rapids/config.yaml

245 lines
12 KiB
YAML
Raw Normal View History

2019-10-24 18:11:24 +02:00
# Participants to include in the analysis
# You must create a file for each participant named pXXX containing their device_id. This can be done manually or automatically
PIDS: [test01]
2019-10-24 22:27:43 +02:00
# Global var with common day segments
DAY_SEGMENTS: &day_segments
[daily, morning, afternoon, evening, night]
2019-11-05 21:17:20 +01:00
# Global timezone
2019-11-06 23:12:06 +01:00
# 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.
2019-11-05 21:17:20 +01:00
TIMEZONE: &timezone
2019-11-06 23:12:06 +01:00
America/New_York
2019-11-05 21:17:20 +01:00
DATABASE_GROUP: &database_group
2020-03-09 17:55:43 +01:00
MY_GROUP
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:
2019-11-05 21:17:20 +01:00
FIXED_TIMEZONE: *timezone
2020-07-09 19:01:50 +02:00
PHONE_VALID_SENSED_BINS:
COMPUTE: False # This flag is automatically ignored (set to True) if you are extracting PHONE_VALID_SENSED_DAYS or screen or Barnett's location features
2020-07-22 22:47:32 +02:00
BIN_SIZE: &bin_size 5 # (in minutes)
2020-07-09 19:01:50 +02:00
# Add as many sensor tables as you have, they all improve the computation of PHONE_VALID_SENSED_BINS and PHONE_VALID_SENSED_DAYS.
2020-07-20 16:32:04 +02:00
# If you are extracting screen or Barnett's location features, screen and locations tables are mandatory.
DB_TABLES: []
2020-07-09 19:01:50 +02:00
PHONE_VALID_SENSED_DAYS:
COMPUTE: False
2020-07-22 22:47:32 +02:00
MIN_VALID_HOURS_PER_DAY: &min_valid_hours_per_day [16] # (out of 24) MIN_HOURS_PER_DAY
MIN_VALID_BINS_PER_HOUR: &min_valid_bins_per_hour [6] # (out of 60min/BIN_SIZE bins)
2020-07-09 19:01:50 +02:00
# Communication SMS features config, TYPES and FEATURES keys need to match
MESSAGES:
COMPUTE: False
DB_TABLE: messages
TYPES : [received, sent]
FEATURES:
2020-06-26 18:20:47 +02:00
received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
sent: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
DAY_SEGMENTS: *day_segments
# Communication call features config, TYPES and FEATURES keys need to match
CALLS:
COMPUTE: False
DB_TABLE: calls
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]
2019-10-25 16:21:09 +02:00
DAY_SEGMENTS: *day_segments
2019-11-05 18:34:22 +01:00
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
2019-12-10 00:23:00 +01:00
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: 720 # minutes, only replicate location samples to consecutive sensed bins if they were logged within this threshold after a valid location row
2019-12-10 00:23:00 +01:00
TIMEZONE: *timezone
2019-11-05 21:17:20 +01:00
BARNETT_LOCATION:
COMPUTE: False
DB_TABLE: locations
DAY_SEGMENTS: [daily] # These features are only available on a daily basis
FEATURES: ["hometime","disttravelled","rog","maxdiam","maxhomedist","siglocsvisited","avgflightlen","stdflightlen","avgflightdur","stdflightdur","probpause","siglocentropy","circdnrtn","wkenddayrtn"]
2020-06-29 19:50:33 +02:00
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
2019-11-06 18:19:30 +01:00
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
2019-11-06 18:19:30 +01:00
DORYAB_LOCATION:
COMPUTE: False
DB_TABLE: locations
DAY_SEGMENTS: *day_segments
FEATURES: ["locationvariance","loglocationvariance","totaldistance","averagespeed","varspeed","circadianmovement","numberofsignificantplaces","numberlocationtransitions","radiusgyration","timeattop1location","timeattop2location","timeattop3location","movingtostaticratio","outlierstimepercent","maxlengthstayatclusters","minlengthstayatclusters","meanlengthstayatclusters","stdlengthstayatclusters","locationentropy","normalizedlocationentropy"]
LOCATIONS_TO_USE: ALL # ALL, ALL_EXCEPT_FUSED OR RESAMPLE_FUSED
DBSCAN_EPS: 10 # meters
DBSCAN_MINSAMPLES: 5
THRESHOLD_STATIC : 1 # km/h
2020-07-22 00:56:43 +02:00
MAXIMUM_GAP_ALLOWED: 300
2020-07-23 20:38:59 +02:00
MINUTES_DATA_USED: False
SAMPLING_FREQUENCY: 0
2019-11-06 18:19:30 +01:00
BLUETOOTH:
COMPUTE: False
DB_TABLE: bluetooth
2019-11-06 18:19:30 +01:00
DAY_SEGMENTS: *day_segments
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
2019-11-18 20:22:08 +01:00
ACTIVITY_RECOGNITION:
COMPUTE: False
DB_TABLE:
ANDROID: plugin_google_activity_recognition
IOS: plugin_ios_activity_recognition
2019-11-18 20:22:08 +01:00
DAY_SEGMENTS: *day_segments
2020-06-05 01:32:28 +02:00
FEATURES: ["count","mostcommonactivity","countuniqueactivities","activitychangecount","sumstationary","summobile","sumvehicle"]
BATTERY:
COMPUTE: False
DB_TABLE: battery
DAY_SEGMENTS: *day_segments
FEATURES: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
2019-11-27 20:25:17 +01:00
SCREEN:
COMPUTE: False
DB_TABLE: screen
2019-11-27 20:25:17 +01:00
DAY_SEGMENTS: *day_segments
REFERENCE_HOUR_FIRST_USE: 0
2020-07-23 20:38:59 +02:00
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_DELTAS: ["countepisode", "episodepersensedminutes", "sumduration", "maxduration", "minduration", "avgduration", "stdduration", "firstuseafter"]
EPISODE_TYPES: ["unlock"]
2020-01-14 15:51:39 +01:00
LIGHT:
COMPUTE: False
DB_TABLE: light
2020-01-14 15:51:39 +01:00
DAY_SEGMENTS: *day_segments
FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
2020-01-15 20:15:24 +01:00
ACCELEROMETER:
COMPUTE: False
DB_TABLE: accelerometer
2020-01-15 20:15:24 +01:00
DAY_SEGMENTS: *day_segments
FEATURES:
MAGNITUDE: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
2020-06-22 19:47:25 +02:00
EXERTIONAL_ACTIVITY_EPISODE: ["sumduration", "maxduration", "minduration", "avgduration", "medianduration", "stdduration"]
NONEXERTIONAL_ACTIVITY_EPISODE: ["sumduration", "maxduration", "minduration", "avgduration", "medianduration", "stdduration"]
VALID_SENSED_MINUTES: False
2020-01-29 22:22:53 +01:00
2020-02-07 17:52:55 +01:00
APPLICATIONS_FOREGROUND:
COMPUTE: False
DB_TABLE: applications_foreground
2020-02-07 17:52:55 +01:00
DAY_SEGMENTS: *day_segments
SINGLE_CATEGORIES: ["all", "email"]
2020-02-07 17:52:55 +01:00
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"]
2020-02-07 17:52:55 +01:00
EXCLUDED_APPS: ["com.fitbit.FitbitMobile", "com.aware.plugin.upmc.cancer"]
FEATURES: ["count", "timeoffirstuse", "timeoflastuse", "frequencyentropy"]
2020-02-07 17:52:55 +01:00
2020-02-07 17:35:15 +01:00
HEARTRATE:
COMPUTE: False
DB_TABLE: fitbit_data
2020-02-07 17:35:15 +01:00
DAY_SEGMENTS: *day_segments
SUMMARY_FEATURES: ["restinghr"] # calories features' accuracy depend on the accuracy of the participants fitbit profile (e.g. heigh, weight) use with care: ["caloriesoutofrange", "caloriesfatburn", "caloriescardio", "caloriespeak"]
2020-06-22 20:15:56 +02:00
INTRADAY_FEATURES: ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "minutesonoutofrangezone", "minutesonfatburnzone", "minutesoncardiozone", "minutesonpeakzone"]
2020-02-07 17:35:15 +01:00
2020-01-29 22:22:53 +01:00
STEP:
COMPUTE: False
DB_TABLE: fitbit_data
2020-01-29 22:22:53 +01:00
DAY_SEGMENTS: *day_segments
EXCLUDE_SLEEP:
2020-06-24 19:40:15 +02:00
EXCLUDE: False
TYPE: FIXED # FIXED OR FITBIT_BASED (CONFIGURE FITBIT's SLEEP DB_TABLE)
FIXED:
START: "23:00"
END: "07:00"
FEATURES:
2020-01-29 22:22:53 +01:00
ALL_STEPS: ["sumallsteps", "maxallsteps", "minallsteps", "avgallsteps", "stdallsteps"]
2020-06-26 23:33:30 +02:00
SEDENTARY_BOUT: ["countepisode", "sumduration", "maxduration", "minduration", "avgduration", "stdduration"]
ACTIVE_BOUT: ["countepisode", "sumduration", "maxduration", "minduration", "avgduration", "stdduration"]
THRESHOLD_ACTIVE_BOUT: 10 # steps
2020-06-26 23:33:30 +02:00
INCLUDE_ZERO_STEP_ROWS: False
SLEEP:
COMPUTE: False
DB_TABLE: fitbit_data
DAY_SEGMENTS: *day_segments
SLEEP_TYPES: ["main", "nap", "all"]
2020-06-13 00:44:05 +02:00
SUMMARY_FEATURES: ["sumdurationafterwakeup", "sumdurationasleep", "sumdurationawake", "sumdurationtofallasleep", "sumdurationinbed", "avgefficiency", "countepisode"]
2020-04-13 19:24:52 +02:00
WIFI:
COMPUTE: False
2020-07-24 22:35:41 +02:00
DB_TABLE:
VISIBLE_ACCESS_POINTS: "wifi" # if you only have a CONNECTED_ACCESS_POINTS table, set this value to ""
CONNECTED_ACCESS_POINTS: "sensor_wifi" # if you only have a VISIBLE_ACCESS_POINTS table, set this value to ""
2020-04-13 19:24:52 +02:00
DAY_SEGMENTS: *day_segments
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
CONVERSATION:
COMPUTE: False
DB_TABLE:
ANDROID: plugin_studentlife_audio_android
IOS: plugin_studentlife_audio
DAY_SEGMENTS: *day_segments
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",
2020-06-24 23:03:14 +02:00
"unknownexpectedfraction","countconversation"]
RECORDINGMINUTES: 1
PAUSEDMINUTES : 3
2020-07-22 22:47:32 +02:00
### Visualizations ################################################################
HEATMAP_FEATURES_CORRELATIONS:
PLOT: False
MIN_ROWS_RATIO: 0.5
MIN_VALID_HOURS_PER_DAY: *min_valid_hours_per_day
MIN_VALID_BINS_PER_HOUR: *min_valid_bins_per_hour
2020-07-22 22:47:32 +02:00
PHONE_FEATURES: [accelerometer, activity_recognition, applications_foreground, battery, calls_incoming, calls_missed, calls_outgoing, conversation, light, location_doryab, messages_received, messages_sent, screen]
FITBIT_FEATURES: [fitbit_heartrate, fitbit_step, fitbit_sleep]
CORR_THRESHOLD: 0.1
CORR_METHOD: "pearson" # choose from {"pearson", "kendall", "spearman"}
2020-07-22 22:47:32 +02:00
HISTOGRAM_VALID_SENSED_HOURS:
PLOT: False
MIN_VALID_HOURS_PER_DAY: *min_valid_hours_per_day
MIN_VALID_BINS_PER_HOUR: *min_valid_bins_per_hour
2020-07-22 22:47:32 +02:00
HEATMAP_DAYS_BY_SENSORS:
PLOT: False
MIN_VALID_HOURS_PER_DAY: *min_valid_hours_per_day
MIN_VALID_BINS_PER_HOUR: *min_valid_bins_per_hour
2020-07-22 22:47:32 +02:00
EXPECTED_NUM_OF_DAYS: -1
DB_TABLES: [accelerometer, applications_foreground, battery, bluetooth, calls, light, locations, messages, screen, wifi, sensor_wifi, plugin_google_activity_recognition, plugin_ios_activity_recognition, plugin_studentlife_audio_android, plugin_studentlife_audio]
2020-07-22 22:47:32 +02:00
HEATMAP_SENSED_BINS:
PLOT: False
BIN_SIZE: *bin_size
OVERALL_COMPLIANCE_HEATMAP:
PLOT: False
ONLY_SHOW_VALID_DAYS: False
EXPECTED_NUM_OF_DAYS: -1
2020-07-22 22:47:32 +02:00
BIN_SIZE: *bin_size
MIN_VALID_HOURS_PER_DAY: *min_valid_hours_per_day
MIN_VALID_BINS_PER_HOUR: *min_valid_bins_per_hour
2020-07-22 22:47:32 +02:00