rapids/example_profile/example_config.yaml

586 lines
29 KiB
YAML

########################################################################################################################
# GLOBAL CONFIGURATION #
########################################################################################################################
# See https://www.rapids.science/latest/setup/configuration/#participant-files
PIDS: [example01, example02]
# See https://www.rapids.science/latest/setup/configuration/#time-segments
TIME_SEGMENTS: &time_segments
TYPE: PERIODIC # FREQUENCY, PERIODIC, EVENT
FILE: "example_profile/exampleworkflow_timesegments.csv"
INCLUDE_PAST_PERIODIC_SEGMENTS: FALSE # Only relevant if TYPE=PERIODIC, see docs
# 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
########################################################################################################################
# PHONE #
########################################################################################################################
# See https://www.rapids.science/latest/setup/configuration/#data-stream-configuration
PHONE_DATA_STREAMS:
USE: aware_csv
# AVAILABLE:
aware_mysql:
DATABASE_GROUP: MY_GROUP
aware_csv:
FOLDER: data/external/example_workflow
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: plugin_google_activity_recognition.csv
IOS: plugin_ios_activity_recognition.csv
EPISODE_THRESHOLD_BETWEEN_ROWS: 5 # minutes. Max time difference for two consecutive rows to be considered within the same battery 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/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/
PHONE_APPLICATIONS_FOREGROUND:
CONTAINER: applications_foreground.csv
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:
COMPUTE: True
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"]
FEATURES: ["count", "timeoffirstuse", "timeoflastuse", "frequencyentropy"]
SRC_SCRIPT: src/features/phone_applications_foreground/rapids/main.py
# 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/
PHONE_BATTERY:
CONTAINER: battery.csv
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.csv
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_SCRIPT: src/features/phone_bluetooth/rapids/main.R
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"]
SRC_SCRIPT: src/features/phone_bluetooth/doryab/main.py
# See https://www.rapids.science/latest/features/phone-calls/
PHONE_CALLS:
CONTAINER: calls.csv
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]
SRC_SCRIPT: src/features/phone_calls/rapids/main.R
# See https://www.rapids.science/latest/features/phone-conversation/
PHONE_CONVERSATION:
CONTAINER:
ANDROID: plugin_studentlife_audio_android.csv
IOS: plugin_studentlife_audio.csv
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
SRC_SCRIPT: src/features/phone_conversation/rapids/main.py
# See https://www.rapids.science/latest/features/phone-data-yield/
PHONE_DATA_YIELD:
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]
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
# See https://www.rapids.science/latest/features/phone-keyboard/
PHONE_KEYBOARD:
CONTAINER: keyboard
PROVIDERS: # None implemented yet but this sensor can be used in PHONE_DATA_YIELD
# See https://www.rapids.science/latest/features/phone-light/
PHONE_LIGHT:
CONTAINER: light.csv
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.csv
LOCATIONS_TO_USE: FUSED_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
HOME_INFERENCE:
DBSCAN_EPS: 10 # meters
DBSCAN_MINSAMPLES: 5
THRESHOLD_STATIC : 1 # km/h
CLUSTERING_ALGORITHM: DBSCAN #DBSCAN,OPTICS
PROVIDERS:
DORYAB:
COMPUTE: True
FEATURES: ["locationvariance","loglocationvariance","totaldistance","averagespeed","varspeed", "numberofsignificantplaces","numberlocationtransitions","radiusgyration","timeattop1location","timeattop2location","timeattop3location","movingtostaticratio","outlierstimepercent","maxlengthstayatclusters","minlengthstayatclusters","meanlengthstayatclusters","stdlengthstayatclusters","locationentropy","normalizedlocationentropy","timeathome"]
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
DBSCAN_EPS: 10 # meters
DBSCAN_MINSAMPLES: 5
THRESHOLD_STATIC : 1 # km/h
MAXIMUM_ROW_GAP: 300
MAXIMUM_ROW_DURATION: 60
MINUTES_DATA_USED: False
CLUSTER_ON: PARTICIPANT_DATASET # PARTICIPANT_DATASET,TIME_SEGMENT
CLUSTERING_ALGORITHM: DBSCAN #DBSCAN,OPTICS
RADIUS_FOR_HOME: 100
SRC_SCRIPT: src/features/phone_locations/doryab/main.py
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
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: messages.csv
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.csv
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"]
SRC_SCRIPT: src/features/phone_screen/rapids/main.py
# See https://www.rapids.science/latest/features/phone-wifi-connected/
PHONE_WIFI_CONNECTED:
CONTAINER: sensor_wifi.csv
PROVIDERS:
RAPIDS:
COMPUTE: True
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.csv
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_csv
# AVAILABLE:
fitbitjson_mysql:
DATABASE_GROUP: MY_GROUP
SLEEP_SUMMARY_EPISODE_DAY_ANCHOR: end # summary sleep episodes are considered as events based on either the start timestamp or end timestamp.
fitbitparsed_mysql:
DATABASE_GROUP: MY_GROUP
SLEEP_SUMMARY_EPISODE_DAY_ANCHOR: end # summary sleep episodes are considered as events based on either the start timestamp or end timestamp.
fitbitjson_csv:
FOLDER: data/external/example_workflow
SLEEP_SUMMARY_EPISODE_DAY_ANCHOR: end # summary sleep episodes are considered as events based on either the start timestamp or end timestamp.
fitbitparsed_csv:
FOLDER: data/external/fitbit_csv
SLEEP_SUMMARY_EPISODE_DAY_ANCHOR: end # summary sleep episodes are considered as events based on either the start timestamp or end timestamp.
# 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.
SRC_SCRIPT: src/features/fitbit_data_yield/rapids/main.R
# See https://www.rapids.science/latest/features/fitbit-heartrate-summary/
FITBIT_HEARTRATE_SUMMARY:
CONTAINER: fitbit_data.csv
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"]
SRC_SCRIPT: src/features/fitbit_heartrate_summary/rapids/main.py
# See https://www.rapids.science/latest/features/fitbit-heartrate-intraday/
FITBIT_HEARTRATE_INTRADAY:
CONTAINER: fitbit_data.csv
PROVIDERS:
RAPIDS:
COMPUTE: True
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: fitbit_data.csv
SLEEP_EPISODE_TIMESTAMP: end # summary sleep episodes are considered as events based on either the start timestamp or end timestamp.
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["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_COMBINING_ALL: True
LEVELS_AND_TYPES: [countepisode, sumduration, maxduration, minduration, avgduration, medianduration, stdduration]
RATIOS_TYPE: [count, duration]
RATIOS_SCOPE: [ACROSS_LEVELS, ACROSS_TYPES, WITHIN_LEVELS, WITHIN_TYPES]
ROUTINE: [starttimefirstmainsleep, endtimelastmainsleep, starttimefirstnap, endtimelastnap]
SLEEP_LEVELS:
CLASSIC: [awake, restless, asleep]
STAGES: [wake, deep, light, rem]
UNIFIED: [awake, asleep]
SLEEP_TYPES: [main, nap]
INCLUDE_SLEEP_LATER_THAN: 0 # a number ranged from 0 (midnight) to 1439 (23:59)
REFERENCE_TIME: MIDNIGHT # chosen from "MIDNIGHT" and "START_OF_THE_SEGMENT"
SRC_SCRIPT: src/features/fitbit_sleep_intraday/rapids/main.py
PRICE:
COMPUTE: False
FEATURES: [avgduration, avgratioduration, avgstarttimeofepisodemain, avgendtimeofepisodemain, avgmidpointofepisodemain, "stdstarttimeofepisodemain", "stdendtimeofepisodemain", "stdmidpointofepisodemain", socialjetlag, meanssdstarttimeofepisodemain, meanssdendtimeofepisodemain, meanssdmidpointofepisodemain, medianssdstarttimeofepisodemain, medianssdendtimeofepisodemain, medianssdmidpointofepisodemain]
SLEEP_LEVELS:
CLASSIC: [awake, restless, asleep]
STAGES: [wake, deep, light, rem]
UNIFIED: [awake, asleep]
DAY_TYPES: [WEEKEND, WEEK, ALL]
GROUP_EPISODES_WITHIN: # by default: today's 6pm to tomorrow's noon
START_TIME: 1080 # number of minutes after the midnight (18:00) 18*60
LENGTH: 1080 # in minutes (18 hours) 18*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: fitbit_data.csv
PROVIDERS:
RAPIDS:
COMPUTE: True
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: fitbit_data.csv
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
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
# 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
# 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
# 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
# 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
# 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: True
# 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
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: True
# See https://www.rapids.science/latest/visualizations/data-quality-visualizations/#4-heatmap-of-sensor-row-count
HEATMAP_SENSOR_ROW_COUNT_PER_TIME_SEGMENT:
PLOT: True
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]
# Features ------
# See https://www.rapids.science/latest/visualizations/feature-visualizations/#1-heatmap-correlation-matrix
HEATMAP_FEATURE_CORRELATION_MATRIX:
PLOT: True
MIN_ROWS_RATIO: 0.5
CORR_THRESHOLD: 0.1
CORR_METHOD: "pearson" # choose from {"pearson", "kendall", "spearman"}
########################################################################################################################
# Analysis Workflow Example #
########################################################################################################################
PARAMS_FOR_ANALYSIS:
CATEGORICAL_OPERATORS: [mostcommon]
DEMOGRAPHIC:
FOLDER: data/external/example_workflow
CONTAINER: participant_info.csv
FEATURES: [age, gender, inpatientdays]
CATEGORICAL_FEATURES: [gender]
TARGET:
FOLDER: data/external/example_workflow
CONTAINER: participant_target.csv
# Cleaning Parameters
COLS_NAN_THRESHOLD: 0.3
COLS_VAR_THRESHOLD: True
ROWS_NAN_THRESHOLD: 0.3
DATA_YIELDED_HOURS_RATIO_THRESHOLD: 0.75
MODEL_NAMES: [LogReg, kNN , SVM, DT, RF, GB, XGBoost, LightGBM]
CV_METHODS: [LeaveOneOut]
RESULT_COMPONENTS: [fold_predictions, fold_metrics, overall_results, fold_feature_importances]
MODEL_SCALER:
LogReg: [notnormalized, minmaxscaler, standardscaler, robustscaler]
kNN: [minmaxscaler, standardscaler, robustscaler]
SVM: [minmaxscaler, standardscaler, robustscaler]
DT: [notnormalized]
RF: [notnormalized]
GB: [notnormalized]
XGBoost: [notnormalized]
LightGBM: [notnormalized]
MODEL_HYPERPARAMS:
LogReg:
{"clf__C": [0.01, 0.1, 1, 10, 100], "clf__solver": ["newton-cg", "lbfgs", "liblinear", "saga"], "clf__penalty": ["l2"]}
kNN:
{"clf__n_neighbors": [3, 5, 7], "clf__weights": ["uniform", "distance"], "clf__metric": ["euclidean", "manhattan", "minkowski"]}
SVM:
{"clf__C": [0.01, 0.1, 1, 10, 100], "clf__gamma": ["scale", "auto"], "clf__kernel": ["rbf", "poly", "sigmoid"]}
DT:
{"clf__criterion": ["gini", "entropy"], "clf__max_depth": [null, 3, 7, 15], "clf__max_features": [null, "auto", "sqrt", "log2"]}
RF:
{"clf__n_estimators": [10, 100, 200],"clf__max_depth": [null, 3, 7, 15]}
GB:
{"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]}
XGBoost:
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [10, 100, 200], "clf__max_depth": [3, 5, 7]}
LightGBM:
{"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]}