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

Update create participant files section

pull/130/head
Meng Li 2021-03-25 11:39:31 -04:00
parent a5eb535126
commit e177aa6386
4 changed files with 9 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
config.yaml
View File

@ -10,15 +10,12 @@ CREATE_PARTICIPANT_FILES:
CSV_FILE_PATH: "data/external/example_participants.csv" # see docs for required format
PHONE_SECTION:
ADD: True
DEVICE_ID_COLUMN: device_id # column name
IGNORED_DEVICE_IDS: []
FITBIT_SECTION:
ADD: True
DEVICE_ID_COLUMN: fitbit_id # column name
IGNORED_DEVICE_IDS: []
EMPATICA_SECTION:
ADD: True
DEVICE_ID_COLUMN: empatica_id # column name
IGNORED_DEVICE_IDS: []
# See https://www.rapids.science/latest/setup/configuration/#time-segments

10
docs/setup/configuration.md
View File

@ -134,14 +134,14 @@ Your CSV file (`[CSV_FILE_PATH]`) should have the following columns (headers) bu
| Column | Description |
|------------------|-----------------------------------------------------------------------------------------------------------|
| phone device id | The name of this column has to match `[PHONE_SECTION][DEVICE_ID_COLUMN]`. Separate multiple ids with `;` |
| fitbit device id | The name of this column has to match `[FITBIT_SECTION][DEVICE_ID_COLUMN]`. Separate multiple ids with `;` |
| empatica device id | The name of this column has to match `[EMPATICA_SECTION][DEVICE_ID_COLUMN]`. Since the most common use case involves having multiple zip files from a single device for each person, set this device id to an arbitrary string (we usually use their `pid`) |
| device_id | Phone device id. Separate multiple ids with `;` |
| fitbit_id | Fitbit device id. Separate multiple ids with `;` |
| empatica_id | Empatica device id. Since the most common use case involves having multiple zip files from a single device for each person, set this device id to an arbitrary string (we usually use their `pid`) |
| pid | Unique identifiers with the format pXXX (your participant files will be named with this string) |
| platform | Use `android`, `ios` or `infer` as explained above, separate values with `;` |
| label | A human readable string that is used in reports and visualizations. |
| start_date | A string with format `YYY-MM-DD`. |
| end_date | A string with format `YYY-MM-DD`. |
| start_date | A string with format `YYY-MM-DD` or `YYYY-MM-DD HH:MM:SS`. By default, `YYYY-MM-DD` is interpreted as `YYYY-MM-DD 00:00:00`. |
| end_date | A string with format `YYY-MM-DD` or `YYYY-MM-DD HH:MM:SS`. By default, `YYYY-MM-DD` is interpreted as `YYYY-MM-DD 00:00:00`. |
!!! example
We added white spaces to this example to make it easy to read but you don't have to.

16
example_profile/example_config.yaml
View File

@ -5,22 +5,6 @@
# See https://www.rapids.science/latest/setup/configuration/#participant-files
PIDS: [example01, example02]
# See https://www.rapids.science/latest/setup/configuration/#automatic-creation-of-participant-files
CREATE_PARTICIPANT_FILES:
CSV_FILE_PATH: "data/external/example_participants.csv" # see docs for required format
PHONE_SECTION:
ADD: True
DEVICE_ID_COLUMN: device_id # column name
IGNORED_DEVICE_IDS: []
FITBIT_SECTION:
ADD: True
DEVICE_ID_COLUMN: fitbit_id # column name
IGNORED_DEVICE_IDS: []
EMPATICA_SECTION:
ADD: False
DEVICE_ID_COLUMN: empatica_id # column name
IGNORED_DEVICE_IDS: []
# See https://www.rapids.science/latest/setup/configuration/#time-segments
TIME_SEGMENTS: &time_segments
TYPE: PERIODIC # FREQUENCY, PERIODIC, EVENT

8
src/data/create_participants_files.R
View File

@ -9,9 +9,9 @@ library("dplyr", warn.conflicts = F)
config <- snakemake@params[["config"]]
group <- config$SOURCE$DATABASE_GROUP
timezone <- config$SOURCE$TIMEZONE
phone_device_id_column = config$PHONE_SECTION$DEVICE_ID_COLUMN
fitbit_device_id_column = config$FITBIT_SECTION$DEVICE_ID_COLUMN
empatica_device_id_column = config$EMPATICA_SECTION$DEVICE_ID_COLUMN
phone_device_id_column = "device_id"
fitbit_device_id_column = "fitbit_id"
empatica_device_id_column = "empatica_id"
add_phone_section = config$PHONE_SECTION$ADD
add_fitbit_section = config$FITBIT_SECTION$ADD
add_empatica_section = config$EMPATICA_SECTION$ADD
@ -22,7 +22,7 @@ empatica_ignored = config$EMPATICA_SECTION$IGNORED_DEVICE_IDS
rmysql.settingsfile <- "./.env"
participants <- read_csv(config$CSV_FILE_PATH, col_types=cols_only(device_id="c",pid="c",label="c",platform="c",
start_date=col_date(format = "%Y-%m-%d"),end_date=col_date(format = "%Y-%m-%d"),fitbit_id="c",empatica_id="c")) %>%
start_date=col_datetime(),end_date=col_datetime(),fitbit_id="c",empatica_id="c")) %>%
mutate(start_date = as.character(start_date), end_date = as.character(end_date)) # we read as date to validate format
participants <- participants %>%
mutate(!!phone_device_id_column := str_replace(!!rlang::sym(phone_device_id_column), ";",","),