rapids/config.yaml

390 lines
18 KiB
YAML
Raw Normal View History

# See https://www.rapids.science/latest/setup/configuration/#database-credentials
2020-11-04 19:27:58 +01:00
DATABASE_GROUP: &database_group
MY_GROUP
2019-10-24 22:27:43 +02:00
# See https://www.rapids.science/latest/setup/configuration/#timezone-of-your-study
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
# 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
2020-11-04 19:27:58 +01:00
CSV_FILE_PATH: "data/external/example_participants.csv" # see docs for required format
TIMEZONE: *timezone
PHONE_SECTION:
2020-10-22 19:08:52 +02:00
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/#day-segments
DAY_SEGMENTS: &day_segments
2020-11-25 01:12:16 +01:00
TYPE: PERIODIC # FREQUENCY, PERIODIC, EVENT
FILE: "data/external/daysegments_periodic.csv"
2020-11-04 19:27:58 +01:00
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 # SINGLE or MULTIPLE
VALUE: *timezone # IF TYPE=SINGLE, see docs
# Sensors ------
# https://www.rapids.science/latest/features/phone-accelerometer/
PHONE_ACCELEROMETER:
TABLE: accelerometer
2020-11-25 01:12:16 +01:00
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"
2020-07-09 19:01:50 +02:00
# 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.
2020-08-31 19:34:15 +02:00
PROVIDERS:
RAPIDS:
2020-11-25 01:12:16 +01:00
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-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-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
2020-08-31 19:34:15 +02:00
SRC_LANGUAGE: "r"
# See https://www.rapids.science/latest/features/phone-calls/
2020-10-19 21:07:12 +02:00
PHONE_CALLS:
TABLE: calls
PROVIDERS:
RAPIDS:
2020-10-22 20:38:40 +02:00
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"
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "rapids" # inside src/features/phone_calls
2019-11-05 18:34:22 +01:00
# 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-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/
2020-10-19 21:07:12 +02:00
PHONE_LOCATIONS:
TABLE: locations
LOCATIONS_TO_USE: FUSED_RESAMPLED # ALL, GPS 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","circadianmovement","numberofsignificantplaces","numberlocationtransitions","radiusgyration","timeattop1location","timeattop2location","timeattop3location","movingtostaticratio","outlierstimepercent","maxlengthstayatclusters","minlengthstayatclusters","meanlengthstayatclusters","stdlengthstayatclusters","locationentropy","normalizedlocationentropy"]
DBSCAN_EPS: 10 # meters
DBSCAN_MINSAMPLES: 5
THRESHOLD_STATIC : 1 # km/h
MAXIMUM_GAP_ALLOWED: 300
MINUTES_DATA_USED: False
SAMPLING_FREQUENCY: 0
2020-10-19 21:07:12 +02:00
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
2020-10-19 21:07:12 +02:00
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/
2020-10-19 21:07:12 +02:00
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"]
2020-10-19 21:07:12 +02:00
SRC_FOLDER: "rapids" # inside src/features/phone_screen
SRC_LANGUAGE: "python"
2020-01-14 15:51:39 +01:00
# See https://www.rapids.science/latest/features/phone-wifi-connected/
PHONE_WIFI_CONNECTED:
TABLE: "sensor_wifi"
PROVIDERS:
RAPIDS:
2020-09-03 20:36:42 +02:00
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_wifi_connected
SRC_LANGUAGE: "r"
2020-02-07 17:52:55 +01:00
# See https://www.rapids.science/latest/features/phone-wifi-visible/
2020-10-19 21:07:12 +02:00
PHONE_WIFI_VISIBLE:
TABLE: "wifi"
2020-10-19 21:07:12 +02:00
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-heartrate-summary/
FITBIT_HEARTRATE_SUMMARY:
TABLE: heartrate_summary
PROVIDERS:
RAPIDS:
2020-10-22 19:08:52 +02:00
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
2020-10-27 22:55:57 +01:00
SRC_LANGUAGE: "python"
2020-02-07 17:35:15 +01:00
# 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:
2020-10-22 19:08:52 +02:00
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
2020-10-30 23:57:04 +01:00
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: []
2020-10-22 19:08:52 +02:00
########################################################################################################################
# PLOTS #
########################################################################################################################
2020-10-22 19:08:52 +02:00
HISTOGRAM_PHONE_DATA_YIELD:
PLOT: False
2020-07-22 22:47:32 +02:00
HEATMAP_FEATURES_CORRELATIONS:
PLOT: False
MIN_ROWS_RATIO: 0.5
2020-11-25 01:12:16 +01:00
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
HEATMAP_DAYS_BY_SENSORS:
PLOT: False
2020-11-25 01:12:16 +01:00
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
2020-11-25 01:12:16 +01:00
BIN_SIZE: #*bin_size
2020-07-22 22:47:32 +02:00
OVERALL_COMPLIANCE_HEATMAP:
PLOT: False
ONLY_SHOW_VALID_DAYS: False
EXPECTED_NUM_OF_DAYS: -1
2020-11-25 01:12:16 +01:00
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