2021-03-13 01:52:34 +01:00
########################################################################################################################
# GLOBAL CONFIGURATION #
########################################################################################################################
2020-08-03 23:30:15 +02:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/setup/configuration/#participant-files
2020-12-05 00:45:16 +01:00
PIDS : [ example01, example02]
2020-11-25 22:34:05 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/setup/configuration/#time-segments
2020-12-03 00:41:03 +01:00
TIME_SEGMENTS : &time_segments
2020-11-25 22:34:05 +01:00
TYPE : PERIODIC # FREQUENCY, PERIODIC, EVENT
2020-12-03 00:41:03 +01:00
FILE : "example_profile/exampleworkflow_timesegments.csv"
2020-11-25 22:34:05 +01:00
INCLUDE_PAST_PERIODIC_SEGMENTS : FALSE # Only relevant if TYPE=PERIODIC, see docs
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/setup/configuration/#timezone-of-your-study
TIMEZONE :
TYPE : SINGLE
SINGLE :
TZCODE : America/New_York
MULTIPLE :
TZCODES_FILE : data/external/multiple_timezones_example.csv
IF_MISSING_TZCODE : STOP
DEFAULT_TZCODE : America/New_York
FITBIT :
ALLOW_MULTIPLE_TZ_PER_DEVICE : False
INFER_FROM_SMARTPHONE_TZ : False
2020-11-26 04:35:38 +01:00
########################################################################################################################
# PHONE #
########################################################################################################################
2020-11-25 22:34:05 +01:00
2021-03-15 00:52:14 +01:00
# See https://www.rapids.science/latest/setup/configuration/#data-stream-configuration
2021-03-13 01:52:34 +01:00
PHONE_DATA_STREAMS :
USE : aware_csv
# AVAILABLE:
aware_mysql :
DATABASE_GROUP : MY_GROUP
2020-11-26 01:42:11 +01:00
2021-03-13 01:52:34 +01:00
aware_csv :
FOLDER : data/external/example_workflow
2021-03-15 00:52:14 +01:00
aware_influxdb :
DATABASE_GROUP : MY_GROUP
2020-11-26 01:42:11 +01:00
# Sensors ------
2020-11-26 04:35:38 +01:00
2021-03-13 01:52:34 +01:00
# https://www.rapids.science/latest/features/phone-accelerometer/
2020-11-26 04:35:38 +01:00
PHONE_ACCELEROMETER :
2021-03-13 00:14:49 +01:00
CONTAINER : accelerometer
2020-11-26 04:35:38 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : False
FEATURES : [ "maxmagnitude" , "minmagnitude" , "avgmagnitude" , "medianmagnitude" , "stdmagnitude" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_accelerometer/rapids/main.py
2020-11-26 04:35:38 +01:00
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" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_accelerometer/panda/main.py
2020-11-26 04:35:38 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-activity-recognition/
2020-11-26 04:35:38 +01:00
PHONE_ACTIVITY_RECOGNITION :
2021-03-13 00:14:49 +01:00
CONTAINER :
2021-03-13 01:52:34 +01:00
ANDROID : plugin_google_activity_recognition.csv
IOS : plugin_ios_activity_recognition.csv
2020-11-26 04:35:38 +01:00
EPISODE_THRESHOLD_BETWEEN_ROWS : 5 # minutes. Max time difference for two consecutive rows to be considered within the same battery episode.
2020-11-25 22:34:05 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
2020-11-26 04:35:38 +01:00
FEATURES : [ "count" , "mostcommonactivity" , "countuniqueactivities" , "durationstationary" , "durationmobile" , "durationvehicle" ]
ACTIVITY_CLASSES :
STATIONARY : [ "still" , "tilting" ]
MOBILE : [ "on_foot" , "walking" , "running" , "on_bicycle" ]
VEHICLE : [ "in_vehicle" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_activity_recognition/rapids/main.py
2020-08-03 23:30:15 +02:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-applications-crashes/
PHONE_APPLICATIONS_CRASHES :
CONTAINER : applications_crashes
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 : # None implemented yet but this sensor can be used in PHONE_DATA_YIELD
# See https://www.rapids.science/latest/features/phone-applications-foreground/
2020-11-26 04:35:38 +01:00
PHONE_APPLICATIONS_FOREGROUND :
2021-03-13 01:52:34 +01:00
CONTAINER : applications_foreground.csv
2020-11-26 04:35:38 +01:00
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
2020-11-25 22:34:05 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
2021-07-02 00:08:33 +02:00
INCLUDE_EPISODE_FEATURES : False
2020-11-26 04:35:38 +01:00
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 : [ "system_apps" ]
EXCLUDED_APPS : [ "com.fitbit.FitbitMobile" , "com.aware.plugin.upmc.cancer" ]
2021-07-02 00:08:33 +02:00
FEATURES :
APP_EVENTS : [ "countevent" , "timeoffirstuse" , "timeoflastuse" , "frequencyentropy" ]
APP_EPISODES : [ "countepisode" , "minduration" , "maxduration" , "meanduration" , "sumduration" ]
IGNORE_EPISODES_SHORTER_THAN : 0 # in minutes, set to 0 to disable
IGNORE_EPISODES_LONGER_THAN : 300 # in minutes, set to 0 to disable
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_applications_foreground/rapids/main.py
2020-11-26 04:35:38 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-applications-notifications/
PHONE_APPLICATIONS_NOTIFICATIONS :
CONTAINER : applications_notifications
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 : # None implemented yet but this sensor can be used in PHONE_DATA_YIELD
# See https://www.rapids.science/latest/features/phone-battery/
2020-11-26 04:35:38 +01:00
PHONE_BATTERY :
2021-03-13 01:52:34 +01:00
CONTAINER : battery.csv
2020-11-26 04:35:38 +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 : True
FEATURES : [ "countdischarge" , "sumdurationdischarge" , "countcharge" , "sumdurationcharge" , "avgconsumptionrate" , "maxconsumptionrate" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_battery/rapids/main.py
2020-11-26 04:35:38 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-bluetooth/
2020-11-26 04:35:38 +01:00
PHONE_BLUETOOTH :
2021-03-13 01:52:34 +01:00
CONTAINER : bluetooth.csv
2020-11-26 04:35:38 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
FEATURES : [ "countscans" , "uniquedevices" , "countscansmostuniquedevice" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_bluetooth/rapids/main.R
2021-03-13 01:52:34 +01:00
DORYAB :
COMPUTE : False
FEATURES :
ALL :
DEVICES : [ "countscans" , "uniquedevices" , "meanscans" , "stdscans" ]
SCANS_MOST_FREQUENT_DEVICE : [ "withinsegments" , "acrosssegments" , "acrossdataset" ]
SCANS_LEAST_FREQUENT_DEVICE : [ "withinsegments" , "acrosssegments" , "acrossdataset" ]
OWN :
DEVICES : [ "countscans" , "uniquedevices" , "meanscans" , "stdscans" ]
SCANS_MOST_FREQUENT_DEVICE : [ "withinsegments" , "acrosssegments" , "acrossdataset" ]
SCANS_LEAST_FREQUENT_DEVICE : [ "withinsegments" , "acrosssegments" , "acrossdataset" ]
OTHERS :
DEVICES : [ "countscans" , "uniquedevices" , "meanscans" , "stdscans" ]
SCANS_MOST_FREQUENT_DEVICE : [ "withinsegments" , "acrosssegments" , "acrossdataset" ]
SCANS_LEAST_FREQUENT_DEVICE : [ "withinsegments" , "acrosssegments" , "acrossdataset" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_bluetooth/doryab/main.py
2020-08-03 23:30:15 +02:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-calls/
2020-11-25 22:34:05 +01:00
PHONE_CALLS :
2021-03-13 01:52:34 +01:00
CONTAINER : calls.csv
2020-11-25 22:34:05 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
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]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_calls/rapids/main.R
2020-11-25 22:34:05 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-conversation/
2020-11-26 04:35:38 +01:00
PHONE_CONVERSATION :
2021-03-13 00:14:49 +01:00
CONTAINER :
2021-03-13 01:52:34 +01:00
ANDROID : plugin_studentlife_audio_android.csv
IOS : plugin_studentlife_audio.csv
2020-11-26 04:35:38 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
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" ,
"unknownexpectedfraction" , "countconversation" ]
RECORDING_MINUTES : 1
PAUSED_MINUTES : 3
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_conversation/rapids/main.py
2020-11-26 04:35:38 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-data-yield/
2020-11-26 04:35:38 +01:00
PHONE_DATA_YIELD :
2021-03-13 01:52:34 +01:00
SENSORS : [ PHONE_ACTIVITY_RECOGNITION, PHONE_APPLICATIONS_FOREGROUND, PHONE_BATTERY, PHONE_BLUETOOTH, PHONE_CALLS, PHONE_CONVERSATION, PHONE_LIGHT, PHONE_LOCATIONS, PHONE_MESSAGES, PHONE_SCREEN, PHONE_WIFI_CONNECTED, PHONE_WIFI_VISIBLE]
2020-11-26 04:35:38 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
FEATURES : [ ratiovalidyieldedminutes, ratiovalidyieldedhours]
2021-03-13 01:52:34 +01:00
MINUTE_RATIO_THRESHOLD_FOR_VALID_YIELDED_HOURS : 0.5 # 0 to 1, minimum percentage of valid minutes in an hour to be considered valid.
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_data_yield/rapids/main.R
2020-11-26 04:35:38 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-keyboard/
PHONE_KEYBOARD :
CONTAINER : keyboard
2021-06-28 22:30:44 +02:00
PROVIDERS :
RAPIDS :
COMPUTE : False
FEATURES : [ "sessioncount" , "averageinterkeydelay" , "averagesessionlength" , "changeintextlengthlessthanminusone" , "changeintextlengthequaltominusone" , "changeintextlengthequaltoone" , "changeintextlengthmorethanone" , "maxtextlength" , "lastmessagelength" , "totalkeyboardtouches" ]
SRC_SCRIPT : src/features/phone_keyboard/rapids/main.py
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-light/
2020-11-26 04:35:38 +01:00
PHONE_LIGHT :
2021-03-13 01:52:34 +01:00
CONTAINER : light.csv
2020-11-26 04:35:38 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
FEATURES : [ "count" , "maxlux" , "minlux" , "avglux" , "medianlux" , "stdlux" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_light/rapids/main.py
2020-11-26 04:35:38 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-locations/
2020-11-25 22:34:05 +01:00
PHONE_LOCATIONS :
2021-03-13 01:52:34 +01:00
CONTAINER : locations.csv
LOCATIONS_TO_USE : FUSED_RESAMPLED # ALL, GPS, ALL_RESAMPLED, OR FUSED_RESAMPLED
2020-11-25 22:34:05 +01:00
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
2021-10-13 23:06:53 +02:00
ACCURACY_LIMIT : 51 # meters
2020-11-25 22:34:05 +01:00
PROVIDERS :
DORYAB :
COMPUTE : True
2021-04-09 18:05:25 +02:00
FEATURES : [ "locationvariance" , "loglocationvariance" , "totaldistance" , "avgspeed" , "varspeed" , "numberofsignificantplaces" , "numberlocationtransitions" , "radiusgyration" , "timeattop1location" , "timeattop2location" , "timeattop3location" , "movingtostaticratio" , "outlierstimepercent" , "maxlengthstayatclusters" , "minlengthstayatclusters" , "avglengthstayatclusters" , "stdlengthstayatclusters" , "locationentropy" , "normalizedlocationentropy" , "timeathome" ]
2020-11-25 22:34:05 +01:00
DBSCAN_EPS : 10 # meters
DBSCAN_MINSAMPLES : 5
THRESHOLD_STATIC : 1 # km/h
2021-04-09 18:05:25 +02:00
MAXIMUM_ROW_GAP : 300 # seconds
2020-11-25 22:34:05 +01:00
MINUTES_DATA_USED : False
2021-04-09 18:05:25 +02:00
CLUSTER_ON : PARTICIPANT_DATASET # PARTICIPANT_DATASET, TIME_SEGMENT, TIME_SEGMENT_INSTANCE
INFER_HOME_LOCATION_STRATEGY : DORYAB_STRATEGY # DORYAB_STRATEGY, SUN_LI_VEGA_STRATEGY
MINIMUM_DAYS_TO_DETECT_HOME_CHANGES : 3
CLUSTERING_ALGORITHM : DBSCAN # DBSCAN, OPTICS
2021-03-13 01:52:34 +01:00
RADIUS_FOR_HOME : 100
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_locations/doryab/main.py
2020-11-25 22:34:05 +01:00
BARNETT :
COMPUTE : False
FEATURES : [ "hometime" , "disttravelled" , "rog" , "maxdiam" , "maxhomedist" , "siglocsvisited" , "avgflightlen" , "stdflightlen" , "avgflightdur" , "stdflightdur" , "probpause" , "siglocentropy" , "circdnrtn" , "wkenddayrtn" ]
2021-03-13 01:52:34 +01:00
IF_MULTIPLE_TIMEZONES : USE_MOST_COMMON
2020-11-25 22:34:05 +01:00
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
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_locations/barnett/main.R
2020-11-25 22:34:05 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-log/
PHONE_LOG :
CONTAINER :
ANDROID : aware_log
IOS : ios_aware_log
PROVIDERS : # None implemented yet but this sensor can be used in PHONE_DATA_YIELD
# See https://www.rapids.science/latest/features/phone-messages/
2020-11-26 04:35:38 +01:00
PHONE_MESSAGES :
2021-03-13 01:52:34 +01:00
CONTAINER : messages.csv
2020-11-25 22:34:05 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
2020-11-26 04:35:38 +01:00
MESSAGES_TYPES : [ received, sent]
FEATURES :
received : [ count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
sent : [ count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_messages/rapids/main.R
2020-11-25 22:34:05 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-screen/
2020-11-25 22:34:05 +01:00
PHONE_SCREEN :
2021-03-13 01:52:34 +01:00
CONTAINER : screen.csv
2020-11-25 22:34:05 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
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" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_screen/rapids/main.py
2020-11-25 22:34:05 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-wifi-connected/
2020-11-26 04:35:38 +01:00
PHONE_WIFI_CONNECTED :
2021-03-13 01:52:34 +01:00
CONTAINER : sensor_wifi.csv
2020-11-25 22:34:05 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
2020-11-26 04:35:38 +01:00
FEATURES : [ "countscans" , "uniquedevices" , "countscansmostuniquedevice" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_wifi_connected/rapids/main.R
2020-11-25 22:34:05 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/phone-wifi-visible/
2020-11-25 22:34:05 +01:00
PHONE_WIFI_VISIBLE :
2021-03-13 01:52:34 +01:00
CONTAINER : wifi.csv
2020-11-25 22:34:05 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
FEATURES : [ "countscans" , "uniquedevices" , "countscansmostuniquedevice" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/phone_wifi_visible/rapids/main.R
2020-11-25 22:34:05 +01:00
2020-11-26 04:35:38 +01:00
########################################################################################################################
# FITBIT #
########################################################################################################################
2020-11-25 22:34:05 +01:00
2021-03-15 00:52:14 +01:00
# See https://www.rapids.science/latest/setup/configuration/#data-stream-configuration
2021-03-13 01:52:34 +01:00
FITBIT_DATA_STREAMS :
USE : fitbitjson_csv
# AVAILABLE:
fitbitjson_mysql :
DATABASE_GROUP : MY_GROUP
2021-04-27 17:44:15 +02:00
SLEEP_SUMMARY_LAST_NIGHT_END : 660 # a number ranged from 0 (midnight) to 1439 (23:59) which denotes number of minutes after midnight. By default, 660 (11:00).
2021-03-13 01:52:34 +01:00
fitbitparsed_mysql :
DATABASE_GROUP : MY_GROUP
2021-04-27 17:44:15 +02:00
SLEEP_SUMMARY_LAST_NIGHT_END : 660 # a number ranged from 0 (midnight) to 1439 (23:59) which denotes number of minutes after midnight. By default, 660 (11:00).
2021-03-13 01:52:34 +01:00
fitbitjson_csv :
FOLDER : data/external/example_workflow
2021-04-27 17:44:15 +02:00
SLEEP_SUMMARY_LAST_NIGHT_END : 660 # a number ranged from 0 (midnight) to 1439 (23:59) which denotes number of minutes after midnight. By default, 660 (11:00).
2021-03-13 01:52:34 +01:00
fitbitparsed_csv :
FOLDER : data/external/fitbit_csv
2021-04-27 17:44:15 +02:00
SLEEP_SUMMARY_LAST_NIGHT_END : 660 # a number ranged from 0 (midnight) to 1439 (23:59) which denotes number of minutes after midnight. By default, 660 (11:00).
2020-11-26 01:42:11 +01:00
2021-03-13 01:52:34 +01:00
# Sensors ------
# See https://www.rapids.science/latest/features/fitbit-data-yield/
FITBIT_DATA_YIELD :
SENSOR : FITBIT_HEARTRATE_INTRADAY
PROVIDERS :
RAPIDS :
COMPUTE : False
FEATURES : [ ratiovalidyieldedminutes, ratiovalidyieldedhours]
MINUTE_RATIO_THRESHOLD_FOR_VALID_YIELDED_HOURS : 0.5 # 0 to 1, minimum percentage of valid minutes in an hour to be considered valid.
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/fitbit_data_yield/rapids/main.R
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/fitbit-heartrate-summary/
2020-11-25 22:34:05 +01:00
FITBIT_HEARTRATE_SUMMARY :
2021-03-13 01:52:34 +01:00
CONTAINER : fitbit_data.csv
2020-11-25 22:34:05 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
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" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/fitbit_heartrate_summary/rapids/main.py
2020-11-25 22:34:05 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/fitbit-heartrate-intraday/
2020-11-25 22:34:05 +01:00
FITBIT_HEARTRATE_INTRADAY :
2021-03-13 01:52:34 +01:00
CONTAINER : fitbit_data.csv
2020-11-25 22:34:05 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
FEATURES : [ "maxhr" , "minhr" , "avghr" , "medianhr" , "modehr" , "stdhr" , "diffmaxmodehr" , "diffminmodehr" , "entropyhr" , "minutesonoutofrangezone" , "minutesonfatburnzone" , "minutesoncardiozone" , "minutesonpeakzone" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/fitbit_heartrate_intraday/rapids/main.py
2020-11-25 22:34:05 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/fitbit-sleep-summary/
2020-11-26 04:35:38 +01:00
FITBIT_SLEEP_SUMMARY :
2021-03-13 01:52:34 +01:00
CONTAINER : fitbit_data.csv
2020-11-26 04:35:38 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
FEATURES : [ "countepisode" , "avgefficiency" , "sumdurationafterwakeup" , "sumdurationasleep" , "sumdurationawake" , "sumdurationtofallasleep" , "sumdurationinbed" , "avgdurationafterwakeup" , "avgdurationasleep" , "avgdurationawake" , "avgdurationtofallasleep" , "avgdurationinbed" ]
SLEEP_TYPES : [ "main" , "nap" , "all" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/fitbit_sleep_summary/rapids/main.py
2020-11-26 04:35:38 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/fitbit-sleep-intraday/
FITBIT_SLEEP_INTRADAY :
CONTAINER : sleep_intraday
PROVIDERS :
RAPIDS :
COMPUTE : False
FEATURES :
LEVELS_AND_TYPES : [ countepisode, sumduration, maxduration, minduration, avgduration, medianduration, stdduration]
RATIOS_TYPE : [ count, duration]
RATIOS_SCOPE : [ ACROSS_LEVELS, ACROSS_TYPES, WITHIN_LEVELS, WITHIN_TYPES]
SLEEP_LEVELS :
2021-04-27 17:44:15 +02:00
INCLUDE_ALL_GROUPS : True
2021-03-13 01:52:34 +01:00
CLASSIC : [ awake, restless, asleep]
STAGES : [ wake, deep, light, rem]
UNIFIED : [ awake, asleep]
2021-04-27 17:44:15 +02:00
SLEEP_TYPES : [ main, nap, all]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/fitbit_sleep_intraday/rapids/main.py
2021-03-13 01:52:34 +01:00
PRICE :
COMPUTE : False
2021-04-27 17:44:15 +02:00
FEATURES : [ avgduration, avgratioduration, avgstarttimeofepisodemain, avgendtimeofepisodemain, avgmidpointofepisodemain, stdstarttimeofepisodemain, stdendtimeofepisodemain, stdmidpointofepisodemain, socialjetlag, rmssdmeanstarttimeofepisodemain, rmssdmeanendtimeofepisodemain, rmssdmeanmidpointofepisodemain, rmssdmedianstarttimeofepisodemain, rmssdmedianendtimeofepisodemain, rmssdmedianmidpointofepisodemain]
2021-03-13 01:52:34 +01:00
SLEEP_LEVELS :
2021-04-27 17:44:15 +02:00
INCLUDE_ALL_GROUPS : True
2021-03-13 01:52:34 +01:00
CLASSIC : [ awake, restless, asleep]
STAGES : [ wake, deep, light, rem]
UNIFIED : [ awake, asleep]
DAY_TYPES : [ WEEKEND, WEEK, ALL]
2021-04-27 17:44:15 +02:00
LAST_NIGHT_END : 660 # number of minutes after midnight (11:00) 11*60
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/fitbit_sleep_intraday/price/main.py
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/fitbit-steps-summary/
2020-11-25 22:34:05 +01:00
FITBIT_STEPS_SUMMARY :
2021-03-13 01:52:34 +01:00
CONTAINER : fitbit_data.csv
2020-11-25 22:34:05 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
FEATURES : [ "maxsumsteps" , "minsumsteps" , "avgsumsteps" , "mediansumsteps" , "stdsumsteps" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/fitbit_steps_summary/rapids/main.py
2020-11-25 22:34:05 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/fitbit-steps-intraday/
2020-11-25 22:34:05 +01:00
FITBIT_STEPS_INTRADAY :
2021-03-13 01:52:34 +01:00
CONTAINER : fitbit_data.csv
2021-05-19 00:27:12 +02:00
EXCLUDE_SLEEP : # you can exclude step data that was logged during sleep periods
TIME_BASED :
EXCLUDE : False
START_TIME : "23:00"
END_TIME : "07:00"
FITBIT_BASED :
EXCLUDE : False
2020-11-25 22:34:05 +01:00
PROVIDERS :
RAPIDS :
COMPUTE : True
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
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/fitbit_steps_intraday/rapids/main.py
2020-11-25 22:34:05 +01:00
2021-03-13 01:52:34 +01:00
########################################################################################################################
# EMPATICA #
########################################################################################################################
EMPATICA_DATA_STREAMS :
USE : empatica_zip
# AVAILABLE:
empatica_zip :
FOLDER : data/external/empatica
# Sensors ------
# See https://www.rapids.science/latest/features/empatica-accelerometer/
EMPATICA_ACCELEROMETER :
CONTAINER : ACC
PROVIDERS :
DBDP :
COMPUTE : False
FEATURES : [ "maxmagnitude" , "minmagnitude" , "avgmagnitude" , "medianmagnitude" , "stdmagnitude" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/empatica_accelerometer/dbdp/main.py
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/empatica-heartrate/
EMPATICA_HEARTRATE :
CONTAINER : HR
PROVIDERS :
DBDP :
COMPUTE : False
FEATURES : [ "maxhr" , "minhr" , "avghr" , "medianhr" , "modehr" , "stdhr" , "diffmaxmodehr" , "diffminmodehr" , "entropyhr" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/empatica_heartrate/dbdp/main.py
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/empatica-temperature/
EMPATICA_TEMPERATURE :
CONTAINER : TEMP
PROVIDERS :
DBDP :
COMPUTE : False
FEATURES : [ "maxtemp" , "mintemp" , "avgtemp" , "mediantemp" , "modetemp" , "stdtemp" , "diffmaxmodetemp" , "diffminmodetemp" , "entropytemp" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/empatica_temperature/dbdp/main.py
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/empatica-electrodermal-activity/
EMPATICA_ELECTRODERMAL_ACTIVITY :
CONTAINER : EDA
PROVIDERS :
DBDP :
COMPUTE : False
FEATURES : [ "maxeda" , "mineda" , "avgeda" , "medianeda" , "modeeda" , "stdeda" , "diffmaxmodeeda" , "diffminmodeeda" , "entropyeda" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/empatica_electrodermal_activity/dbdp/main.py
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/empatica-blood-volume-pulse/
EMPATICA_BLOOD_VOLUME_PULSE :
CONTAINER : BVP
PROVIDERS :
DBDP :
COMPUTE : False
FEATURES : [ "maxbvp" , "minbvp" , "avgbvp" , "medianbvp" , "modebvp" , "stdbvp" , "diffmaxmodebvp" , "diffminmodebvp" , "entropybvp" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/empatica_blood_volume_pulse/dbdp/main.py
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/empatica-inter-beat-interval/
EMPATICA_INTER_BEAT_INTERVAL :
CONTAINER : IBI
PROVIDERS :
DBDP :
COMPUTE : False
FEATURES : [ "maxibi" , "minibi" , "avgibi" , "medianibi" , "modeibi" , "stdibi" , "diffmaxmodeibi" , "diffminmodeibi" , "entropyibi" ]
2021-03-15 00:52:14 +01:00
SRC_SCRIPT : src/features/empatica_inter_beat_interval/dbdp/main.py
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/features/empatica-tags/
EMPATICA_TAGS :
CONTAINER : TAGS
PROVIDERS : # None implemented yet
2020-11-25 22:34:05 +01:00
2020-11-26 04:35:38 +01:00
2020-12-01 20:21:33 +01:00
########################################################################################################################
# PLOTS #
########################################################################################################################
2021-03-13 01:52:34 +01:00
# Data quality ------
# See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#1-histograms-of-phone-data-yield
2020-12-01 20:21:33 +01:00
HISTOGRAM_PHONE_DATA_YIELD :
PLOT : True
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#2-heatmaps-of-overall-data-yield
HEATMAP_PHONE_DATA_YIELD_PER_PARTICIPANT_PER_TIME_SEGMENT :
PLOT : True
2021-03-24 02:40:55 +01:00
TIME : RELATIVE_TIME # ABSOLUTE_TIME or RELATIVE_TIME
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#3-heatmap-of-recorded-phone-sensors
2020-12-04 03:00:32 +01:00
HEATMAP_SENSORS_PER_MINUTE_PER_TIME_SEGMENT :
PLOT : True
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#4-heatmap-of-sensor-row-count
2020-12-04 03:00:32 +01:00
HEATMAP_SENSOR_ROW_COUNT_PER_TIME_SEGMENT :
2021-03-24 02:40:55 +01:00
PLOT : True
2021-03-13 01:52:34 +01:00
SENSORS : [ PHONE_ACTIVITY_RECOGNITION, PHONE_APPLICATIONS_FOREGROUND, PHONE_BATTERY, PHONE_BLUETOOTH, PHONE_CALLS, PHONE_CONVERSATION, PHONE_LIGHT, PHONE_LOCATIONS, PHONE_MESSAGES, PHONE_SCREEN, PHONE_WIFI_CONNECTED, PHONE_WIFI_VISIBLE]
2020-12-04 03:00:32 +01:00
2021-03-13 01:52:34 +01:00
# Features ------
2020-12-04 03:00:32 +01:00
2021-03-13 01:52:34 +01:00
# See https://www.rapids.science/latest/visualizations/feature-visualizations/#1-heatmap-correlation-matrix
2020-12-04 03:00:32 +01:00
HEATMAP_FEATURE_CORRELATION_MATRIX :
2021-03-24 02:40:55 +01:00
PLOT : True
2020-12-04 03:00:32 +01:00
MIN_ROWS_RATIO : 0.5
CORR_THRESHOLD : 0.1
CORR_METHOD : "pearson" # choose from {"pearson", "kendall", "spearman"}
2020-12-01 20:21:33 +01:00
2021-10-03 17:16:47 +02:00
########################################################################################################################
# Data Cleaning #
########################################################################################################################
DATA_CLEANING :
COMPUTE : True
COLS_NAN_THRESHOLD : 0.3
COLS_VAR_THRESHOLD : True
ROWS_NAN_THRESHOLD : 0.3
DATA_YIELDED_HOURS_RATIO_THRESHOLD : 0.75
CORR_VALID_PAIRS_THRESHOLD : 0.5
CORR_THRESHOLD : 0.95
2020-12-01 20:21:33 +01:00
2020-11-26 04:35:38 +01:00
########################################################################################################################
# Analysis Workflow Example #
########################################################################################################################
2020-11-25 22:34:05 +01:00
2020-08-03 23:30:15 +02:00
PARAMS_FOR_ANALYSIS :
2020-11-25 22:34:05 +01:00
CATEGORICAL_OPERATORS : [ mostcommon]
DEMOGRAPHIC :
2021-03-13 01:52:34 +01:00
FOLDER : data/external/example_workflow
CONTAINER : participant_info.csv
2020-11-25 22:34:05 +01:00
FEATURES : [ age, gender, inpatientdays]
CATEGORICAL_FEATURES : [ gender]
TARGET :
2021-03-13 01:52:34 +01:00
FOLDER : data/external/example_workflow
CONTAINER : participant_target.csv
2020-11-25 22:34:05 +01:00
MODEL_NAMES : [ LogReg, kNN , SVM, DT, RF, GB, XGBoost, LightGBM]
CV_METHODS : [ LeaveOneOut]
RESULT_COMPONENTS : [ fold_predictions, fold_metrics, overall_results, fold_feature_importances]
2020-08-03 23:30:15 +02:00
MODEL_SCALER :
2020-11-25 22:34:05 +01:00
LogReg : [ notnormalized, minmaxscaler, standardscaler, robustscaler]
kNN : [ minmaxscaler, standardscaler, robustscaler]
SVM : [ minmaxscaler, standardscaler, robustscaler]
DT : [ notnormalized]
RF : [ notnormalized]
GB : [ notnormalized]
XGBoost : [ notnormalized]
LightGBM : [ notnormalized]
2020-08-03 23:30:15 +02:00
MODEL_HYPERPARAMS :
LogReg :
{"clf__C": [0.01, 0.1, 1, 10, 100], "clf__solver": ["newton-cg", "lbfgs", "liblinear", "saga"], "clf__penalty": [ "l2" ] }
kNN :
2020-11-25 22:34:05 +01:00
{"clf__n_neighbors": [3, 5, 7], "clf__weights": ["uniform", "distance"], "clf__metric": [ "euclidean" , "manhattan" , "minkowski" ] }
2020-08-03 23:30:15 +02:00
SVM :
{"clf__C": [0.01, 0.1, 1, 10, 100], "clf__gamma": ["scale", "auto"], "clf__kernel": [ "rbf" , "poly" , "sigmoid" ] }
DT :
2020-11-25 22:34:05 +01:00
{"clf__criterion": ["gini", "entropy"], "clf__max_depth": [null, 3, 7, 15], "clf__max_features": [ null , "auto" , "sqrt" , "log2" ] }
2020-08-03 23:30:15 +02:00
RF :
2020-11-25 22:34:05 +01:00
{"clf__n_estimators": [10, 100, 200],"clf__max_depth": [ null , 3 , 7 , 15 ] }
2020-08-03 23:30:15 +02:00
GB :
2020-11-25 22:34:05 +01:00
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [10, 100, 200], "clf__subsample": [0.5, 0.7, 1.0], "clf__max_depth": [ null , 3 , 5 , 7 ] }
2020-08-03 23:30:15 +02:00
XGBoost :
2020-11-25 22:34:05 +01:00
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [10, 100, 200], "clf__max_depth": [ 3 , 5 , 7 ] }
2020-08-03 23:30:15 +02:00
LightGBM :
2020-11-25 22:34:05 +01:00
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [10, 100, 200], "clf__num_leaves": [3, 5, 7], "clf__colsample_bytree": [ 0.6 , 0.8 , 1 ] }