165 lines
8.0 KiB
YAML
165 lines
8.0 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, plugin_ios_activity_recognition, screen]
|
|
|
|
FITBIT_TABLE: [fitbit_data]
|
|
FITBIT_SENSORS: [heartrate, steps, sleep, calories]
|
|
|
|
# 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
|
|
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:
|
|
FIXED_TIMEZONE: *timezone
|
|
|
|
# Communication SMS features config, TYPES and FEATURES keys need to match
|
|
SMS:
|
|
TYPES : [received, sent]
|
|
FEATURES:
|
|
received: [count, distinctcontacts, timefirstsms, timelastsms, countmostfrequentcontact]
|
|
sent: [count, distinctcontacts, timefirstsms, timelastsms, countmostfrequentcontact]
|
|
DAY_SEGMENTS: *day_segments
|
|
|
|
# Communication call features config, TYPES and FEATURES keys need to match
|
|
CALLS:
|
|
TYPES: [missed, incoming, outgoing]
|
|
FEATURES:
|
|
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:
|
|
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"]
|
|
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
|
|
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
|
|
|
|
ACTIVITY_RECOGNITION:
|
|
DAY_SEGMENTS: *day_segments
|
|
FEATURES: ['count','mostcommonactivity','countuniqueactivities','activitychangecount','sumstationary','summobile','sumvehicle']
|
|
|
|
BATTERY:
|
|
DAY_SEGMENTS: *day_segments
|
|
FEATURES: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
|
|
|
|
SCREEN:
|
|
DAY_SEGMENTS: *day_segments
|
|
REFERENCE_HOUR_FIRST_USE: 0
|
|
FEATURES_DELTAS: ["countepisode", "episodepersensedminutes", "sumduration", "maxduration", "minduration", "avgduration", "stdduration", "firstuseafter"]
|
|
EPISODE_TYPES: ["unlock"]
|
|
|
|
LIGHT:
|
|
DAY_SEGMENTS: *day_segments
|
|
FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
|
|
|
|
ACCELEROMETER:
|
|
DAY_SEGMENTS: *day_segments
|
|
FEATURES: ["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"]
|
|
FEATURES: ["count", "timeoffirstuse", "timeoflastuse", "frequencyentropy"]
|
|
|
|
HEARTRATE:
|
|
DAY_SEGMENTS: *day_segments
|
|
FEATURES: ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "lengthoutofrange", "lengthfatburn", "lengthcardio", "lengthpeak"]
|
|
|
|
STEP:
|
|
DAY_SEGMENTS: *day_segments
|
|
FEATURES:
|
|
ALL_STEPS: ["sumallsteps", "maxallsteps", "minallsteps", "avgallsteps", "stdallsteps"]
|
|
SEDENTARY_BOUT: ["countsedentarybout", "maxdurationsedentarybout", "mindurationsedentarybout", "avgdurationsedentarybout", "stddurationsedentarybout", "sumdurationsedentarybout"]
|
|
ACTIVE_BOUT: ["countactivebout", "maxdurationactivebout", "mindurationactivebout", "avgdurationactivebout", "stddurationactivebout"]
|
|
THRESHOLD_ACTIVE_BOUT: 10 # steps
|
|
INCLUDE_ZERO_STEP_ROWS: True
|
|
|
|
WIFI:
|
|
DAY_SEGMENTS: *day_segments
|
|
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
|
|
|
|
PARAMS_FOR_ANALYSIS:
|
|
GROUNDTRUTH_TABLE: participant_info
|
|
SOURCES: &sources ["phone_features", "fitbit_features", "phone_fitbit_features"]
|
|
DAY_SEGMENTS: *day_segments
|
|
PHONE_FEATURES: [accelerometer, applications_foreground, battery, call_incoming, call_missed, call_outgoing, activity_recognition, light, location_barnett, screen, sms_received, sms_sent]
|
|
FITBIT_FEATURES: [fitbit_heartrate, fitbit_step]
|
|
PHONE_FITBIT_FEATURES: "" # This array is merged in the input_merge_features_of_single_participant function in models.snakefile
|
|
DEMOGRAPHIC_FEATURES: [age, gender, inpatientdays]
|
|
|
|
# Whether or not to include only days with enough valid sensed hours
|
|
# logic can be found in rule phone_valid_sensed_days of rules/preprocessing.snakefile
|
|
DROP_VALID_SENSED_DAYS:
|
|
ENABLED: True
|
|
|
|
# Whether or not to include certain days in the analysis, logic can be found in rule days_to_analyse of rules/mystudy.snakefile
|
|
# If you want to include all days downloaded for each participant, set ENABLED to False
|
|
DAYS_TO_ANALYSE:
|
|
ENABLED: True
|
|
DAYS_BEFORE_SURGERY: 15
|
|
DAYS_IN_HOSPITAL: F # T or F
|
|
DAYS_AFTER_DISCHARGE: 7
|
|
|
|
# Cleaning Parameters
|
|
COLS_NAN_THRESHOLD: 0.5
|
|
COLS_VAR_THRESHOLD: True
|
|
ROWS_NAN_THRESHOLD: 0.5
|
|
PARTICIPANTS_DAY_THRESHOLD: 7
|
|
|
|
SUMMARISED: ["summarised"] # "summarised" or "notsummarised"
|
|
|
|
# Target Settings:
|
|
# 1 => TARGETS_RATIO_THRESHOLD (ceiling) or more of available CESD scores were TARGETS_VALUE_THRESHOLD or higher; 0 => otherwise
|
|
TARGETS_RATIO_THRESHOLD: 0.5
|
|
TARGETS_VALUE_THRESHOLD: 16
|