has_attr(container, "infer_device_os"))
stop(paste0("The following container.py script does not have a infer_device_os function: ", stream_container))
return(list("infer_device_os" = container$infer_device_os, "pull_data" = container$pull_data))
} else if(language == "r"){
source(stream_container)
if(!exists("pull_data"))
stop(paste0("The following container.R script does not have a pull_data function: ", stream_container))
if(!exists("infer_device_os"))
stop(paste0("The following container.R script does not have a infer_device_os function: ", stream_container))
return(list("infer_device_os" = infer_device_os, "pull_data" = pull_data))
}
}
prepare_participants_file <- function() { prepare_participants_file <- function() {
#TODO Define appropriate arguments and pass them from config.yaml
stream_container <- snakemake@input[["stream_container"]]
container_functions <- load_container_script(stream_container)
pull_data_container <- container_functions$pull_data username_list_csv_location <- snakemake@input[["username_list"]]
# TODO Figure out how to use the functions in the container
participant_data <- pull_participants_ids("whatever", usernames, participants_container) 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"]]
usernames <- read_csv(username_list_csv_location, col_types = "c", progress = FALSE)
participant_data <- pull_participants_ids(data_configuration, usernames, participants_container)
participant_data %<>% participant_data %<>%
rename(participant_id = id) rename(participant_id = id)
device_ids <- pull_participants_device_ids("whatever", participant_data$participant_id, device_id_container) device_ids <- pull_participants_device_ids(data_configuration, participant_data$participant_id, device_id_container)
device_ids %<>% device_ids %<>%
group_by(participant_id) %>% group_by(participant_id) %>%
summarise(device_ids = list(unique(device_id))) summarise(device_ids = list(unique(device_id)))
participant_data %<>% participant_data %<>%
left_join(device_ids, by = "participant_id") left_join(device_ids, by = "participant_id")
start_end_datetimes <- pull_participants_start_end_dates("whatever", participant_data$participant_id, start_end_date_container) start_end_datetimes <- pull_participants_start_end_dates(data_configuration, participant_data$participant_id, start_end_date_container)
participant_data %<>% participant_data %<>%
left_join(start_end_datetimes, by = "participant_id") left_join(start_end_datetimes, by = "participant_id")