rapids/example_profile/example_config.yaml

402 lines
19 KiB
YAML
Raw Normal View History

2020-11-25 22:34:05 +01:00
# See https://www.rapids.science/setup/configuration/#database-credentials
DATABASE_GROUP: &database_group
2020-12-07 16:56:37 +01:00
MY_GROUP
2020-08-03 23:30:15 +02:00
2020-11-25 22:34:05 +01:00
# See https://www.rapids.science/setup/configuration/#timezone-of-your-study
2020-08-03 23:30:15 +02:00
TIMEZONE: &timezone
America/New_York
2020-11-25 22:34:05 +01:00
# See https://www.rapids.science/setup/configuration/#participant-files
2020-12-05 00:45:16 +01:00
PIDS: [example01, example02]
2020-11-25 22:34:05 +01:00
# See https://www.rapids.science/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
CSV_FILE_PATH: "data/external/example_participants.csv" # see docs for required format
TIMEZONE: *timezone
PHONE_SECTION:
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: []
2020-12-03 00:41:03 +01:00
# See https://www.rapids.science/setup/configuration/#time-segments
TIME_SEGMENTS: &time_segments
2020-11-25 22:34:05 +01:00
TYPE: PERIODIC # FREQUENCY, PERIODIC, EVENT
2020-12-03 00:41:03 +01:00
FILE: "example_profile/exampleworkflow_timesegments.csv"
2020-11-25 22:34:05 +01:00
INCLUDE_PAST_PERIODIC_SEGMENTS: FALSE # Only relevant if TYPE=PERIODIC, see docs
########################################################################################################################
# PHONE #
########################################################################################################################
2020-11-25 22:34:05 +01:00
# See https://www.rapids.science/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 ------
PHONE_ACCELEROMETER:
TABLE: accelerometer
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"
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.
2020-11-25 22:34:05 +01:00
PROVIDERS:
RAPIDS:
COMPUTE: True
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"
2020-08-03 23:30:15 +02:00
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
2020-11-25 22:34:05 +01:00
PROVIDERS:
RAPIDS:
COMPUTE: True
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: ["system_apps"]
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"
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: True
FEATURES: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
SRC_FOLDER: "rapids" # inside src/features/phone_battery
SRC_LANGUAGE: "python"
PHONE_BLUETOOTH:
TABLE: bluetooth
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_bluetooth
2020-11-25 22:34:05 +01:00
SRC_LANGUAGE: "r"
2020-08-03 23:30:15 +02:00
2020-11-25 22:34:05 +01:00
PHONE_CALLS:
TABLE: calls
PROVIDERS:
RAPIDS:
COMPUTE: True
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"
SRC_FOLDER: "rapids" # inside src/features/phone_calls
PHONE_CONVERSATION:
TABLE:
ANDROID: plugin_studentlife_audio_android
IOS: plugin_studentlife_audio
PROVIDERS:
RAPIDS:
COMPUTE: True
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"
PHONE_DATA_YIELD:
SENSORS: [PHONE_ACCELEROMETER, PHONE_ACTIVITY_RECOGNITION, PHONE_APPLICATIONS_FOREGROUND, PHONE_BATTERY, PHONE_BLUETOOTH, PHONE_CALLS, PHONE_CONVERSATION, PHONE_LIGHT, PHONE_LOCATIONS, PHONE_MESSAGES, PHONE_SCREEN, PHONE_WIFI_CONNECTED, PHONE_WIFI_VISIBLE]
PROVIDERS:
RAPIDS:
COMPUTE: True
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
PHONE_LIGHT:
TABLE: light
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
SRC_FOLDER: "rapids" # inside src/features/phone_light
SRC_LANGUAGE: "python"
2020-11-25 22:34:05 +01:00
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: True
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
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
SRC_FOLDER: "barnett" # inside src/features/phone_locations
SRC_LANGUAGE: "r"
PHONE_MESSAGES:
TABLE: messages
2020-11-25 22:34:05 +01:00
PROVIDERS:
RAPIDS:
COMPUTE: True
MESSAGES_TYPES : [received, sent]
FEATURES:
received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
sent: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
2020-11-25 22:34:05 +01:00
SRC_LANGUAGE: "r"
SRC_FOLDER: "rapids" # inside src/features/phone_messages
2020-11-25 22:34:05 +01:00
PHONE_SCREEN:
TABLE: screen
PROVIDERS:
RAPIDS:
COMPUTE: True
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"]
SRC_FOLDER: "rapids" # inside src/features/phone_screen
SRC_LANGUAGE: "python"
PHONE_WIFI_CONNECTED:
TABLE: "sensor_wifi"
2020-11-25 22:34:05 +01:00
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_wifi_connected
SRC_LANGUAGE: "r"
2020-11-25 22:34:05 +01:00
PHONE_WIFI_VISIBLE:
TABLE: "wifi"
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_wifi_visible
SRC_LANGUAGE: "r"
########################################################################################################################
# FITBIT #
########################################################################################################################
2020-11-25 22:34:05 +01:00
# 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 only supports SINGLE timezones
VALUE: *timezone # see docs
HIDDEN:
SINGLE_FITBIT_TABLE: TRUE
2020-11-25 22:34:05 +01:00
FITBIT_HEARTRATE_SUMMARY:
TABLE: fitbit_data
PROVIDERS:
RAPIDS:
COMPUTE: True
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"
FITBIT_HEARTRATE_INTRADAY:
TABLE: fitbit_data
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "minutesonoutofrangezone", "minutesonfatburnzone", "minutesoncardiozone", "minutesonpeakzone"]
SRC_FOLDER: "rapids" # inside src/features/fitbit_heartrate_intraday
SRC_LANGUAGE: "python"
FITBIT_SLEEP_SUMMARY:
TABLE: fitbit_data
SLEEP_EPISODE_TIMESTAMP: end # summary sleep episodes are considered as events based on either the start timestamp or end timestamp.
PROVIDERS:
RAPIDS:
COMPUTE: True
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"
2020-11-25 22:34:05 +01:00
FITBIT_STEPS_SUMMARY:
TABLE: fitbit_data
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["maxsumsteps", "minsumsteps", "avgsumsteps", "mediansumsteps", "stdsumsteps"]
SRC_FOLDER: "rapids" # inside src/features/fitbit_steps_summary
SRC_LANGUAGE: "python"
FITBIT_STEPS_INTRADAY:
TABLE: fitbit_data
PROVIDERS:
RAPIDS:
COMPUTE: True
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
SRC_LANGUAGE: "python"
########################################################################################################################
# PLOTS #
########################################################################################################################
HISTOGRAM_PHONE_DATA_YIELD:
PLOT: True
2020-12-04 03:00:32 +01:00
HEATMAP_SENSORS_PER_MINUTE_PER_TIME_SEGMENT:
PLOT: True
HEATMAP_SENSOR_ROW_COUNT_PER_TIME_SEGMENT:
PLOT: True
2020-12-21 22:30:46 +01:00
SENSORS: [PHONE_ACTIVITY_RECOGNITION, PHONE_APPLICATIONS_FOREGROUND, PHONE_BATTERY, PHONE_BLUETOOTH, PHONE_CALLS, PHONE_CONVERSATION, PHONE_LIGHT, PHONE_LOCATIONS, PHONE_MESSAGES, PHONE_SCREEN, PHONE_WIFI_CONNECTED, PHONE_WIFI_VISIBLE]
2020-12-04 03:00:32 +01:00
HEATMAP_PHONE_DATA_YIELD_PER_PARTICIPANT_PER_TIME_SEGMENT:
PLOT: True
HEATMAP_FEATURE_CORRELATION_MATRIX:
PLOT: TRUE
MIN_ROWS_RATIO: 0.5
CORR_THRESHOLD: 0.1
CORR_METHOD: "pearson" # choose from {"pearson", "kendall", "spearman"}
########################################################################################################################
# Analysis Workflow Example #
########################################################################################################################
2020-11-25 22:34:05 +01:00
2020-08-03 23:30:15 +02:00
PARAMS_FOR_ANALYSIS:
2020-11-25 22:34:05 +01:00
CATEGORICAL_OPERATORS: [mostcommon]
DEMOGRAPHIC:
TABLE: participant_info
FEATURES: [age, gender, inpatientdays]
CATEGORICAL_FEATURES: [gender]
SOURCE:
DATABASE_GROUP: *database_group
TIMEZONE: *timezone
TARGET:
TABLE: participant_target
SOURCE:
DATABASE_GROUP: *database_group
TIMEZONE: *timezone
2020-08-03 23:30:15 +02:00
# Cleaning Parameters
2020-11-25 22:34:05 +01:00
COLS_NAN_THRESHOLD: 0.3
2020-08-03 23:30:15 +02:00
COLS_VAR_THRESHOLD: True
2020-11-25 22:34:05 +01:00
ROWS_NAN_THRESHOLD: 0.3
DATA_YIELDED_HOURS_RATIO_THRESHOLD: 0.75
MODEL_NAMES: [LogReg, kNN , SVM, DT, RF, GB, XGBoost, LightGBM]
CV_METHODS: [LeaveOneOut]
RESULT_COMPONENTS: [fold_predictions, fold_metrics, overall_results, fold_feature_importances]
2020-08-03 23:30:15 +02:00
MODEL_SCALER:
2020-11-25 22:34:05 +01:00
LogReg: [notnormalized, minmaxscaler, standardscaler, robustscaler]
kNN: [minmaxscaler, standardscaler, robustscaler]
SVM: [minmaxscaler, standardscaler, robustscaler]
DT: [notnormalized]
RF: [notnormalized]
GB: [notnormalized]
XGBoost: [notnormalized]
LightGBM: [notnormalized]
2020-08-03 23:30:15 +02:00
MODEL_HYPERPARAMS:
LogReg:
{"clf__C": [0.01, 0.1, 1, 10, 100], "clf__solver": ["newton-cg", "lbfgs", "liblinear", "saga"], "clf__penalty": ["l2"]}
kNN:
2020-11-25 22:34:05 +01:00
{"clf__n_neighbors": [3, 5, 7], "clf__weights": ["uniform", "distance"], "clf__metric": ["euclidean", "manhattan", "minkowski"]}
2020-08-03 23:30:15 +02:00
SVM:
{"clf__C": [0.01, 0.1, 1, 10, 100], "clf__gamma": ["scale", "auto"], "clf__kernel": ["rbf", "poly", "sigmoid"]}
DT:
2020-11-25 22:34:05 +01:00
{"clf__criterion": ["gini", "entropy"], "clf__max_depth": [null, 3, 7, 15], "clf__max_features": [null, "auto", "sqrt", "log2"]}
2020-08-03 23:30:15 +02:00
RF:
2020-11-25 22:34:05 +01:00
{"clf__n_estimators": [10, 100, 200],"clf__max_depth": [null, 3, 7, 15]}
2020-08-03 23:30:15 +02:00
GB:
2020-11-25 22:34:05 +01:00
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [10, 100, 200], "clf__subsample": [0.5, 0.7, 1.0], "clf__max_depth": [null, 3, 5, 7]}
2020-08-03 23:30:15 +02:00
XGBoost:
2020-11-25 22:34:05 +01:00
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [10, 100, 200], "clf__max_depth": [3, 5, 7]}
2020-08-03 23:30:15 +02:00
LightGBM:
2020-11-25 22:34:05 +01:00
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [10, 100, 200], "clf__num_leaves": [3, 5, 7], "clf__colsample_bytree": [0.6, 0.8, 1]}