rapids/config.yaml

124 lines
6.2 KiB
YAML

# Valid database table names
SENSORS: [applications_crashes, applications_foreground, applications_notifications, battery, bluetooth, calls, locations, messages, plugin_ambient_noise, plugin_device_usage, plugin_google_activity_recognition, screen]
FITBIT_TABLE: [fitbit_data]
FITBIT_SENSORS: [heartrate, steps, sleep]
# Participants to include in the analysis
# You must create a file for each participant
# named pXXX containing their device_id
PIDS: [p01, p02]
# Global var with common day segments
DAY_SEGMENTS: &day_segments
[daily, morning, afternoon, evening, night]
# Global timezone
# Use codes from https://en.wikipedia.org/wiki/List_of_tz_database_time_zones
# Double check your code, for example EST is not US Eastern Time.
TIMEZONE: &timezone
America/New_York
DATABASE_GROUP: &database_group
AAPECS
DOWNLOAD_PARTICIPANTS:
IGNORED_DEVICE_IDS: [] # for example "5a1dd68c-6cd1-48fe-ae1e-14344ac5215f"
GROUP: *database_group
# Download data config
DOWNLOAD_DATASET:
GROUP: *database_group
# Readable datetime config
READABLE_DATETIME:
FIXED_TIMEZONE: *timezone
# Communication SMS features config, TYPES and METRICS keys need to match
SMS:
TYPES : [received, sent]
METRICS:
received: [count, distinctcontacts, timefirstsms, timelastsms, countmostfrequentcontact]
sent: [count, distinctcontacts, timefirstsms, timelastsms, countmostfrequentcontact]
DAY_SEGMENTS: *day_segments
# Communication call features config, TYPES and METRICS keys need to match
CALLS:
TYPES: [missed, incoming, outgoing]
METRICS:
missed: [count, distinctcontacts, timefirstcall, timelastcall, countmostfrequentcontact]
incoming: [count, distinctcontacts, meanduration, sumduration, minduration, maxduration, stdduration, modeduration, hubermduration, varqnduration, entropyduration, timefirstcall, timelastcall, countmostfrequentcontact]
outgoing: [count, distinctcontacts, meanduration, sumduration, minduration, maxduration, stdduration, modeduration, hubermduration, varqnduration, entropyduration, timefirstcall, timelastcall, countmostfrequentcontact]
DAY_SEGMENTS: *day_segments
APPLICATION_GENRES:
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_GENRES: 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
PHONE_VALID_SENSED_DAYS:
BIN_SIZE: 5 # (in minutes)
MIN_VALID_HOURS: 20 # (out of 24)
MIN_BINS_PER_HOUR: 8 # (out of 60min/BIN_SIZE bins)
RESAMPLE_FUSED_LOCATION:
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
TIME_SINCE_VALID_LOCATION: 12 # hours, only replicate location samples to consecutive sensed bins if they were logged within this threshold after a valid location row
TIMEZONE: *timezone
BARNETT_LOCATION:
METRICS: ["hometime","disttravelled","rog","maxdiam","maxhomedist","siglocsvisited","avgflightlen","stdflightlen","avgflightdur","stdflightdur","probpause","siglocentropy","minsmissing","circdnrtn","wkenddayrtn"]
LOCATIONS_TO_USE: ALL # ALL, ALL_EXCEPT_FUSED OR RESAMPLE_FUSED
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
BLUETOOTH:
DAY_SEGMENTS: *day_segments
METRICS: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
GOOGLE_ACTIVITY_RECOGNITION:
DAY_SEGMENTS: *day_segments
METRICS: ['count','mostcommonactivity','countuniqueactivities','activitychangecount','sumstationary','summobile','sumvehicle']
BATTERY:
DAY_SEGMENTS: *day_segments
METRICS: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
SCREEN:
DAY_SEGMENTS: *day_segments
METRICS_EVENTS: ["counton", "countunlock", "unlocksperminute"]
METRICS_DELTAS: ["sumduration", "maxduration", "minduration", "avgduration", "stdduration"]
EPISODES: ["unlock"]
LIGHT:
DAY_SEGMENTS: *day_segments
METRICS: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
ACCELEROMETER:
DAY_SEGMENTS: *day_segments
METRICS: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude", "ratioexertionalactivityepisodes", "sumexertionalactivityepisodes", "longestexertionalactivityepisode", "longestnonexertionalactivityepisode", "countexertionalactivityepisodes", "countnonexertionalactivityepisodes"]
APPLICATIONS_FOREGROUND:
DAY_SEGMENTS: *day_segments
SINGLE_CATEGORIES: ["all", "video"]
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", "video"]
EXCLUDED_APPS: ["com.fitbit.FitbitMobile", "com.aware.plugin.upmc.cancer"]
METRICS: ["count", "timeoffirstuse", "timeoflastuse", "frequencyentropy"]
HEARTRATE:
DAY_SEGMENTS: *day_segments
METRICS: ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "lengthoutofrange", "lengthfatburn", "lengthcardio", "lengthpeak"]
STEP:
DAY_SEGMENTS: *day_segments
METRICS:
ALL_STEPS: ["sumallsteps", "maxallsteps", "minallsteps", "avgallsteps", "stdallsteps"]
SEDENTARY_BOUT: ["countsedentarybout", "maxdurationsedentarybout", "mindurationsedentarybout", "avgdurationsedentarybout", "stddurationsedentarybout"]
ACTIVE_BOUT: ["countactivebout", "maxdurationactivebout", "mindurationactivebout", "avgdurationactivebout", "stddurationactivebout"]
THRESHOLD_ACTIVE_BOUT: 10 # steps