Update Snakemake, testing_config.yaml, and messages' filenames in the tests directory

pull/103/head
abhineethreddyk 2020-10-19 17:13:10 -04:00
parent 24bf62a7ab
commit 87b23d7848
17 changed files with 605 additions and 129 deletions

View File

@ -13,18 +13,13 @@ if len(config["PIDS"]) == 0:
raise ValueError("Add participants IDs to PIDS in config.yaml. Remember to create their participant files in data/external")
if config["PHONE_VALID_SENSED_BINS"]["COMPUTE"] or config["PHONE_VALID_SENSED_DAYS"]["COMPUTE"]: # valid sensed bins is necessary for sensed days, so we add these files anyways if sensed days are requested
if len(config["PHONE_VALID_SENSED_BINS"]["DB_TABLES"]) == 0:
raise ValueError("If you want to compute PHONE_VALID_SENSED_BINS or PHONE_VALID_SENSED_DAYS, you need to add at least one table to [PHONE_VALID_SENSED_BINS][DB_TABLES] in config.yaml")
if len(config["PHONE_VALID_SENSED_BINS"]["PHONE_SENSORS"]) == 0:
raise ValueError("If you want to compute PHONE_VALID_SENSED_BINS or PHONE_VALID_SENSED_DAYS, you need to add at least one PHONE_SENSOR to [PHONE_VALID_SENSED_BINS][PHONE_SENSORS] in config.yaml")
pids_android = list(filter(lambda pid: infer_participant_platform("data/external/" + pid) == "android", config["PIDS"]))
pids_ios = list(filter(lambda pid: infer_participant_platform("data/external/" + pid) == "ios", config["PIDS"]))
tables_android = [table for table in config["PHONE_VALID_SENSED_BINS"]["DB_TABLES"] if table not in [config["CONVERSATION"]["DB_TABLE"]["IOS"], config["ACTIVITY_RECOGNITION"]["DB_TABLE"]["IOS"]]] # for android, discard any ios tables that may exist
tables_ios = [table for table in config["PHONE_VALID_SENSED_BINS"]["DB_TABLES"] if table not in [config["CONVERSATION"]["DB_TABLE"]["ANDROID"], config["ACTIVITY_RECOGNITION"]["DB_TABLE"]["ANDROID"]]] # for ios, discard any android tables that may exist
for pids,table in zip([pids_android, pids_ios], [tables_android, tables_ios]):
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=pids, sensor=table))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=pids, sensor=table))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=map(str.lower, config["PHONE_VALID_SENSED_BINS"]["PHONE_SENSORS"])))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=map(str.lower, config["PHONE_VALID_SENSED_BINS"]["PHONE_SENSORS"])))
files_to_compute.extend(expand("data/interim/{pid}/phone_sensed_bins.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_sensed_timestamps.csv", pid=config["PIDS"]))
if config["PHONE_VALID_SENSED_DAYS"]["COMPUTE"]:
files_to_compute.extend(expand("data/interim/{pid}/phone_valid_sensed_days_{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins.csv",
@ -32,68 +27,158 @@ if config["PHONE_VALID_SENSED_DAYS"]["COMPUTE"]:
min_valid_hours_per_day=config["PHONE_VALID_SENSED_DAYS"]["MIN_VALID_HOURS_PER_DAY"],
min_valid_bins_per_hour=config["PHONE_VALID_SENSED_DAYS"]["MIN_VALID_BINS_PER_HOUR"]))
for provider in config["MESSAGES"]["PROVIDERS"].keys():
if config["MESSAGES"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["MESSAGES"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["MESSAGES"]["DB_TABLE"]))
files_to_compute.extend(expand("data/interim/{pid}/{sensor_key}_features/{sensor_key}_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["MESSAGES"]["PROVIDERS"][provider]["SRC_LANGUAGE"], provider_key=provider, sensor_key="MESSAGES".lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/{sensor_key}.csv", pid=config["PIDS"], sensor_key="MESSAGES".lower()))
for provider in config["PHONE_MESSAGES"]["PROVIDERS"].keys():
if config["PHONE_MESSAGES"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/phone_messages_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_messages_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_messages_features/phone_messages_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_MESSAGES"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_messages.csv", pid=config["PIDS"]))
for provider in config["CALLS"]["PROVIDERS"].keys():
if config["CALLS"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["CALLS"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["CALLS"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime_unified.csv", pid=config["PIDS"], sensor=config["CALLS"]["DB_TABLE"]))
files_to_compute.extend(expand("data/interim/{pid}/{sensor_key}_features/{sensor_key}_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["CALLS"]["PROVIDERS"][provider]["SRC_LANGUAGE"], provider_key=provider, sensor_key="CALLS".lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/{sensor_key}.csv", pid=config["PIDS"], sensor_key="CALLS".lower()))
for provider in config["PHONE_CALLS"]["PROVIDERS"].keys():
if config["PHONE_CALLS"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/phone_calls_raw.csv", pid=config["PIDS"], sensor=config["PHONE_CALLS"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_calls_with_datetime.csv", pid=config["PIDS"], sensor=config["PHONE_CALLS"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_calls_with_datetime_unified.csv", pid=config["PIDS"], sensor=config["PHONE_CALLS"]["DB_TABLE"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_calls_features/phone_calls_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_CALLS"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_calls.csv", pid=config["PIDS"]))
for provider in config["BLUETOOTH"]["PROVIDERS"].keys():
if config["BLUETOOTH"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["BLUETOOTH"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["BLUETOOTH"]["DB_TABLE"]))
files_to_compute.extend(expand("data/interim/{pid}/{sensor_key}_features/{sensor_key}_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["BLUETOOTH"]["PROVIDERS"][provider]["SRC_LANGUAGE"], provider_key=provider, sensor_key="BLUETOOTH".lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/{sensor_key}.csv", pid=config["PIDS"], sensor_key="BLUETOOTH".lower()))
for provider in config["PHONE_BLUETOOTH"]["PROVIDERS"].keys():
if config["PHONE_BLUETOOTH"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/phone_bluetooth_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_bluetooth_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_bluetooth_features/phone_bluetooth_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_BLUETOOTH"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_bluetooth.csv", pid=config["PIDS"]))
for provider in config["LIGHT"]["PROVIDERS"].keys():
if config["LIGHT"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["LIGHT"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["LIGHT"]["DB_TABLE"]))
files_to_compute.extend(expand("data/interim/{pid}/{sensor_key}_features/{sensor_key}_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["LIGHT"]["PROVIDERS"][provider]["SRC_LANGUAGE"], provider_key=provider, sensor_key="LIGHT".lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/{sensor_key}.csv", pid=config["PIDS"], sensor_key="LIGHT".lower()))
for provider in config["PHONE_ACTIVITY_RECOGNITION"]["PROVIDERS"].keys():
if config["PHONE_ACTIVITY_RECOGNITION"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/phone_activity_recognition_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_activity_recognition_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_activity_recognition_with_datetime_unified.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_activity_recognition_episodes.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_activity_recognition_episodes_resampled.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_activity_recognition_episodes_resampled_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_activity_recognition_features/phone_activity_recognition_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_ACTIVITY_RECOGNITION"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_activity_recognition.csv", pid=config["PIDS"]))
for provider in config["APPLICATIONS_FOREGROUND"]["PROVIDERS"].keys():
if config["APPLICATIONS_FOREGROUND"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["APPLICATIONS_FOREGROUND"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["APPLICATIONS_FOREGROUND"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime_with_genre.csv", pid=config["PIDS"], sensor=config["APPLICATIONS_FOREGROUND"]["DB_TABLE"]))
files_to_compute.extend(expand("data/interim/{pid}/{sensor_key}_features/{sensor_key}_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["APPLICATIONS_FOREGROUND"]["PROVIDERS"][provider]["SRC_LANGUAGE"], provider_key=provider, sensor_key="APPLICATIONS_FOREGROUND".lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/{sensor_key}.csv", pid=config["PIDS"], sensor_key="APPLICATIONS_FOREGROUND".lower()))
for provider in config["WIFI"]["PROVIDERS"].keys():
if config["WIFI"]["PROVIDERS"][provider]["COMPUTE"]:
if len(config["WIFI"]["DB_TABLE"]["VISIBLE_ACCESS_POINTS"]) > 0:
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["WIFI"]["DB_TABLE"]["VISIBLE_ACCESS_POINTS"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["WIFI"]["DB_TABLE"]["VISIBLE_ACCESS_POINTS"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor_key}_with_datetime_visibleandconnected.csv", pid=config["PIDS"], sensor_key="WIFI".lower()))
files_to_compute.extend(expand("data/interim/{pid}/{sensor_key}_features/{sensor_key}_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["WIFI"]["PROVIDERS"][provider]["SRC_LANGUAGE"], provider_key=provider, sensor_key="WIFI".lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/{sensor_key}.csv", pid=config["PIDS"], sensor_key="WIFI".lower()))
if len(config["WIFI"]["DB_TABLE"]["CONNECTED_ACCESS_POINTS"]) > 0:
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["WIFI"]["DB_TABLE"]["CONNECTED_ACCESS_POINTS"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["WIFI"]["DB_TABLE"]["CONNECTED_ACCESS_POINTS"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor_key}_with_datetime_visibleandconnected.csv", pid=config["PIDS"], sensor_key="WIFI".lower()))
files_to_compute.extend(expand("data/interim/{pid}/{sensor_key}_features/{sensor_key}_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["WIFI"]["PROVIDERS"][provider]["SRC_LANGUAGE"], provider_key=provider, sensor_key="WIFI".lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/{sensor_key}.csv", pid=config["PIDS"], sensor_key="WIFI".lower()))
for provider in config["PHONE_BATTERY"]["PROVIDERS"].keys():
if config["PHONE_BATTERY"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/phone_battery_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_battery_episodes.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_battery_episodes_resampled.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_battery_episodes_resampled_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_battery_features/phone_battery_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_BATTERY"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_battery.csv", pid=config["PIDS"]))
for provider in config["PHONE_SCREEN"]["PROVIDERS"].keys():
if config["PHONE_SCREEN"]["PROVIDERS"][provider]["COMPUTE"]:
if "PHONE_SCREEN" in config["PHONE_VALID_SENSED_BINS"]["PHONE_SENSORS"]:
files_to_compute.extend(expand("data/interim/{pid}/phone_sensed_bins.csv", pid=config["PIDS"]))
else:
raise ValueError("Error: Add PHONE_SCREEN (and as many phone sensor as you have in your database) to [PHONE_VALID_SENSED_BINS][PHONE_SENSORS] in config.yaml. This is necessary to compute phone_sensed_bins (bins of time when the smartphone was sensing data)")
files_to_compute.extend(expand("data/raw/{pid}/phone_screen_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_screen_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_screen_with_datetime_unified.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_screen_episodes.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_screen_episodes_resampled.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_screen_episodes_resampled_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_screen_features/phone_screen_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_SCREEN"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_screen.csv", pid=config["PIDS"]))
for provider in config["PHONE_LIGHT"]["PROVIDERS"].keys():
if config["PHONE_LIGHT"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/phone_light_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_light_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_light_features/phone_light_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_LIGHT"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_light.csv", pid=config["PIDS"],))
for provider in config["PHONE_ACCELEROMETER"]["PROVIDERS"].keys():
if config["PHONE_ACCELEROMETER"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/phone_accelerometer_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_accelerometer_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_accelerometer_features/phone_accelerometer_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_ACCELEROMETER"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_accelerometer.csv", pid=config["PIDS"]))
for provider in config["PHONE_APPLICATIONS_FOREGROUND"]["PROVIDERS"].keys():
if config["PHONE_APPLICATIONS_FOREGROUND"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/phone_applications_foreground_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_applications_foreground_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_applications_foreground_with_datetime_with_categories.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_applications_foreground_features/phone_applications_foreground_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_APPLICATIONS_FOREGROUND"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_applications_foreground.csv", pid=config["PIDS"]))
for provider in config["PHONE_WIFI_VISIBLE"]["PROVIDERS"].keys():
if config["PHONE_WIFI_VISIBLE"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/phone_wifi_visible_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_wifi_visible_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_wifi_visible_features/phone_wifi_visible_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_WIFI_VISIBLE"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_wifi_visible.csv", pid=config["PIDS"]))
for provider in config["PHONE_WIFI_CONNECTED"]["PROVIDERS"].keys():
if config["PHONE_WIFI_CONNECTED"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/phone_wifi_connected_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_wifi_connected_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_wifi_connected_features/phone_wifi_connected_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_WIFI_CONNECTED"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_wifi_connected.csv", pid=config["PIDS"]))
if config["HEARTRATE"]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["HEARTRATE"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_heartrate_{fitbit_data_type}_with_datetime.csv", pid=config["PIDS"], fitbit_data_type=["summary", "intraday"]))
files_to_compute.extend(expand("data/processed/{pid}/fitbit_heartrate_{day_segment}.csv", pid = config["PIDS"], day_segment = config["HEARTRATE"]["DAY_SEGMENTS"]))
if config["STEP"]["COMPUTE"]:
if config["STEP"]["EXCLUDE_SLEEP"]["EXCLUDE"] == True and config["STEP"]["EXCLUDE_SLEEP"]["TYPE"] == "FITBIT_BASED":
files_to_compute.extend(expand("data/raw/{pid}/fitbit_sleep_{fitbit_data_type}_with_datetime.csv", pid=config["PIDS"], fitbit_data_type=["summary"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["STEP"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_step_{fitbit_data_type}_with_datetime.csv", pid=config["PIDS"], fitbit_data_type=["intraday"]))
files_to_compute.extend(expand("data/processed/{pid}/fitbit_step_{day_segment}.csv", pid = config["PIDS"], day_segment = config["STEP"]["DAY_SEGMENTS"]))
if config["SLEEP"]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["SLEEP"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_sleep_{fitbit_data_type}_with_datetime.csv", pid=config["PIDS"], fitbit_data_type=["intraday", "summary"]))
files_to_compute.extend(expand("data/processed/{pid}/fitbit_sleep_{day_segment}.csv", pid = config["PIDS"], day_segment = config["SLEEP"]["DAY_SEGMENTS"]))
for provider in config["PHONE_CONVERSATION"]["PROVIDERS"].keys():
if config["PHONE_CONVERSATION"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/phone_conversation_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_conversation_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_conversation_with_datetime_unified.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_conversation_features/phone_conversation_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_CONVERSATION"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_conversation.csv", pid=config["PIDS"]))
for provider in config["PHONE_LOCATIONS"]["PROVIDERS"].keys():
if config["PHONE_LOCATIONS"]["PROVIDERS"][provider]["COMPUTE"]:
if config["PHONE_LOCATIONS"]["LOCATIONS_TO_USE"] == "RESAMPLE_FUSED":
if config["PHONE_LOCATIONS"]["DB_TABLE"] in config["PHONE_VALID_SENSED_BINS"]["DB_TABLES"]:
files_to_compute.extend(expand("data/interim/{pid}/phone_sensed_bins.csv", pid=config["PIDS"]))
else:
raise ValueError("Error: Add your locations table (and as many sensor tables as you have) to [PHONE_VALID_SENSED_BINS][DB_TABLES] in config.yaml. This is necessary to compute phone_sensed_bins (bins of time when the smartphone was sensing data) which is used to resample fused location data (RESAMPLED_FUSED)")
files_to_compute.extend(expand("data/raw/{pid}/phone_locations_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_locations_processed.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_locations_processed_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_locations_features/phone_locations_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_LOCATIONS"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_locations.csv", pid=config["PIDS"]))
# visualization for data exploration
if config["HEATMAP_FEATURES_CORRELATIONS"]["PLOT"]:
files_to_compute.extend(expand("reports/data_exploration/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/heatmap_features_correlations.html", min_valid_hours_per_day=config["HEATMAP_FEATURES_CORRELATIONS"]["MIN_VALID_HOURS_PER_DAY"], min_valid_bins_per_hour=config["PHONE_VALID_SENSED_DAYS"]["MIN_VALID_BINS_PER_HOUR"]))
if config["HISTOGRAM_VALID_SENSED_HOURS"]["PLOT"]:
files_to_compute.extend(expand("reports/data_exploration/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/histogram_valid_sensed_hours.html", min_valid_hours_per_day=config["HISTOGRAM_VALID_SENSED_HOURS"]["MIN_VALID_HOURS_PER_DAY"], min_valid_bins_per_hour=config["PHONE_VALID_SENSED_DAYS"]["MIN_VALID_BINS_PER_HOUR"]))
if config["HEATMAP_DAYS_BY_SENSORS"]["PLOT"]:
files_to_compute.extend(expand("reports/interim/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{pid}/heatmap_days_by_sensors.html", pid=config["PIDS"], min_valid_hours_per_day=config["HEATMAP_DAYS_BY_SENSORS"]["MIN_VALID_HOURS_PER_DAY"], min_valid_bins_per_hour=config["PHONE_VALID_SENSED_DAYS"]["MIN_VALID_BINS_PER_HOUR"]))
files_to_compute.extend(expand("reports/data_exploration/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/heatmap_days_by_sensors_all_participants.html", min_valid_hours_per_day=config["HEATMAP_DAYS_BY_SENSORS"]["MIN_VALID_HOURS_PER_DAY"], min_valid_bins_per_hour=config["PHONE_VALID_SENSED_DAYS"]["MIN_VALID_BINS_PER_HOUR"]))
if config["HEATMAP_SENSED_BINS"]["PLOT"]:
files_to_compute.extend(expand("reports/interim/heatmap_sensed_bins/{pid}/heatmap_sensed_bins.html", pid=config["PIDS"]))
files_to_compute.extend(["reports/data_exploration/heatmap_sensed_bins_all_participants.html"])
if config["OVERALL_COMPLIANCE_HEATMAP"]["PLOT"]:
files_to_compute.extend(expand("reports/data_exploration/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/overall_compliance_heatmap.html", min_valid_hours_per_day=config["OVERALL_COMPLIANCE_HEATMAP"]["MIN_VALID_HOURS_PER_DAY"], min_valid_bins_per_hour=config["PHONE_VALID_SENSED_DAYS"]["MIN_VALID_BINS_PER_HOUR"]))
for provider in config["CONVERSATION"]["PROVIDERS"].keys():
if config["CONVERSATION"]["PROVIDERS"][provider]["COMPUTE"]:
pids_android = list(filter(lambda pid: infer_participant_platform("data/external/" + pid) == "android", config["PIDS"]))
pids_ios = list(filter(lambda pid: infer_participant_platform("data/external/" + pid) == "ios", config["PIDS"]))
for pids,table in zip([pids_android, pids_ios], [config["CONVERSATION"]["DB_TABLE"]["ANDROID"], config["CONVERSATION"]["DB_TABLE"]["IOS"]]):
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=pids, sensor=table))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=pids, sensor=table))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime_unified.csv", pid=pids, sensor=table))
files_to_compute.extend(expand("data/interim/{pid}/{sensor_key}_features/{sensor_key}_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["CONVERSATION"]["PROVIDERS"][provider]["SRC_LANGUAGE"], provider_key=provider, sensor_key="CONVERSATION".lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/{sensor_key}.csv", pid=config["PIDS"], sensor_key="CONVERSATION".lower()))
rule all:
input:

View File

@ -6,12 +6,46 @@ PIDS: [test03, test04,test05, test06]
DAY_SEGMENTS: &day_segments
TYPE: FREQUENCY # FREQUENCY, PERIODIC, EVENT
FILE: "data/external/daysegments_frequency.csv"
INCLUDE_PAST_PERIODIC_SEGMENTS: FALSE # Only relevant if TYPE=PERIODIC, if set to TRUE we consider day segments back enough in the past as to include the first day of data
# 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
PHONE_VALID_SENSED_BINS:
DB_TABLES: [bluetooth]
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
BIN_SIZE: &bin_size 5 # (in minutes)
# Add as many PHONE sensors as you have, they all improve the computation of PHONE_VALID_SENSED_BINS and PHONE_VALID_SENSED_DAYS.
# If you are extracting screen or Barnett/Doryab location features, PHONE_SCREEN and PHONE_LOCATIONS tables are mandatory.
# You can choose any of the keys shown below, just make sure its DB_TABLE exists in your database!
# PHONE_MESSAGES, PHONE_CALLS, PHONE_LOCATIONS, PHONE_BLUETOOTH, PHONE_ACTIVITY_RECOGNITION, PHONE_BATTERY, PHONE_SCREEN, PHONE_LIGHT,
# PHONE_ACCELEROMETER, PHONE_APPLICATIONS_FOREGROUND, PHONE_WIFI_VISIBLE, PHONE_WIFI_CONNECTED, PHONE_CONVERSATION
PHONE_SENSORS: []
PHONE_VALID_SENSED_DAYS:
COMPUTE: False
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)
# Communication SMS features config, TYPES and FEATURES keys need to match
MESSAGES:
PHONE_MESSAGES:
DB_TABLE: messages
PROVIDERS:
RAPIDS:
@ -21,68 +55,163 @@ MESSAGES:
received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
sent: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
SRC_LANGUAGE: "r"
SRC_FOLDER: "rapids" # inside src/features/messages
SRC_FOLDER: "rapids" # inside src/features/phone_messages
# Communication call features config, TYPES and FEATURES keys need to match
CALLS:
PHONE_CALLS:
DB_TABLE: calls
PROVIDERS:
RAPIDS:
COMPUTE: True
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"
SRC_FOLDER: "rapids" # inside src/features/calls
SRC_FOLDER: "rapids" # inside src/features/phone_calls
BLUETOOTH:
PHONE_LOCATIONS:
DB_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
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_BLUETOOTH:
DB_TABLE: bluetooth
PROVIDERS:
RAPIDS:
COMPUTE: True
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/bluetooth
SRC_FOLDER: "rapids" # inside src/features/phone_bluetooth
SRC_LANGUAGE: "r"
LIGHT:
PHONE_ACTIVITY_RECOGNITION:
DB_TABLE:
ANDROID: plugin_google_activity_recognition
IOS: plugin_ios_activity_recognition
PROVIDERS:
RAPIDS:
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"
PHONE_BATTERY:
DB_TABLE: battery
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
SRC_FOLDER: "rapids" # inside src/features/phone_battery
SRC_LANGUAGE: "python"
PHONE_SCREEN:
DB_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"]
SRC_FOLDER: "rapids" # inside src/features/phone_screen
SRC_LANGUAGE: "python"
PHONE_LIGHT:
DB_TABLE: light
PROVIDERS:
RAPIDS:
COMPUTE: True
COMPUTE: False
FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
SRC_FOLDER: "rapids" # inside src/features/light
SRC_FOLDER: "rapids" # inside src/features/phone_light
SRC_LANGUAGE: "python"
WIFI:
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 ""
PHONE_ACCELEROMETER:
DB_TABLE: accelerometer
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/bluetooth
SRC_LANGUAGE: "r"
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"
APPLICATIONS_FOREGROUND:
PHONE_APPLICATIONS_FOREGROUND:
DB_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: True
COMPUTE: False
SINGLE_CATEGORIES: ["all", "email"]
MULTIPLE_CATEGORIES:
social: ["socialnetworks", "socialmediatools"]
entertainment: ["entertainment", "gamingstrategy"]
SINGLE_APPS: ["top1global", "com.facebook.moments"] # There's no entropy for single apps
EXCLUDED_CATEGORIES: ["systemapp", "tvvideoapps"]
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/applications_foreground
SRC_FOLDER: "rapids" # inside src/features/phone_applications_foreground
SRC_LANGUAGE: "python"
CONVERSATION:
PHONE_WIFI_VISIBLE:
DB_TABLE: "wifi"
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_wifi_visible
SRC_LANGUAGE: "r"
PHONE_WIFI_CONNECTED:
DB_TABLE: "sensor_wifi"
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_wifi_connected
SRC_LANGUAGE: "r"
PHONE_CONVERSATION:
DB_TABLE:
ANDROID: plugin_studentlife_audio_android
IOS: plugin_studentlife_audio
@ -90,12 +219,79 @@ CONVERSATION:
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",
"sdconversationduration","minconversationduration","maxconversationduration","timefirstconversation","timelastconversation","sumenergy",
"avgenergy","sdenergy","minenergy","maxenergy","silencesensedfraction","noisesensedfraction",
"voicesensedfraction","unknownsensedfraction","silenceexpectedfraction","noiseexpectedfraction","voiceexpectedfraction",
"unknownexpectedfraction","countconversation"]
RECORDING_MINUTES: 1
PAUSED_MINUTES : 3
SRC_FOLDER: "rapids" # inside src/features/conversation
SRC_FOLDER: "rapids" # inside src/features/phone_conversation
SRC_LANGUAGE: "python"
HEARTRATE:
COMPUTE: False
DB_TABLE: fitbit_data
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"]
INTRADAY_FEATURES: ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "minutesonoutofrangezone", "minutesonfatburnzone", "minutesoncardiozone", "minutesonpeakzone"]
STEP:
COMPUTE: False
DB_TABLE: fitbit_data
DAY_SEGMENTS: *day_segments
EXCLUDE_SLEEP:
EXCLUDE: False
TYPE: FIXED # FIXED OR FITBIT_BASED (CONFIGURE FITBIT's SLEEP DB_TABLE)
FIXED:
START: "23:00"
END: "07:00"
FEATURES:
ALL_STEPS: ["sumallsteps", "maxallsteps", "minallsteps", "avgallsteps", "stdallsteps"]
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
SLEEP:
COMPUTE: False
DB_TABLE: fitbit_data
DAY_SEGMENTS: *day_segments
SLEEP_TYPES: ["main", "nap", "all"]
SUMMARY_FEATURES: ["sumdurationafterwakeup", "sumdurationasleep", "sumdurationawake", "sumdurationtofallasleep", "sumdurationinbed", "avgefficiency", "countepisode"]
### 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
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"}
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
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
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]
HEATMAP_SENSED_BINS:
PLOT: False
BIN_SIZE: *bin_size
OVERALL_COMPLIANCE_HEATMAP:
PLOT: False
ONLY_SHOW_VALID_DAYS: False
EXPECTED_NUM_OF_DAYS: -1
BIN_SIZE: *bin_size
MIN_VALID_HOURS_PER_DAY: *min_valid_hours_per_day
MIN_VALID_BINS_PER_HOUR: *min_valid_bins_per_hour

View File

@ -2,17 +2,50 @@
# You must create a file for each participant named pXXX containing their device_id. This can be done manually or automatically
PIDS: [test01, test02, test03, test04]
# Global var with common day segments
DAY_SEGMENTS: &day_segments
TYPE: PERIODIC # FREQUENCY, PERIODIC, EVENT
FILE: "data/external/daysegments_periodic.csv"
INCLUDE_PAST_PERIODIC_SEGMENTS: FALSE # Only relevant if TYPE=PERIODIC, if set to TRUE we consider day segments back enough in the past as to include the first day of data
# 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
PHONE_VALID_SENSED_BINS:
DB_TABLES: [messages, calls, bluetooth, light, wifi, applications_foreground]
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
BIN_SIZE: &bin_size 5 # (in minutes)
# Add as many PHONE sensors as you have, they all improve the computation of PHONE_VALID_SENSED_BINS and PHONE_VALID_SENSED_DAYS.
# If you are extracting screen or Barnett/Doryab location features, PHONE_SCREEN and PHONE_LOCATIONS tables are mandatory.
# You can choose any of the keys shown below, just make sure its DB_TABLE exists in your database!
# PHONE_MESSAGES, PHONE_CALLS, PHONE_LOCATIONS, PHONE_BLUETOOTH, PHONE_ACTIVITY_RECOGNITION, PHONE_BATTERY, PHONE_SCREEN, PHONE_LIGHT,
# PHONE_ACCELEROMETER, PHONE_APPLICATIONS_FOREGROUND, PHONE_WIFI_VISIBLE, PHONE_WIFI_CONNECTED, PHONE_CONVERSATION
PHONE_SENSORS: []
PHONE_VALID_SENSED_DAYS:
COMPUTE: False
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)
# Communication SMS features config, TYPES and FEATURES keys need to match
MESSAGES:
PHONE_MESSAGES:
DB_TABLE: messages
PROVIDERS:
RAPIDS:
@ -22,68 +55,163 @@ MESSAGES:
received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
sent: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
SRC_LANGUAGE: "r"
SRC_FOLDER: "rapids" # inside src/features/messages
SRC_FOLDER: "rapids" # inside src/features/phone_messages
# Communication call features config, TYPES and FEATURES keys need to match
CALLS:
PHONE_CALLS:
DB_TABLE: calls
PROVIDERS:
RAPIDS:
COMPUTE: True
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"
SRC_FOLDER: "rapids" # inside src/features/calls
SRC_FOLDER: "rapids" # inside src/features/phone_calls
BLUETOOTH:
PHONE_LOCATIONS:
DB_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
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_BLUETOOTH:
DB_TABLE: bluetooth
PROVIDERS:
RAPIDS:
COMPUTE: True
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/bluetooth
SRC_FOLDER: "rapids" # inside src/features/phone_bluetooth
SRC_LANGUAGE: "r"
LIGHT:
PHONE_ACTIVITY_RECOGNITION:
DB_TABLE:
ANDROID: plugin_google_activity_recognition
IOS: plugin_ios_activity_recognition
PROVIDERS:
RAPIDS:
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"
PHONE_BATTERY:
DB_TABLE: battery
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
SRC_FOLDER: "rapids" # inside src/features/phone_battery
SRC_LANGUAGE: "python"
PHONE_SCREEN:
DB_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"]
SRC_FOLDER: "rapids" # inside src/features/phone_screen
SRC_LANGUAGE: "python"
PHONE_LIGHT:
DB_TABLE: light
PROVIDERS:
RAPIDS:
COMPUTE: True
COMPUTE: False
FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
SRC_FOLDER: "rapids" # inside src/features/light
SRC_FOLDER: "rapids" # inside src/features/phone_light
SRC_LANGUAGE: "python"
WIFI:
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 ""
PHONE_ACCELEROMETER:
DB_TABLE: accelerometer
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/bluetooth
SRC_LANGUAGE: "r"
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"
APPLICATIONS_FOREGROUND:
PHONE_APPLICATIONS_FOREGROUND:
DB_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: True
COMPUTE: False
SINGLE_CATEGORIES: ["all", "email"]
MULTIPLE_CATEGORIES:
social: ["socialnetworks", "socialmediatools"]
entertainment: ["entertainment", "gamingstrategy"]
SINGLE_APPS: ["top1global", "com.facebook.moments"] # There's no entropy for single apps
EXCLUDED_CATEGORIES: ["systemapp", "tvvideoapps"]
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/applications_foreground
SRC_FOLDER: "rapids" # inside src/features/phone_applications_foreground
SRC_LANGUAGE: "python"
CONVERSATION:
PHONE_WIFI_VISIBLE:
DB_TABLE: "wifi"
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_wifi_visible
SRC_LANGUAGE: "r"
PHONE_WIFI_CONNECTED:
DB_TABLE: "sensor_wifi"
PROVIDERS:
RAPIDS:
COMPUTE: False
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_wifi_connected
SRC_LANGUAGE: "r"
PHONE_CONVERSATION:
DB_TABLE:
ANDROID: plugin_studentlife_audio_android
IOS: plugin_studentlife_audio
@ -91,12 +219,79 @@ CONVERSATION:
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",
"sdconversationduration","minconversationduration","maxconversationduration","timefirstconversation","timelastconversation","sumenergy",
"avgenergy","sdenergy","minenergy","maxenergy","silencesensedfraction","noisesensedfraction",
"voicesensedfraction","unknownsensedfraction","silenceexpectedfraction","noiseexpectedfraction","voiceexpectedfraction",
"unknownexpectedfraction","countconversation"]
RECORDING_MINUTES: 1
PAUSED_MINUTES : 3
SRC_FOLDER: "rapids" # inside src/features/conversation
SRC_FOLDER: "rapids" # inside src/features/phone_conversation
SRC_LANGUAGE: "python"
HEARTRATE:
COMPUTE: False
DB_TABLE: fitbit_data
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"]
INTRADAY_FEATURES: ["maxhr", "minhr", "avghr", "medianhr", "modehr", "stdhr", "diffmaxmodehr", "diffminmodehr", "entropyhr", "minutesonoutofrangezone", "minutesonfatburnzone", "minutesoncardiozone", "minutesonpeakzone"]
STEP:
COMPUTE: False
DB_TABLE: fitbit_data
DAY_SEGMENTS: *day_segments
EXCLUDE_SLEEP:
EXCLUDE: False
TYPE: FIXED # FIXED OR FITBIT_BASED (CONFIGURE FITBIT's SLEEP DB_TABLE)
FIXED:
START: "23:00"
END: "07:00"
FEATURES:
ALL_STEPS: ["sumallsteps", "maxallsteps", "minallsteps", "avgallsteps", "stdallsteps"]
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
SLEEP:
COMPUTE: False
DB_TABLE: fitbit_data
DAY_SEGMENTS: *day_segments
SLEEP_TYPES: ["main", "nap", "all"]
SUMMARY_FEATURES: ["sumdurationafterwakeup", "sumdurationasleep", "sumdurationawake", "sumdurationtofallasleep", "sumdurationinbed", "avgefficiency", "countepisode"]
### 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
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"}
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
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
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]
HEATMAP_SENSED_BINS:
PLOT: False
BIN_SIZE: *bin_size
OVERALL_COMPLIANCE_HEATMAP:
PLOT: False
ONLY_SHOW_VALID_DAYS: False
EXPECTED_NUM_OF_DAYS: -1
BIN_SIZE: *bin_size
MIN_VALID_HOURS_PER_DAY: *min_valid_hours_per_day
MIN_VALID_BINS_PER_HOUR: *min_valid_bins_per_hour