rapids/config.yaml

437 lines
21 KiB
YAML

# See https://www.rapids.science/latest/setup/configuration/#database-credentials
DATABASE_GROUP: &database_group
MY_GROUP
# See https://www.rapids.science/latest/setup/configuration/#timezone-of-your-study
TIMEZONE: &timezone
America/New_York
# See https://www.rapids.science/latest/setup/configuration/#participant-files
PIDS: [test01]
# See https://www.rapids.science/latest/setup/configuration/#automatic-creation-of-participant-files
CREATE_PARTICIPANT_FILES:
SOURCE:
TYPE: AWARE_DEVICE_TABLE #AWARE_DEVICE_TABLE or CSV_FILE
DATABASE_GROUP: *database_group
CSV_FILE_PATH: "data/external/example_participants.csv" # see docs for required format
TIMEZONE: *timezone
PHONE_SECTION:
ADD: TRUE
DEVICE_ID_COLUMN: device_id # column name
IGNORED_DEVICE_IDS: []
FITBIT_SECTION:
ADD: TRUE
DEVICE_ID_COLUMN: device_id # column name
IGNORED_DEVICE_IDS: []
# See https://www.rapids.science/latest/setup/configuration/#time-segments
TIME_SEGMENTS: &time_segments
TYPE: PERIODIC # FREQUENCY, PERIODIC, EVENT
FILE: "data/external/timesegments_periodic.csv"
INCLUDE_PAST_PERIODIC_SEGMENTS: FALSE # Only relevant if TYPE=PERIODIC, see docs
########################################################################################################################
# PHONE #
########################################################################################################################
# See https://www.rapids.science/latest/setup/configuration/#device-data-source-configuration
PHONE_DATA_CONFIGURATION:
SOURCE:
TYPE: DATABASE
DATABASE_GROUP: *database_group
DEVICE_ID_COLUMN: device_id # column name
TIMEZONE:
TYPE: SINGLE
VALUE: *timezone
# Sensors ------
# https://www.rapids.science/latest/features/phone-accelerometer/
PHONE_ACCELEROMETER:
TABLE: accelerometer
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
SRC_FOLDER: "rapids" # inside src/features/phone_accelerometer
SRC_LANGUAGE: "python"
PANDA:
COMPUTE: False
VALID_SENSED_MINUTES: False
FEATURES:
exertional_activity_episode: ["sumduration", "maxduration", "minduration", "avgduration", "medianduration", "stdduration"]
nonexertional_activity_episode: ["sumduration", "maxduration", "minduration", "avgduration", "medianduration", "stdduration"]
SRC_FOLDER: "panda" # inside src/features/phone_accelerometer
SRC_LANGUAGE: "python"
# See https://www.rapids.science/latest/features/phone-activity-recognition/
PHONE_ACTIVITY_RECOGNITION:
TABLE:
ANDROID: plugin_google_activity_recognition
IOS: plugin_ios_activity_recognition
EPISODE_THRESHOLD_BETWEEN_ROWS: 5 # minutes. Max time difference for two consecutive rows to be considered within the same battery episode.
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["count", "mostcommonactivity", "countuniqueactivities", "durationstationary", "durationmobile", "durationvehicle"]
ACTIVITY_CLASSES:
STATIONARY: ["still", "tilting"]
MOBILE: ["on_foot", "walking", "running", "on_bicycle"]
VEHICLE: ["in_vehicle"]
SRC_FOLDER: "rapids" # inside src/features/phone_activity_recognition
SRC_LANGUAGE: "python"
# See https://www.rapids.science/latest/features/phone-applications-crashes/
PHONE_APPLICATIONS_CRASHES:
TABLE: 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:
TABLE: applications_foreground
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: False
SINGLE_CATEGORIES: ["all", "email"]
MULTIPLE_CATEGORIES:
social: ["socialnetworks", "socialmediatools"]
entertainment: ["entertainment", "gamingknowledge", "gamingcasual", "gamingadventure", "gamingstrategy", "gamingtoolscommunity", "gamingroleplaying", "gamingaction", "gaminglogic", "gamingsports", "gamingsimulation"]
SINGLE_APPS: ["top1global", "com.facebook.moments", "com.google.android.youtube", "com.twitter.android"] # There's no entropy for single apps
EXCLUDED_CATEGORIES: []
EXCLUDED_APPS: ["com.fitbit.FitbitMobile", "com.aware.plugin.upmc.cancer"]
FEATURES: ["count", "timeoffirstuse", "timeoflastuse", "frequencyentropy"]
SRC_FOLDER: "rapids" # inside src/features/phone_applications_foreground
SRC_LANGUAGE: "python"
# See https://www.rapids.science/latest/features/phone-applications-notifications/
PHONE_APPLICATIONS_NOTIFICATIONS:
TABLE: 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-aware-log/
PHONE_AWARE_LOG:
TABLE: aware_log
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:
TABLE: 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: False
FEATURES: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
SRC_FOLDER: "rapids" # inside src/features/phone_battery
SRC_LANGUAGE: "python"
# See https://www.rapids.science/latest/features/phone-bluetooth/
PHONE_BLUETOOTH:
TABLE: bluetooth
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_bluetooth
SRC_LANGUAGE: "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_FOLDER: "doryab" # inside src/features/phone_bluetooth
SRC_LANGUAGE: "python"
# See https://www.rapids.science/latest/features/phone-calls/
PHONE_CALLS:
TABLE: calls
PROVIDERS:
RAPIDS:
COMPUTE: False
CALL_TYPES: [missed, incoming, outgoing]
FEATURES:
missed: [count, distinctcontacts, timefirstcall, timelastcall, countmostfrequentcontact]
incoming: [count, distinctcontacts, meanduration, sumduration, minduration, maxduration, stdduration, modeduration, entropyduration, timefirstcall, timelastcall, countmostfrequentcontact]
outgoing: [count, distinctcontacts, meanduration, sumduration, minduration, maxduration, stdduration, modeduration, entropyduration, timefirstcall, timelastcall, countmostfrequentcontact]
SRC_LANGUAGE: "r"
SRC_FOLDER: "rapids" # inside src/features/phone_calls
# See https://www.rapids.science/latest/features/phone-conversation/
PHONE_CONVERSATION:
TABLE:
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_FOLDER: "rapids" # inside src/features/phone_conversation
SRC_LANGUAGE: "python"
# See https://www.rapids.science/latest/features/phone-data-yield/
PHONE_DATA_YIELD:
SENSORS: []
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: [ratiovalidyieldedminutes, ratiovalidyieldedhours]
MINUTE_RATIO_THRESHOLD_FOR_VALID_YIELDED_HOURS: 0.5 # 0 to 1 representing the number of minutes with at least
SRC_LANGUAGE: "r"
SRC_FOLDER: "rapids" # inside src/features/phone_data_yield
# See https://www.rapids.science/latest/features/phone-keyboard/
PHONE_KEYBOARD:
TABLE: 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:
TABLE: light
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
SRC_FOLDER: "rapids" # inside src/features/phone_light
SRC_LANGUAGE: "python"
# See https://www.rapids.science/latest/features/phone-locations/
PHONE_LOCATIONS:
TABLE: 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
PROVIDERS:
DORYAB:
COMPUTE: False
FEATURES: ["locationvariance","loglocationvariance","totaldistance","averagespeed","varspeed", "numberofsignificantplaces","numberlocationtransitions","radiusgyration","timeattop1location","timeattop2location","timeattop3location","movingtostaticratio","outlierstimepercent","maxlengthstayatclusters","minlengthstayatclusters","meanlengthstayatclusters","stdlengthstayatclusters","locationentropy","normalizedlocationentropy"]
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
SRC_FOLDER: "doryab" # inside src/features/phone_locations
SRC_LANGUAGE: "python"
BARNETT:
COMPUTE: False
FEATURES: ["hometime","disttravelled","rog","maxdiam","maxhomedist","siglocsvisited","avgflightlen","stdflightlen","avgflightdur","stdflightdur","probpause","siglocentropy","circdnrtn","wkenddayrtn"]
ACCURACY_LIMIT: 51 # meters, drops location coordinates with an accuracy higher than this. This number means there's a 68% probability the true location is within this radius
TIMEZONE: *timezone
MINUTES_DATA_USED: False # Use this for quality control purposes, how many minutes of data (location coordinates gruped by minute) were used to compute features
SRC_FOLDER: "barnett" # inside src/features/phone_locations
SRC_LANGUAGE: "r"
# See https://www.rapids.science/latest/features/phone-messages/
PHONE_MESSAGES:
TABLE: messages
PROVIDERS:
RAPIDS:
COMPUTE: False
MESSAGES_TYPES : [received, sent]
FEATURES:
received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
sent: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
SRC_LANGUAGE: "r"
SRC_FOLDER: "rapids" # inside src/features/phone_messages
# See https://www.rapids.science/latest/features/phone-screen/
PHONE_SCREEN:
TABLE: screen
PROVIDERS:
RAPIDS:
COMPUTE: False
REFERENCE_HOUR_FIRST_USE: 0
IGNORE_EPISODES_SHORTER_THAN: 0 # in minutes, set to 0 to disable
IGNORE_EPISODES_LONGER_THAN: 0 # in minutes, set to 0 to disable
FEATURES: ["countepisode", "sumduration", "maxduration", "minduration", "avgduration", "stdduration", "firstuseafter"] # "episodepersensedminutes" needs to be added later
EPISODE_TYPES: ["unlock"]
SRC_FOLDER: "rapids" # inside src/features/phone_screen
SRC_LANGUAGE: "python"
# See https://www.rapids.science/latest/features/phone-wifi-connected/
PHONE_WIFI_CONNECTED:
TABLE: "sensor_wifi"
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_wifi_connected
SRC_LANGUAGE: "r"
# See https://www.rapids.science/latest/features/phone-wifi-visible/
PHONE_WIFI_VISIBLE:
TABLE: "wifi"
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_wifi_visible
SRC_LANGUAGE: "r"
########################################################################################################################
# FITBIT #
########################################################################################################################
# See https://www.rapids.science/latest/setup/configuration/#device-data-source-configuration
FITBIT_DATA_CONFIGURATION:
SOURCE:
TYPE: DATABASE # DATABASE or FILES (set each [FITBIT_SENSOR][TABLE] attribute with a table name or a file path accordingly)
COLUMN_FORMAT: JSON # JSON or PLAIN_TEXT
DATABASE_GROUP: *database_group
DEVICE_ID_COLUMN: device_id # column name
TIMEZONE:
TYPE: SINGLE # Fitbit devices don't support time zones so we read this data in the timezone indicated by VALUE
VALUE: *timezone
# 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 representing the number of minutes with at least
SRC_LANGUAGE: "r"
SRC_FOLDER: "rapids" # inside src/features/fitbit_data_yield
# See https://www.rapids.science/latest/features/fitbit-heartrate-summary/
FITBIT_HEARTRATE_SUMMARY:
TABLE: 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_FOLDER: "rapids" # inside src/features/fitbit_heartrate_summary
SRC_LANGUAGE: "python"
# See https://www.rapids.science/latest/features/fitbit-heartrate-intraday/
FITBIT_HEARTRATE_INTRADAY:
TABLE: heartrate_intraday
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "minutesonoutofrangezone", "minutesonfatburnzone", "minutesoncardiozone", "minutesonpeakzone"]
SRC_FOLDER: "rapids" # inside src/features/fitbit_heartrate_intraday
SRC_LANGUAGE: "python"
# See https://www.rapids.science/latest/features/fitbit-sleep-summary/
FITBIT_SLEEP_SUMMARY:
TABLE: sleep_summary
SLEEP_EPISODE_TIMESTAMP: end # summary sleep episodes are considered as events based on either the start timestamp or end timestamp.
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countepisode", "avgefficiency", "sumdurationafterwakeup", "sumdurationasleep", "sumdurationawake", "sumdurationtofallasleep", "sumdurationinbed", "avgdurationafterwakeup", "avgdurationasleep", "avgdurationawake", "avgdurationtofallasleep", "avgdurationinbed"]
SLEEP_TYPES: ["main", "nap", "all"]
SRC_FOLDER: "rapids" # inside src/features/fitbit_sleep_summary
SRC_LANGUAGE: "python"
# See https://www.rapids.science/latest/features/fitbit-steps-summary/
FITBIT_STEPS_SUMMARY:
TABLE: steps_summary
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["maxsumsteps", "minsumsteps", "avgsumsteps", "mediansumsteps", "stdsumsteps"]
SRC_FOLDER: "rapids" # inside src/features/fitbit_steps_summary
SRC_LANGUAGE: "python"
# See https://www.rapids.science/latest/features/fitbit-steps-intraday/
FITBIT_STEPS_INTRADAY:
TABLE: steps_intraday
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES:
STEPS: ["sum", "max", "min", "avg", "std"]
SEDENTARY_BOUT: ["countepisode", "sumduration", "maxduration", "minduration", "avgduration", "stdduration"]
ACTIVE_BOUT: ["countepisode", "sumduration", "maxduration", "minduration", "avgduration", "stdduration"]
THRESHOLD_ACTIVE_BOUT: 10 # steps
INCLUDE_ZERO_STEP_ROWS: False
SRC_FOLDER: "rapids" # inside src/features/fitbit_steps_intraday
SRC_LANGUAGE: "python"
# FITBIT_CALORIES:
# TABLE_FORMAT: JSON # JSON or CSV. If your JSON or CSV data are files change [DEVICE_DATA][FITBIT][SOURCE][TYPE] to FILES
# TABLE:
# JSON: fitbit_calories
# CSV:
# SUMMARY: calories_summary
# INTRADAY: calories_intraday
# PROVIDERS:
# RAPIDS:
# COMPUTE: False
# FEATURES: []
########################################################################################################################
# PLOTS #
########################################################################################################################
# Data quality
HISTOGRAM_PHONE_DATA_YIELD:
PLOT: False
HEATMAP_PHONE_DATA_YIELD_PER_PARTICIPANT_PER_TIME_SEGMENT:
PLOT: False
HEATMAP_SENSORS_PER_MINUTE_PER_TIME_SEGMENT:
PLOT: False
HEATMAP_SENSOR_ROW_COUNT_PER_TIME_SEGMENT:
PLOT: False
SENSORS: [PHONE_ACCELEROMETER, 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
HEATMAP_FEATURE_CORRELATION_MATRIX:
PLOT: False
MIN_ROWS_RATIO: 0.5
CORR_THRESHOLD: 0.1
CORR_METHOD: "pearson" # choose from {"pearson", "kendall", "spearman"}