rapids/config.yaml

365 lines
17 KiB
YAML
Raw Normal View History

2020-11-04 19:27:58 +01:00
# See https://www.rapids.science/setup/configuration/#database-credentials
DATABASE_GROUP: &database_group
MY_GROUP
2019-10-24 22:27:43 +02:00
2020-11-04 19:27:58 +01:00
# See https://www.rapids.science/setup/configuration/#timezone-of-your-study
2019-11-05 21:17:20 +01:00
TIMEZONE: &timezone
2019-11-06 23:12:06 +01:00
America/New_York
2019-11-05 21:17:20 +01:00
2020-11-04 19:27:58 +01:00
# See https://www.rapids.science/setup/configuration/#participant-files
PIDS: [j01]
2020-11-04 19:27:58 +01:00
# See https://www.rapids.science/setup/configuration/#automatic-creation-of-participant-files
CREATE_PARTICIPANT_FILES:
SOURCE:
TYPE: AWARE_DEVICE_TABLE #AWARE_DEVICE_TABLE or CSV_FILE
DATABASE_GROUP: *database_group
2020-11-04 19:27:58 +01:00
CSV_FILE_PATH: "data/external/example_participants.csv" # see docs for required format
TIMEZONE: *timezone
PHONE_SECTION:
2020-10-22 19:08:52 +02:00
ADD: TRUE
DEVICE_ID_COLUMN: device_id # column name
IGNORED_DEVICE_IDS: []
FITBIT_SECTION:
ADD: TRUE
DEVICE_ID_COLUMN: device_id # column name
IGNORED_DEVICE_IDS: []
2020-11-04 19:27:58 +01:00
# See https://www.rapids.science/setup/configuration/#day-segments
DAY_SEGMENTS: &day_segments
2020-11-04 19:27:58 +01:00
TYPE: EVENT # FREQUENCY, PERIODIC, EVENT
FILE: "data/external/daysegments_event.csv"
INCLUDE_PAST_PERIODIC_SEGMENTS: FALSE # Only relevant if TYPE=PERIODIC, see docs
2020-11-04 19:27:58 +01:00
# See https://www.rapids.science/setup/configuration/#device-data-source-configuration
2020-11-04 23:16:46 +01:00
DEVICE_DATA:
PHONE:
SOURCE:
TYPE: DATABASE
DATABASE_GROUP: *database_group
DEVICE_ID_COLUMN: device_id # column name
TIMEZONE:
TYPE: SINGLE # SINGLE or MULTIPLE
2020-11-04 19:27:58 +01:00
VALUE: *timezone # IF TYPE=SINGLE, see docs
FITBIT:
SOURCE:
TYPE: DATABASE # DATABASE or FILES (set each FITBIT_SENSOR TABLE attribute accordingly with a table name or a file path)
COLUMN_FORMAT: JSON # JSON or PLAIN_TEXT
DATABASE_GROUP: *database_group
DEVICE_ID_COLUMN: device_id # column name
2020-10-22 20:38:40 +02:00
TIMEZONE:
TYPE: SINGLE # Fitbit only supports SINGLE timezones
2020-11-04 19:27:58 +01:00
VALUE: *timezone # see docs
############## PHONE ###########################################################
################################################################################
2020-07-09 19:01:50 +02:00
PHONE_VALID_SENSED_BINS:
COMPUTE: False # This flag is automatically ignored (set to True) if you are extracting PHONE_VALID_SENSED_DAYS or screen or Barnett's location features
2020-07-22 22:47:32 +02:00
BIN_SIZE: &bin_size 5 # (in minutes)
2020-10-19 21:07:12 +02:00
# Add as many PHONE sensors as you have, they all improve the computation of PHONE_VALID_SENSED_BINS and PHONE_VALID_SENSED_DAYS.
# If you are extracting screen or Barnett/Doryab location features, PHONE_SCREEN and PHONE_LOCATIONS tables are mandatory.
# You can choose any of the keys shown below, just make sure its TABLE exists in your database!
2020-10-19 21:07:12 +02:00
# PHONE_MESSAGES, PHONE_CALLS, PHONE_LOCATIONS, PHONE_BLUETOOTH, PHONE_ACTIVITY_RECOGNITION, PHONE_BATTERY, PHONE_SCREEN, PHONE_LIGHT,
# PHONE_ACCELEROMETER, PHONE_APPLICATIONS_FOREGROUND, PHONE_WIFI_VISIBLE, PHONE_WIFI_CONNECTED, PHONE_CONVERSATION
PHONE_SENSORS: []
2020-07-09 19:01:50 +02:00
PHONE_VALID_SENSED_DAYS:
COMPUTE: False
MIN_VALID_BINS_PER_HOUR: &min_valid_bins_per_hour [6] # (out of 60min/BIN_SIZE bins)
MIN_VALID_HOURS_PER_DAY: &min_valid_hours_per_day [16] # (out of 24) MIN_HOURS_PER_DAY
2020-07-09 19:01:50 +02:00
# Communication SMS features config, TYPES and FEATURES keys need to match
2020-10-19 21:07:12 +02:00
PHONE_MESSAGES:
TABLE: messages
2020-08-31 19:34:15 +02:00
PROVIDERS:
RAPIDS:
2020-11-04 19:27:58 +01:00
COMPUTE: True
2020-08-31 19:34:15 +02:00
MESSAGES_TYPES : [received, sent]
FEATURES:
received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
sent: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
SRC_LANGUAGE: "r"
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "rapids" # inside src/features/phone_messages
# Communication call features config, TYPES and FEATURES keys need to match
2020-10-19 21:07:12 +02:00
PHONE_CALLS:
TABLE: calls
PROVIDERS:
RAPIDS:
2020-10-22 20:38:40 +02:00
COMPUTE: False
CALL_TYPES: [missed, incoming, outgoing]
FEATURES:
missed: [count, distinctcontacts, timefirstcall, timelastcall, countmostfrequentcontact]
incoming: [count, distinctcontacts, meanduration, sumduration, minduration, maxduration, stdduration, modeduration, entropyduration, timefirstcall, timelastcall, countmostfrequentcontact]
outgoing: [count, distinctcontacts, meanduration, sumduration, minduration, maxduration, stdduration, modeduration, entropyduration, timefirstcall, timelastcall, countmostfrequentcontact]
SRC_LANGUAGE: "r"
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "rapids" # inside src/features/phone_calls
2019-11-05 18:34:22 +01:00
2020-10-19 21:07:12 +02:00
PHONE_LOCATIONS:
TABLE: locations
LOCATIONS_TO_USE: FUSED_RESAMPLED # ALL, GPS OR FUSED_RESAMPLED
FUSED_RESAMPLED_CONSECUTIVE_THRESHOLD: 30 # minutes, only replicate location samples to the next sensed bin if the phone did not stop collecting data for more than this threshold
FUSED_RESAMPLED_TIME_SINCE_VALID_LOCATION: 720 # minutes, only replicate location samples to consecutive sensed bins if they were logged within this threshold after a valid location row
PROVIDERS:
DORYAB:
COMPUTE: False
FEATURES: ["locationvariance","loglocationvariance","totaldistance","averagespeed","varspeed","circadianmovement","numberofsignificantplaces","numberlocationtransitions","radiusgyration","timeattop1location","timeattop2location","timeattop3location","movingtostaticratio","outlierstimepercent","maxlengthstayatclusters","minlengthstayatclusters","meanlengthstayatclusters","stdlengthstayatclusters","locationentropy","normalizedlocationentropy"]
DBSCAN_EPS: 10 # meters
DBSCAN_MINSAMPLES: 5
THRESHOLD_STATIC : 1 # km/h
MAXIMUM_GAP_ALLOWED: 300
MINUTES_DATA_USED: False
SAMPLING_FREQUENCY: 0
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "doryab" # inside src/features/phone_locations
SRC_LANGUAGE: "python"
BARNETT:
COMPUTE: False
FEATURES: ["hometime","disttravelled","rog","maxdiam","maxhomedist","siglocsvisited","avgflightlen","stdflightlen","avgflightdur","stdflightdur","probpause","siglocentropy","circdnrtn","wkenddayrtn"]
ACCURACY_LIMIT: 51 # meters, drops location coordinates with an accuracy higher than this. This number means there's a 68% probability the true location is within this radius
TIMEZONE: *timezone
MINUTES_DATA_USED: False # Use this for quality control purposes, how many minutes of data (location coordinates gruped by minute) were used to compute features
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "barnett" # inside src/features/phone_locations
SRC_LANGUAGE: "r"
2020-10-19 21:07:12 +02:00
PHONE_BLUETOOTH:
TABLE: bluetooth
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "rapids" # inside src/features/phone_bluetooth
SRC_LANGUAGE: "r"
2019-11-18 20:22:08 +01:00
2020-10-19 21:07:12 +02:00
PHONE_ACTIVITY_RECOGNITION:
TABLE:
ANDROID: plugin_google_activity_recognition
IOS: plugin_ios_activity_recognition
2020-10-26 20:51:22 +01:00
EPISODE_THRESHOLD_BETWEEN_ROWS: 5 # minutes. Max time difference for two consecutive rows to be considered within the same battery episode.
PROVIDERS:
RAPIDS:
2020-10-22 20:38:40 +02:00
COMPUTE: False
FEATURES: ["count", "mostcommonactivity", "countuniqueactivities", "durationstationary", "durationmobile", "durationvehicle"]
ACTIVITY_CLASSES:
STATIONARY: ["still", "tilting"]
MOBILE: ["on_foot", "walking", "running", "on_bicycle"]
VEHICLE: ["in_vehicle"]
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "rapids" # inside src/features/phone_activity_recognition
SRC_LANGUAGE: "python"
2020-10-19 21:07:12 +02:00
PHONE_BATTERY:
TABLE: battery
2020-10-26 20:51:22 +01:00
EPISODE_THRESHOLD_BETWEEN_ROWS: 30 # minutes. Max time difference for two consecutive rows to be considered within the same battery episode.
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "rapids" # inside src/features/phone_battery
SRC_LANGUAGE: "python"
2019-11-27 20:25:17 +01:00
2020-10-19 21:07:12 +02:00
PHONE_SCREEN:
TABLE: screen
PROVIDERS:
RAPIDS:
COMPUTE: False
REFERENCE_HOUR_FIRST_USE: 0
IGNORE_EPISODES_SHORTER_THAN: 0 # in minutes, set to 0 to disable
IGNORE_EPISODES_LONGER_THAN: 0 # in minutes, set to 0 to disable
FEATURES: ["countepisode", "sumduration", "maxduration", "minduration", "avgduration", "stdduration", "firstuseafter"] # "episodepersensedminutes" needs to be added later
EPISODE_TYPES: ["unlock"]
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "rapids" # inside src/features/phone_screen
SRC_LANGUAGE: "python"
2020-01-14 15:51:39 +01:00
2020-10-19 21:07:12 +02:00
PHONE_LIGHT:
TABLE: light
2020-09-01 18:01:24 +02:00
PROVIDERS:
RAPIDS:
2020-09-03 20:36:42 +02:00
COMPUTE: False
2020-09-01 18:01:24 +02:00
FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "rapids" # inside src/features/phone_light
2020-09-01 18:01:24 +02:00
SRC_LANGUAGE: "python"
2020-10-19 21:07:12 +02:00
PHONE_ACCELEROMETER:
TABLE: accelerometer
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "rapids" # inside src/features/phone_accelerometer
SRC_LANGUAGE: "python"
PANDA:
COMPUTE: False
VALID_SENSED_MINUTES: False
FEATURES:
exertional_activity_episode: ["sumduration", "maxduration", "minduration", "avgduration", "medianduration", "stdduration"]
nonexertional_activity_episode: ["sumduration", "maxduration", "minduration", "avgduration", "medianduration", "stdduration"]
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "panda" # inside src/features/phone_accelerometer
SRC_LANGUAGE: "python"
2020-01-29 22:22:53 +01:00
2020-10-19 21:07:12 +02:00
PHONE_APPLICATIONS_FOREGROUND:
TABLE: applications_foreground
2020-10-19 21:07:12 +02:00
APPLICATION_CATEGORIES:
CATALOGUE_SOURCE: FILE # FILE (genres are read from CATALOGUE_FILE) or GOOGLE (genres are scrapped from the Play Store)
CATALOGUE_FILE: "data/external/stachl_application_genre_catalogue.csv"
UPDATE_CATALOGUE_FILE: False # if CATALOGUE_SOURCE is equal to FILE, whether or not to update CATALOGUE_FILE, if CATALOGUE_SOURCE is equal to GOOGLE all scraped genres will be saved to CATALOGUE_FILE
SCRAPE_MISSING_CATEGORIES: False # whether or not to scrape missing genres, only effective if CATALOGUE_SOURCE is equal to FILE. If CATALOGUE_SOURCE is equal to GOOGLE, all genres are scraped anyway
PROVIDERS:
RAPIDS:
2020-09-03 20:36:42 +02:00
COMPUTE: False
SINGLE_CATEGORIES: ["all", "email"]
MULTIPLE_CATEGORIES:
social: ["socialnetworks", "socialmediatools"]
entertainment: ["entertainment", "gamingknowledge", "gamingcasual", "gamingadventure", "gamingstrategy", "gamingtoolscommunity", "gamingroleplaying", "gamingaction", "gaminglogic", "gamingsports", "gamingsimulation"]
SINGLE_APPS: ["top1global", "com.facebook.moments", "com.google.android.youtube", "com.twitter.android"] # There's no entropy for single apps
EXCLUDED_CATEGORIES: []
EXCLUDED_APPS: ["com.fitbit.FitbitMobile", "com.aware.plugin.upmc.cancer"]
FEATURES: ["count", "timeoffirstuse", "timeoflastuse", "frequencyentropy"]
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "rapids" # inside src/features/phone_applications_foreground
SRC_LANGUAGE: "python"
2020-02-07 17:52:55 +01:00
2020-10-19 21:07:12 +02:00
PHONE_WIFI_VISIBLE:
TABLE: "wifi"
2020-10-19 21:07:12 +02:00
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_wifi_visible
SRC_LANGUAGE: "r"
PHONE_WIFI_CONNECTED:
TABLE: "sensor_wifi"
2020-10-19 21:07:12 +02:00
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_wifi_connected
SRC_LANGUAGE: "r"
PHONE_CONVERSATION:
TABLE:
2020-10-19 21:07:12 +02:00
ANDROID: plugin_studentlife_audio_android
IOS: plugin_studentlife_audio
PROVIDERS:
RAPIDS:
2020-10-22 20:38:40 +02:00
COMPUTE: False
2020-10-19 21:07:12 +02:00
FEATURES: ["minutessilence", "minutesnoise", "minutesvoice", "minutesunknown","sumconversationduration","avgconversationduration",
"sdconversationduration","minconversationduration","maxconversationduration","timefirstconversation","timelastconversation","noisesumenergy",
"noiseavgenergy","noisesdenergy","noiseminenergy","noisemaxenergy","voicesumenergy",
"voiceavgenergy","voicesdenergy","voiceminenergy","voicemaxenergy","silencesensedfraction","noisesensedfraction",
"voicesensedfraction","unknownsensedfraction","silenceexpectedfraction","noiseexpectedfraction","voiceexpectedfraction",
2020-06-24 23:03:14 +02:00
"unknownexpectedfraction","countconversation"]
2020-10-19 21:07:12 +02:00
RECORDING_MINUTES: 1
PAUSED_MINUTES : 3
SRC_FOLDER: "rapids" # inside src/features/phone_conversation
SRC_LANGUAGE: "python"
2020-10-22 19:08:52 +02:00
############## FITBIT ##########################################################
################################################################################
2020-10-19 21:07:12 +02:00
FITBIT_HEARTRATE_SUMMARY:
TABLE: heartrate_summary
PROVIDERS:
RAPIDS:
2020-10-22 19:08:52 +02:00
COMPUTE: False
FEATURES: ["maxrestinghr", "minrestinghr", "avgrestinghr", "medianrestinghr", "moderestinghr", "stdrestinghr", "diffmaxmoderestinghr", "diffminmoderestinghr", "entropyrestinghr"] # calories features' accuracy depend on the accuracy of the participants fitbit profile (e.g. height, weight) use these with care: ["sumcaloriesoutofrange", "maxcaloriesoutofrange", "mincaloriesoutofrange", "avgcaloriesoutofrange", "mediancaloriesoutofrange", "stdcaloriesoutofrange", "entropycaloriesoutofrange", "sumcaloriesfatburn", "maxcaloriesfatburn", "mincaloriesfatburn", "avgcaloriesfatburn", "mediancaloriesfatburn", "stdcaloriesfatburn", "entropycaloriesfatburn", "sumcaloriescardio", "maxcaloriescardio", "mincaloriescardio", "avgcaloriescardio", "mediancaloriescardio", "stdcaloriescardio", "entropycaloriescardio", "sumcaloriespeak", "maxcaloriespeak", "mincaloriespeak", "avgcaloriespeak", "mediancaloriespeak", "stdcaloriespeak", "entropycaloriespeak"]
SRC_FOLDER: "rapids" # inside src/features/fitbit_heartrate_summary
SRC_LANGUAGE: "python"
FITBIT_HEARTRATE_INTRADAY:
TABLE: heartrate_intraday
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "minutesonoutofrangezone", "minutesonfatburnzone", "minutesoncardiozone", "minutesonpeakzone"]
SRC_FOLDER: "rapids" # inside src/features/fitbit_heartrate_intraday
2020-10-27 22:55:57 +01:00
SRC_LANGUAGE: "python"
2020-02-07 17:35:15 +01:00
FITBIT_STEPS_SUMMARY:
TABLE: steps_summary
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["maxsumsteps", "minsumsteps", "avgsumsteps", "mediansumsteps", "stdsumsteps"]
SRC_FOLDER: "rapids" # inside src/features/fitbit_steps_summary
SRC_LANGUAGE: "python"
FITBIT_STEPS_INTRADAY:
TABLE: steps_intraday
PROVIDERS:
RAPIDS:
2020-10-22 19:08:52 +02:00
COMPUTE: False
FEATURES:
STEPS: ["sum", "max", "min", "avg", "std"]
SEDENTARY_BOUT: ["countepisode", "sumduration", "maxduration", "minduration", "avgduration", "stdduration"]
ACTIVE_BOUT: ["countepisode", "sumduration", "maxduration", "minduration", "avgduration", "stdduration"]
THRESHOLD_ACTIVE_BOUT: 10 # steps
INCLUDE_ZERO_STEP_ROWS: False
SRC_FOLDER: "rapids" # inside src/features/fitbit_steps_intraday
2020-10-30 23:57:04 +01:00
SRC_LANGUAGE: "python"
FITBIT_SLEEP:
2020-11-04 23:16:46 +01:00
TABLE_FORMAT: JSON # JSON or CSV. If your JSON or CSV data are files change [DEVICE_DATA][FITBIT][SOURCE][TYPE] to FILES
2020-10-22 19:08:52 +02:00
TABLE:
JSON: fitbit_sleep
CSV:
2020-10-28 19:03:02 +01:00
SUMMARY: sleep_summary
INTRADAY: sleep_intraday
PROVIDERS:
RAPIDS:
2020-10-22 19:08:52 +02:00
COMPUTE: False
SLEEP_TYPES: ["main", "nap", "all"]
SUMMARY_FEATURES: ["sumdurationafterwakeup", "sumdurationasleep", "sumdurationawake", "sumdurationtofallasleep", "sumdurationinbed", "avgefficiency", "countepisode"]
2020-10-22 19:08:52 +02:00
FITBIT_CALORIES:
2020-11-04 23:16:46 +01:00
TABLE_FORMAT: JSON # JSON or CSV. If your JSON or CSV data are files change [DEVICE_DATA][FITBIT][SOURCE][TYPE] to FILES
2020-10-22 19:08:52 +02:00
TABLE:
JSON: fitbit_calories
CSV:
2020-10-28 19:03:02 +01:00
SUMMARY: calories_summary
INTRADAY: calories_intraday
2020-10-22 19:08:52 +02:00
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: []
### Visualizations #############################################################
################################################################################
2020-07-22 22:47:32 +02:00
HEATMAP_FEATURES_CORRELATIONS:
PLOT: False
MIN_ROWS_RATIO: 0.5
MIN_VALID_HOURS_PER_DAY: *min_valid_hours_per_day
MIN_VALID_BINS_PER_HOUR: *min_valid_bins_per_hour
2020-07-22 22:47:32 +02:00
PHONE_FEATURES: [accelerometer, activity_recognition, applications_foreground, battery, calls_incoming, calls_missed, calls_outgoing, conversation, light, location_doryab, messages_received, messages_sent, screen]
FITBIT_FEATURES: [fitbit_heartrate, fitbit_step, fitbit_sleep]
CORR_THRESHOLD: 0.1
CORR_METHOD: "pearson" # choose from {"pearson", "kendall", "spearman"}
2020-07-22 22:47:32 +02:00
HISTOGRAM_VALID_SENSED_HOURS:
PLOT: False
MIN_VALID_HOURS_PER_DAY: *min_valid_hours_per_day
MIN_VALID_BINS_PER_HOUR: *min_valid_bins_per_hour
2020-07-22 22:47:32 +02:00
HEATMAP_DAYS_BY_SENSORS:
PLOT: False
MIN_VALID_HOURS_PER_DAY: *min_valid_hours_per_day
MIN_VALID_BINS_PER_HOUR: *min_valid_bins_per_hour
2020-07-22 22:47:32 +02:00
EXPECTED_NUM_OF_DAYS: -1
DB_TABLES: [accelerometer, applications_foreground, battery, bluetooth, calls, light, locations, messages, screen, wifi, sensor_wifi, plugin_google_activity_recognition, plugin_ios_activity_recognition, plugin_studentlife_audio_android, plugin_studentlife_audio]
2020-07-22 22:47:32 +02:00
HEATMAP_SENSED_BINS:
PLOT: False
BIN_SIZE: *bin_size
OVERALL_COMPLIANCE_HEATMAP:
PLOT: False
ONLY_SHOW_VALID_DAYS: False
EXPECTED_NUM_OF_DAYS: -1
2020-07-22 22:47:32 +02:00
BIN_SIZE: *bin_size
MIN_VALID_HOURS_PER_DAY: *min_valid_hours_per_day
MIN_VALID_BINS_PER_HOUR: *min_valid_bins_per_hour
2020-07-22 22:47:32 +02:00