rapids/config.yaml

153 lines
7.6 KiB
YAML
Raw Normal View History

2019-10-24 18:11:24 +02:00
# 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]
2019-10-24 18:11:24 +02:00
2020-01-15 23:18:10 +01:00
FITBIT_TABLE: [fitbit_data]
FITBIT_SENSORS: [heartrate, steps, sleep]
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
2019-10-24 22:27:43 +02:00
PIDS: [p01, p02]
# 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
# Communication SMS features config, TYPES and METRICS keys need to match
SMS:
TYPES : [received, sent]
METRICS:
2019-11-12 21:53:59 +01:00
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]
2019-11-12 21:40:48 +01:00
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]
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
2019-11-05 18:34:22 +01:00
PHONE_VALID_SENSED_DAYS:
BIN_SIZE: 5 # (in minutes)
MIN_VALID_HOURS: 20 # (out of 24)
2019-11-05 21:17:20 +01:00
MIN_BINS_PER_HOUR: 8 # (out of 60min/BIN_SIZE bins)
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: 12 # hours, only replicate location samples to consecutive sensed bins if they were logged within this threshold after a valid location row
TIMEZONE: *timezone
2019-11-05 21:17:20 +01:00
BARNETT_LOCATION:
DAY_SEGMENTS: [daily] # These metrics are only available on a daily basis
METRICS: ["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
2019-11-06 18:19:30 +01:00
TIMEZONE: *timezone
BLUETOOTH:
DAY_SEGMENTS: *day_segments
2019-11-18 20:22:08 +01:00
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"]
2019-11-27 20:25:17 +01:00
SCREEN:
DAY_SEGMENTS: *day_segments
REFERENCE_HOUR_FIRST_USE: 0
METRICS_DELTAS: ["countepisode", "episodepersensedminutes", "sumduration", "maxduration", "minduration", "avgduration", "stdduration", "firstuseafter"]
EPISODE_TYPES: ["unlock"]
2020-01-14 15:51:39 +01:00
LIGHT:
DAY_SEGMENTS: *day_segments
METRICS: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
2020-01-15 20:15:24 +01:00
ACCELEROMETER:
DAY_SEGMENTS: *day_segments
FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude", "ratioexertionalactivityepisodes", "sumexertionalactivityepisodes", "longestexertionalactivityepisode", "longestnonexertionalactivityepisode", "countexertionalactivityepisodes", "countnonexertionalactivityepisodes"]
2020-01-29 22:22:53 +01:00
2020-02-07 17:52:55 +01:00
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"]
2020-02-07 17:35:15 +01:00
HEARTRATE:
DAY_SEGMENTS: *day_segments
METRICS: ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "lengthoutofrange", "lengthfatburn", "lengthcardio", "lengthpeak"]
2020-01-29 22:22:53 +01:00
STEP:
DAY_SEGMENTS: *day_segments
METRICS:
ALL_STEPS: ["sumallsteps", "maxallsteps", "minallsteps", "avgallsteps", "stdallsteps"]
SEDENTARY_BOUT: ["countsedentarybout", "maxdurationsedentarybout", "mindurationsedentarybout", "avgdurationsedentarybout", "stddurationsedentarybout", "sumdurationsedentarybout"]
2020-01-29 22:22:53 +01:00
ACTIVE_BOUT: ["countactivebout", "maxdurationactivebout", "mindurationactivebout", "avgdurationactivebout", "stddurationactivebout"]
THRESHOLD_ACTIVE_BOUT: 10 # steps
INCLUDE_ZERO_STEP_ROWS: True
METRICS_FOR_ANALYSIS:
GROUNDTRUTH_TABLE: participant_info
SOURCES: &sources ["phone_metrics", "fitbit_metrics", "phone_fitbit_metrics"]
DAY_SEGMENTS: *day_segments
PHONE_METRICS: [accelerometer, applications_foreground, battery, call_incoming, call_missed, call_outgoing, google_activity_recognition, light, location_barnett, screen, sms_received, sms_sent]
FITBIT_METRICS: [fitbit_heartrate, fitbit_step]
PHONE_FITBIT_METRICS: "" # This array is merged in the input_merge_features_of_single_participant function in models.snakefile
# 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