rapids/config.yaml

753 lines
37 KiB
YAML

########################################################################################################################
# GLOBAL CONFIGURATION #
########################################################################################################################
# See https://www.rapids.science/latest/setup/configuration/#participant-files
PIDS: ['p031', 'p032', 'p033', 'p034', 'p035', 'p036', 'p037', 'p038', 'p039', 'p040', 'p042', 'p043', 'p044', 'p045', 'p046', 'p049', 'p050', 'p052', 'p053', 'p054', 'p055', 'p057', 'p058', 'p059', 'p060', 'p061', 'p062', 'p064', 'p067', 'p068', 'p069', 'p070', 'p071', 'p072', 'p073', 'p074', 'p075', 'p076', 'p077', 'p078', 'p079', 'p080', 'p081', 'p082', 'p083', 'p084', 'p085', 'p086', 'p088', 'p089', 'p090', 'p091', 'p092', 'p093', 'p106', 'p107']
# See https://www.rapids.science/latest/setup/configuration/#automatic-creation-of-participant-files
CREATE_PARTICIPANT_FILES:
USERNAMES_CSV: "data/external/main_study_usernames.csv"
CSV_FILE_PATH: "data/external/main_study_participants.csv" # see docs for required format
PHONE_SECTION:
ADD: True
IGNORED_DEVICE_IDS: []
FITBIT_SECTION:
ADD: False
IGNORED_DEVICE_IDS: []
EMPATICA_SECTION:
ADD: True
IGNORED_DEVICE_IDS: []
# See https://www.rapids.science/latest/setup/configuration/#time-segments
TIME_SEGMENTS: &time_segments
TYPE: EVENT # FREQUENCY, PERIODIC, EVENT
FILE: "data/external/straw_events.csv"
INCLUDE_PAST_PERIODIC_SEGMENTS: TRUE # Only relevant if TYPE=PERIODIC, see docs
TAILORED_EVENTS: # Only relevant if TYPE=EVENT
COMPUTE: True
SEGMENTING_METHOD: "30_before" # 30_before, 90_before, stress_event
INTERVAL_OF_INTEREST: 10 # duration of event of interest [minutes]
IOI_ERROR_TOLERANCE: 5 # interval of interest erorr tolerance (before and after IOI) [minutes]
# See https://www.rapids.science/latest/setup/configuration/#timezone-of-your-study
TIMEZONE:
TYPE: MULTIPLE
SINGLE:
TZCODE: Europe/Ljubljana
MULTIPLE:
TZ_FILE: data/external/timezone.csv
TZCODES_FILE: data/external/multiple_timezones.csv
IF_MISSING_TZCODE: USE_DEFAULT
DEFAULT_TZCODE: Europe/Ljubljana
FITBIT:
ALLOW_MULTIPLE_TZ_PER_DEVICE: False
INFER_FROM_SMARTPHONE_TZ: False
########################################################################################################################
# PHONE #
########################################################################################################################
# See https://www.rapids.science/latest/setup/configuration/#data-stream-configuration
PHONE_DATA_STREAMS:
USE: aware_postgresql
# AVAILABLE:
aware_mysql:
DATABASE_GROUP: MY_GROUP
aware_postgresql:
DATABASE_GROUP: PSQL_STRAW
aware_csv:
FOLDER: data/external/aware_csv
aware_influxdb:
DATABASE_GROUP: MY_GROUP
# Sensors ------
# https://www.rapids.science/latest/features/phone-accelerometer/
PHONE_ACCELEROMETER:
CONTAINER: accelerometer
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
SRC_SCRIPT: src/features/phone_accelerometer/rapids/main.py
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"]
SRC_SCRIPT: src/features/phone_accelerometer/panda/main.py
# See https://www.rapids.science/latest/features/phone-activity-recognition/
PHONE_ACTIVITY_RECOGNITION:
CONTAINER:
ANDROID: google_ar
IOS: plugin_ios_activity_recognition
EPISODE_THRESHOLD_BETWEEN_ROWS: 5 # minutes. Max time difference for two consecutive rows to be considered within the same AR episode.
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["count", "mostcommonactivity", "countuniqueactivities", "durationstationary", "durationmobile", "durationvehicle"]
ACTIVITY_CLASSES:
STATIONARY: ["still", "tilting"]
MOBILE: ["on_foot", "walking", "running", "on_bicycle"]
VEHICLE: ["in_vehicle"]
SRC_SCRIPT: src/features/phone_activity_recognition/rapids/main.py
# 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/play_store_application_genre_catalogue.csv"
UPDATE_CATALOGUE_FILE: False # if CATALOGUE_SOURCE is equal to FILE, whether 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 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/
PHONE_APPLICATIONS_FOREGROUND:
CONTAINER: applications
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/play_store_application_genre_catalogue.csv"
# Refer to data/external/play_store_categories_count.csv for a list of categories (genres) and their frequency.
PACKAGE_NAMES_HASHED: True
UPDATE_CATALOGUE_FILE: False # if CATALOGUE_SOURCE is equal to FILE, whether 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 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:
COMPUTE: True
INCLUDE_EPISODE_FEATURES: True
SINGLE_CATEGORIES: ["Productivity", "Tools", "Communication", "Education", "Social"]
MULTIPLE_CATEGORIES:
games: ["Puzzle", "Card", "Casual", "Board", "Strategy", "Trivia", "Word", "Adventure", "Role Playing", "Simulation", "Board, Brain Games", "Racing"]
social: ["Communication", "Social", "Dating"]
productivity: ["Tools", "Productivity", "Finance", "Education", "News & Magazines", "Business", "Books & Reference"]
health: ["Health & Fitness", "Lifestyle", "Food & Drink", "Sports", "Medical", "Parenting"]
entertainment: ["Shopping", "Music & Audio", "Entertainment", "Travel & Local", "Photography", "Video Players & Editors", "Personalization", "House & Home", "Art & Design", "Auto & Vehicles", "Entertainment,Music & Video",
"Puzzle", "Card", "Casual", "Board", "Strategy", "Trivia", "Word", "Adventure", "Role Playing", "Simulation", "Board, Brain Games", "Racing" # Add all games.
]
maps_weather: ["Maps & Navigation", "Weather"]
EXCLUDED_CATEGORIES: ["System", "STRAW"]
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
SRC_SCRIPT: src/features/phone_applications_foreground/rapids/main.py
# See https://www.rapids.science/latest/features/phone-applications-notifications/
PHONE_APPLICATIONS_NOTIFICATIONS:
CONTAINER: 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/
PHONE_BATTERY:
CONTAINER: battery
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"]
SRC_SCRIPT: src/features/phone_battery/rapids/main.py
# See https://www.rapids.science/latest/features/phone-bluetooth/
PHONE_BLUETOOTH:
CONTAINER: bluetooth
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_SCRIPT: src/features/phone_bluetooth/rapids/main.R
DORYAB:
COMPUTE: True
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"]
SRC_SCRIPT: src/features/phone_bluetooth/doryab/main.py
# See https://www.rapids.science/latest/features/phone-calls/
PHONE_CALLS:
CONTAINER: call
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES_TYPE: EPISODES # EVENTS or EPISODES
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_SCRIPT: src/features/phone_calls/rapids/main.R
# See https://www.rapids.science/latest/features/phone-conversation/
PHONE_CONVERSATION: # TODO Adapt for speech
CONTAINER:
ANDROID: plugin_studentlife_audio_android
IOS: plugin_studentlife_audio
PROVIDERS:
RAPIDS:
COMPUTE: False
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
SRC_SCRIPT: src/features/phone_conversation/rapids/main.py
# See https://www.rapids.science/latest/features/phone-data-yield/
PHONE_DATA_YIELD:
SENSORS: [#PHONE_ACCELEROMETER,
PHONE_ACTIVITY_RECOGNITION,
PHONE_APPLICATIONS_FOREGROUND,
PHONE_APPLICATIONS_NOTIFICATIONS,
PHONE_BATTERY,
PHONE_BLUETOOTH,
PHONE_CALLS,
PHONE_LIGHT,
PHONE_LOCATIONS,
PHONE_MESSAGES,
PHONE_SCREEN,
PHONE_WIFI_VISIBLE]
PROVIDERS:
RAPIDS:
COMPUTE: True
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.
SRC_SCRIPT: src/features/phone_data_yield/rapids/main.R
PHONE_ESM:
CONTAINER: esm
PROVIDERS:
STRAW:
COMPUTE: True
SCALES: ["PANAS_positive_affect", "PANAS_negative_affect", "JCQ_job_demand", "JCQ_job_control", "JCQ_supervisor_support", "JCQ_coworker_support",
"appraisal_stressfulness_period", "appraisal_stressfulness_event", "appraisal_threat", "appraisal_challenge"]
FEATURES: [mean]
SRC_SCRIPT: src/features/phone_esm/straw/main.py
# See https://www.rapids.science/latest/features/phone-keyboard/
PHONE_KEYBOARD:
CONTAINER: keyboard
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["sessioncount","averageinterkeydelay","averagesessionlength","changeintextlengthlessthanminusone","changeintextlengthequaltominusone","changeintextlengthequaltoone","changeintextlengthmorethanone","maxtextlength","lastmessagelength","totalkeyboardtouches"]
SRC_SCRIPT: src/features/phone_keyboard/rapids/main.py
# See https://www.rapids.science/latest/features/phone-light/
PHONE_LIGHT:
CONTAINER: light_sensor
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
SRC_SCRIPT: src/features/phone_light/rapids/main.py
# See https://www.rapids.science/latest/features/phone-locations/
PHONE_LOCATIONS:
CONTAINER: locations
LOCATIONS_TO_USE: ALL_RESAMPLED # ALL, GPS, ALL_RESAMPLED, 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
ACCURACY_LIMIT: 100 # meters, drops location coordinates with an accuracy equal or higher than this. This number means there's a 68% probability the true location is within this radius
PROVIDERS:
DORYAB:
COMPUTE: True
FEATURES: ["locationvariance","loglocationvariance","totaldistance","avgspeed","varspeed", "numberofsignificantplaces","numberlocationtransitions","radiusgyration","timeattop1location","timeattop2location","timeattop3location","movingtostaticratio","outlierstimepercent","maxlengthstayatclusters","minlengthstayatclusters","avglengthstayatclusters","stdlengthstayatclusters","locationentropy","normalizedlocationentropy","timeathome", "homelabel"]
DBSCAN_EPS: 100 # meters
DBSCAN_MINSAMPLES: 5
THRESHOLD_STATIC : 1 # km/h
MAXIMUM_ROW_GAP: 300 # seconds
MINUTES_DATA_USED: False
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
RADIUS_FOR_HOME: 100
SRC_SCRIPT: src/features/phone_locations/doryab/main.py
BARNETT:
COMPUTE: True
FEATURES: ["hometime","disttravelled","rog","maxdiam","maxhomedist","siglocsvisited","avgflightlen","stdflightlen","avgflightdur","stdflightdur","probpause","siglocentropy","circdnrtn","wkenddayrtn"]
IF_MULTIPLE_TIMEZONES: USE_MOST_COMMON
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
SRC_SCRIPT: src/features/phone_locations/barnett/main.R
# 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/
PHONE_MESSAGES:
CONTAINER: sms
PROVIDERS:
RAPIDS:
COMPUTE: True
MESSAGES_TYPES : [received, sent]
FEATURES:
received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
sent: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
SRC_SCRIPT: src/features/phone_messages/rapids/main.R
# See https://www.rapids.science/latest/features/phone-screen/
PHONE_SCREEN:
CONTAINER: screen
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: 360 # in minutes, set to 0 to disable
FEATURES: ["countepisode", "sumduration", "maxduration", "minduration", "avgduration", "stdduration", "firstuseafter"] # "episodepersensedminutes" needs to be added later
EPISODE_TYPES: ["unlock"]
SRC_SCRIPT: src/features/phone_screen/rapids/main.py
# Custom added sensor
PHONE_SPEECH:
CONTAINER: speech
PROVIDERS:
STRAW:
COMPUTE: True
FEATURES: ["meanspeech", "stdspeech", "nlargest", "nsmallest", "medianspeech"]
SRC_SCRIPT: src/features/phone_speech/straw/main.py
# See https://www.rapids.science/latest/features/phone-wifi-connected/
PHONE_WIFI_CONNECTED:
CONTAINER: sensor_wifi
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_SCRIPT: src/features/phone_wifi_connected/rapids/main.R
# See https://www.rapids.science/latest/features/phone-wifi-visible/
PHONE_WIFI_VISIBLE:
CONTAINER: wifi
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_SCRIPT: src/features/phone_wifi_visible/rapids/main.R
########################################################################################################################
# FITBIT #
########################################################################################################################
# See https://www.rapids.science/latest/setup/configuration/#data-stream-configuration
FITBIT_DATA_STREAMS:
USE: fitbitjson_mysql
# AVAILABLE:
fitbitjson_mysql:
DATABASE_GROUP: MY_GROUP
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).
fitbitparsed_mysql:
DATABASE_GROUP: MY_GROUP
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).
fitbitjson_csv:
FOLDER: data/external/fitbit_csv
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).
fitbitparsed_csv:
FOLDER: data/external/fitbit_csv
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).
# Sensors ------
# See https://www.rapids.science/latest/features/fitbit-calories-intraday/
FITBIT_CALORIES_INTRADAY:
CONTAINER: fitbit_data
PROVIDERS:
RAPIDS:
COMPUTE: False
EPISODE_TYPE: [sedentary, lightlyactive, fairlyactive, veryactive, mvpa, lowmet, highmet]
EPISODE_TIME_THRESHOLD: 5 # minutes
EPISODE_MET_THRESHOLD: 3
EPISODE_MVPA_CATEGORIES: [fairlyactive, veryactive]
EPISODE_REFERENCE_TIME: MIDNIGHT # or START_OF_THE_SEGMENT
FEATURES: [count, sumduration, avgduration, minduration, maxduration, stdduration, starttimefirst, endtimefirst, starttimelast, endtimelast, starttimelongest, endtimelongest, summet, avgmet, maxmet, minmet, stdmet, sumcalories, avgcalories, maxcalories, mincalories, stdcalories]
SRC_SCRIPT: src/features/fitbit_calories_intraday/rapids/main.R
# 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.
SRC_SCRIPT: src/features/fitbit_data_yield/rapids/main.R
# See https://www.rapids.science/latest/features/fitbit-heartrate-summary/
FITBIT_HEARTRATE_SUMMARY:
CONTAINER: heartrate_summary
PROVIDERS:
RAPIDS:
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_SCRIPT: src/features/fitbit_heartrate_summary/rapids/main.py
# See https://www.rapids.science/latest/features/fitbit-heartrate-intraday/
FITBIT_HEARTRATE_INTRADAY:
CONTAINER: heartrate_intraday
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "minutesonoutofrangezone", "minutesonfatburnzone", "minutesoncardiozone", "minutesonpeakzone"]
SRC_SCRIPT: src/features/fitbit_heartrate_intraday/rapids/main.py
# See https://www.rapids.science/latest/features/fitbit-sleep-summary/
FITBIT_SLEEP_SUMMARY:
CONTAINER: sleep_summary
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["firstwaketime", "lastwaketime", "firstbedtime", "lastbedtime", "countepisode", "avgefficiency", "sumdurationafterwakeup", "sumdurationasleep", "sumdurationawake", "sumdurationtofallasleep", "sumdurationinbed", "avgdurationafterwakeup", "avgdurationasleep", "avgdurationawake", "avgdurationtofallasleep", "avgdurationinbed"]
SLEEP_TYPES: ["main", "nap", "all"]
SRC_SCRIPT: src/features/fitbit_sleep_summary/rapids/main.py
# 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:
INCLUDE_ALL_GROUPS: True
CLASSIC: [awake, restless, asleep]
STAGES: [wake, deep, light, rem]
UNIFIED: [awake, asleep]
SLEEP_TYPES: [main, nap, all]
SRC_SCRIPT: src/features/fitbit_sleep_intraday/rapids/main.py
PRICE:
COMPUTE: False
FEATURES: [avgduration, avgratioduration, avgstarttimeofepisodemain, avgendtimeofepisodemain, avgmidpointofepisodemain, stdstarttimeofepisodemain, stdendtimeofepisodemain, stdmidpointofepisodemain, socialjetlag, rmssdmeanstarttimeofepisodemain, rmssdmeanendtimeofepisodemain, rmssdmeanmidpointofepisodemain, rmssdmedianstarttimeofepisodemain, rmssdmedianendtimeofepisodemain, rmssdmedianmidpointofepisodemain]
SLEEP_LEVELS:
INCLUDE_ALL_GROUPS: True
CLASSIC: [awake, restless, asleep]
STAGES: [wake, deep, light, rem]
UNIFIED: [awake, asleep]
DAY_TYPES: [WEEKEND, WEEK, ALL]
LAST_NIGHT_END: 660 # number of minutes after midnight (11:00) 11*60
SRC_SCRIPT: src/features/fitbit_sleep_intraday/price/main.py
# See https://www.rapids.science/latest/features/fitbit-steps-summary/
FITBIT_STEPS_SUMMARY:
CONTAINER: steps_summary
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["maxsumsteps", "minsumsteps", "avgsumsteps", "mediansumsteps", "stdsumsteps"]
SRC_SCRIPT: src/features/fitbit_steps_summary/rapids/main.py
# See https://www.rapids.science/latest/features/fitbit-steps-intraday/
FITBIT_STEPS_INTRADAY:
CONTAINER: steps_intraday
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
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES:
STEPS: ["sum", "max", "min", "avg", "std", "firststeptime", "laststeptime"]
SEDENTARY_BOUT: ["countepisode", "sumduration", "maxduration", "minduration", "avgduration", "stdduration"]
ACTIVE_BOUT: ["countepisode", "sumduration", "maxduration", "minduration", "avgduration", "stdduration"]
REFERENCE_HOUR: 0
THRESHOLD_ACTIVE_BOUT: 10 # steps
INCLUDE_ZERO_STEP_ROWS: False
SRC_SCRIPT: src/features/fitbit_steps_intraday/rapids/main.py
########################################################################################################################
# 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"]
SRC_SCRIPT: src/features/empatica_accelerometer/dbdp/main.py
CR:
COMPUTE: True
FEATURES: ["totalMagnitudeBand", "absoluteMeanBand", "varianceBand"] # Acc features
WINDOWS:
COMPUTE: True
WINDOW_LENGTH: 15 # specify window length in seconds
SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows']
SRC_SCRIPT: src/features/empatica_accelerometer/cr/main.py
# 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"]
SRC_SCRIPT: src/features/empatica_heartrate/dbdp/main.py
# 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"]
SRC_SCRIPT: src/features/empatica_temperature/dbdp/main.py
CR:
COMPUTE: True
FEATURES: ["maximum", "minimum", "meanAbsChange", "longestStrikeAboveMean", "longestStrikeBelowMean",
"stdDev", "median", "meanChange", "sumSquared", "squareSumOfComponent", "sumOfSquareComponents"]
WINDOWS:
COMPUTE: True
WINDOW_LENGTH: 300 # specify window length in seconds
SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows']
SRC_SCRIPT: src/features/empatica_temperature/cr/main.py
# 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"]
SRC_SCRIPT: src/features/empatica_electrodermal_activity/dbdp/main.py
CR:
COMPUTE: True
FEATURES: ['mean', 'std', 'q25', 'q75', 'qd', 'deriv', 'power', 'numPeaks', 'ratePeaks', 'powerPeaks', 'sumPosDeriv', 'propPosDeriv', 'derivTonic',
'sigTonicDifference', 'freqFeats','maxPeakAmplitudeChangeBefore', 'maxPeakAmplitudeChangeAfter', 'avgPeakAmplitudeChangeBefore',
'avgPeakAmplitudeChangeAfter', 'avgPeakChangeRatio', 'maxPeakIncreaseTime', 'maxPeakDecreaseTime', 'maxPeakDuration', 'maxPeakChangeRatio',
'avgPeakIncreaseTime', 'avgPeakDecreaseTime', 'avgPeakDuration', 'signalOverallChange', 'changeDuration', 'changeRate', 'significantIncrease',
'significantDecrease']
WINDOWS:
COMPUTE: True
WINDOW_LENGTH: 60 # specify window length in seconds
SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', count_windows, eda_num_peaks_non_zero]
IMPUTE_NANS: True
SRC_SCRIPT: src/features/empatica_electrodermal_activity/cr/main.py
# 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"]
SRC_SCRIPT: src/features/empatica_blood_volume_pulse/dbdp/main.py
CR:
COMPUTE: False
FEATURES: ['meanHr', 'ibi', 'sdnn', 'sdsd', 'rmssd', 'pnn20', 'pnn50', 'sd', 'sd2', 'sd1/sd2', 'numRR', # Time features
'VLF', 'LF', 'LFnorm', 'HF', 'HFnorm', 'LF/HF', 'fullIntegral'] # Freq features
WINDOWS:
COMPUTE: True
WINDOW_LENGTH: 300 # specify window length in seconds
SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows', 'hrv_num_windows_non_nan']
SRC_SCRIPT: src/features/empatica_blood_volume_pulse/cr/main.py
# 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"]
SRC_SCRIPT: src/features/empatica_inter_beat_interval/dbdp/main.py
CR:
COMPUTE: True
FEATURES: ['meanHr', 'ibi', 'sdnn', 'sdsd', 'rmssd', 'pnn20', 'pnn50', 'sd', 'sd2', 'sd1/sd2', 'numRR', # Time features
'VLF', 'LF', 'LFnorm', 'HF', 'HFnorm', 'LF/HF', 'fullIntegral'] # Freq features
PATCH_WITH_BVP: True
WINDOWS:
COMPUTE: True
WINDOW_LENGTH: 300 # specify window length in seconds
SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'nlargest', 'nsmallest', 'count_windows', 'hrv_num_windows_non_nan']
SRC_SCRIPT: src/features/empatica_inter_beat_interval/cr/main.py
# See https://www.rapids.science/latest/features/empatica-tags/
EMPATICA_TAGS:
CONTAINER: TAGS
PROVIDERS: # None implemented yet
########################################################################################################################
# PLOTS #
########################################################################################################################
# Data quality ------
# See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#1-histograms-of-phone-data-yield
HISTOGRAM_PHONE_DATA_YIELD:
PLOT: False
# 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: False
TIME: RELATIVE_TIME # ABSOLUTE_TIME or RELATIVE_TIME
# See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#3-heatmap-of-recorded-phone-sensors
HEATMAP_SENSORS_PER_MINUTE_PER_TIME_SEGMENT:
PLOT: False
# See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#4-heatmap-of-sensor-row-count
HEATMAP_SENSOR_ROW_COUNT_PER_TIME_SEGMENT:
PLOT: False
SENSORS: []
# Features ------
# See https://www.rapids.science/latest/visualizations/feature-visualizations/#1-heatmap-correlation-matrix
HEATMAP_FEATURE_CORRELATION_MATRIX:
PLOT: False
MIN_ROWS_RATIO: 0.5
CORR_THRESHOLD: 0.1
CORR_METHOD: "pearson" # choose from {"pearson", "kendall", "spearman"}
########################################################################################################################
# Data Cleaning #
########################################################################################################################
ALL_CLEANING_INDIVIDUAL:
PROVIDERS:
RAPIDS:
COMPUTE: False
IMPUTE_SELECTED_EVENT_FEATURES:
COMPUTE: False
MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33
COLS_NAN_THRESHOLD: 1 # set to 1 to disable
COLS_VAR_THRESHOLD: True
ROWS_NAN_THRESHOLD: 1 # set to 1 to disable
DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
DATA_YIELD_RATIO_THRESHOLD: 0 # set to 0 to disable
DROP_HIGHLY_CORRELATED_FEATURES:
COMPUTE: True
MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
CORR_THRESHOLD: 0.95
SRC_SCRIPT: src/features/all_cleaning_individual/rapids/main.R
STRAW:
COMPUTE: True
PHONE_DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_MINUTES # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
PHONE_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
EMPATICA_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
ROWS_NAN_THRESHOLD: 0.33 # set to 1 to disable
COLS_NAN_THRESHOLD: 0.9 # set to 1 to remove only columns that contains all (100% of) NaN
COLS_VAR_THRESHOLD: True
DROP_HIGHLY_CORRELATED_FEATURES:
COMPUTE: True
MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
CORR_THRESHOLD: 0.95
STANDARDIZATION: True
SRC_SCRIPT: src/features/all_cleaning_individual/straw/main.py
ALL_CLEANING_OVERALL:
PROVIDERS:
RAPIDS:
COMPUTE: False
IMPUTE_SELECTED_EVENT_FEATURES:
COMPUTE: False
MIN_DATA_YIELDED_MINUTES_TO_IMPUTE: 0.33
COLS_NAN_THRESHOLD: 1 # set to 1 to disable
COLS_VAR_THRESHOLD: True
ROWS_NAN_THRESHOLD: 1 # set to 1 to disable
DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_HOURS # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
DATA_YIELD_RATIO_THRESHOLD: 0 # set to 0 to disable
DROP_HIGHLY_CORRELATED_FEATURES:
COMPUTE: True
MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
CORR_THRESHOLD: 0.95
SRC_SCRIPT: src/features/all_cleaning_overall/rapids/main.R
STRAW:
COMPUTE: True
PHONE_DATA_YIELD_FEATURE: RATIO_VALID_YIELDED_MINUTES # RATIO_VALID_YIELDED_HOURS or RATIO_VALID_YIELDED_MINUTES
PHONE_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
EMPATICA_DATA_YIELD_RATIO_THRESHOLD: 0.5 # set to 0 to disable
ROWS_NAN_THRESHOLD: 0.33 # set to 1 to disable
COLS_NAN_THRESHOLD: 0.8 # set to 1 to remove only columns that contains all (100% of) NaN
COLS_VAR_THRESHOLD: True
DROP_HIGHLY_CORRELATED_FEATURES:
COMPUTE: True
MIN_OVERLAP_FOR_CORR_THRESHOLD: 0.5
CORR_THRESHOLD: 0.95
STANDARDIZATION: True
TARGET_STANDARDIZATION: False
SRC_SCRIPT: src/features/all_cleaning_overall/straw/main.py
########################################################################################################################
# Baseline #
########################################################################################################################
PARAMS_FOR_ANALYSIS:
BASELINE:
COMPUTE: True
FOLDER: data/external/baseline
CONTAINER: [results-survey637813_final.csv, # Slovenia
results-survey358134_final.csv, # Belgium 1
results-survey413767_final.csv # Belgium 2
]
QUESTION_LIST: survey637813+question_text.csv
FEATURES: [age, gender, startlanguage, limesurvey_demand, limesurvey_control, limesurvey_demand_control_ratio, limesurvey_demand_control_ratio_quartile]
CATEGORICAL_FEATURES: [gender]
TARGET:
COMPUTE: True
LABEL: appraisal_stressfulness_event_mean
ALL_LABELS: [PANAS_positive_affect_mean, PANAS_negative_affect_mean, JCQ_job_demand_mean, JCQ_job_control_mean, JCQ_supervisor_support_mean, JCQ_coworker_support_mean, appraisal_stressfulness_period_mean]
# PANAS_positive_affect_mean, PANAS_negative_affect_mean, JCQ_job_demand_mean, JCQ_job_control_mean, JCQ_supervisor_support_mean,
# JCQ_coworker_support_mean, appraisal_stressfulness_period_mean, appraisal_stressfulness_event_mean, appraisal_threat_mean, appraisal_challenge_mean