junos
/
rapids
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Add analysis example workflow

pull/103/head
Meng Li 2020-11-25 16:34:05 -05:00
parent ced3305ddb
commit b4a512faf3
32 changed files with 983 additions and 1086 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

43
Snakefile
View File

@ -19,6 +19,8 @@ for provider in config["PHONE_DATA_YIELD"]["PROVIDERS"].keys():
files_to_compute.extend(expand("data/interim/{pid}/phone_yielded_timestamps_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_data_yield_features/phone_data_yield_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_DATA_YIELD"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_data_yield.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_MESSAGES"]["PROVIDERS"].keys():
if config["PHONE_MESSAGES"]["PROVIDERS"][provider]["COMPUTE"]:
@ -26,6 +28,8 @@ for provider in config["PHONE_MESSAGES"]["PROVIDERS"].keys():
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_CALLS"]["PROVIDERS"].keys():
if config["PHONE_CALLS"]["PROVIDERS"][provider]["COMPUTE"]:
@ -34,6 +38,8 @@ for provider in config["PHONE_CALLS"]["PROVIDERS"].keys():
files_to_compute.extend(expand("data/raw/{pid}/phone_calls_with_datetime_unified.csv", pid=config["PIDS"]))
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_BLUETOOTH"]["PROVIDERS"].keys():
if config["PHONE_BLUETOOTH"]["PROVIDERS"][provider]["COMPUTE"]:
@ -41,6 +47,8 @@ for provider in config["PHONE_BLUETOOTH"]["PROVIDERS"].keys():
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_ACTIVITY_RECOGNITION"]["PROVIDERS"].keys():
if config["PHONE_ACTIVITY_RECOGNITION"]["PROVIDERS"][provider]["COMPUTE"]:
@ -52,7 +60,8 @@ for provider in config["PHONE_ACTIVITY_RECOGNITION"]["PROVIDERS"].keys():
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_BATTERY"]["PROVIDERS"].keys():
if config["PHONE_BATTERY"]["PROVIDERS"][provider]["COMPUTE"]:
@ -62,7 +71,8 @@ for provider in config["PHONE_BATTERY"]["PROVIDERS"].keys():
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_SCREEN"]["PROVIDERS"].keys():
if config["PHONE_SCREEN"]["PROVIDERS"][provider]["COMPUTE"]:
@ -78,6 +88,8 @@ for provider in config["PHONE_SCREEN"]["PROVIDERS"].keys():
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_LIGHT"]["PROVIDERS"].keys():
if config["PHONE_LIGHT"]["PROVIDERS"][provider]["COMPUTE"]:
@ -85,6 +97,8 @@ for provider in config["PHONE_LIGHT"]["PROVIDERS"].keys():
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"],))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_ACCELEROMETER"]["PROVIDERS"].keys():
if config["PHONE_ACCELEROMETER"]["PROVIDERS"][provider]["COMPUTE"]:
@ -92,6 +106,8 @@ for provider in config["PHONE_ACCELEROMETER"]["PROVIDERS"].keys():
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_APPLICATIONS_FOREGROUND"]["PROVIDERS"].keys():
if config["PHONE_APPLICATIONS_FOREGROUND"]["PROVIDERS"][provider]["COMPUTE"]:
@ -100,6 +116,8 @@ for provider in config["PHONE_APPLICATIONS_FOREGROUND"]["PROVIDERS"].keys():
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_WIFI_VISIBLE"]["PROVIDERS"].keys():
if config["PHONE_WIFI_VISIBLE"]["PROVIDERS"][provider]["COMPUTE"]:
@ -107,6 +125,8 @@ for provider in config["PHONE_WIFI_VISIBLE"]["PROVIDERS"].keys():
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_WIFI_CONNECTED"]["PROVIDERS"].keys():
if config["PHONE_WIFI_CONNECTED"]["PROVIDERS"][provider]["COMPUTE"]:
@ -114,6 +134,8 @@ for provider in config["PHONE_WIFI_CONNECTED"]["PROVIDERS"].keys():
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_CONVERSATION"]["PROVIDERS"].keys():
if config["PHONE_CONVERSATION"]["PROVIDERS"][provider]["COMPUTE"]:
@ -122,6 +144,8 @@ for provider in config["PHONE_CONVERSATION"]["PROVIDERS"].keys():
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_LOCATIONS"]["PROVIDERS"].keys():
if config["PHONE_LOCATIONS"]["PROVIDERS"][provider]["COMPUTE"]:
@ -136,6 +160,8 @@ for provider in config["PHONE_LOCATIONS"]["PROVIDERS"].keys():
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
if config["FITBIT_CALORIES"]["TABLE_FORMAT"] not in ["JSON", "CSV"]:
raise ValueError("config['FITBIT_CALORIES']['TABLE_FORMAT'] should be JSON or CSV but you typed" + config["FITBIT_CALORIES"]["TABLE_FORMAT"])
@ -147,6 +173,8 @@ for provider in config["FITBIT_HEARTRATE_SUMMARY"]["PROVIDERS"].keys():
files_to_compute.extend(expand("data/raw/{pid}/fitbit_heartrate_summary_parsed_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/fitbit_heartrate_summary_features/fitbit_heartrate_summary_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["FITBIT_HEARTRATE_SUMMARY"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/fitbit_heartrate_summary.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["FITBIT_HEARTRATE_INTRADAY"]["PROVIDERS"].keys():
if config["FITBIT_HEARTRATE_INTRADAY"]["PROVIDERS"][provider]["COMPUTE"]:
@ -155,6 +183,8 @@ for provider in config["FITBIT_HEARTRATE_INTRADAY"]["PROVIDERS"].keys():
files_to_compute.extend(expand("data/raw/{pid}/fitbit_heartrate_intraday_parsed_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/fitbit_heartrate_intraday_features/fitbit_heartrate_intraday_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["FITBIT_HEARTRATE_INTRADAY"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/fitbit_heartrate_intraday.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["FITBIT_SLEEP_SUMMARY"]["PROVIDERS"].keys():
if config["FITBIT_SLEEP_SUMMARY"]["PROVIDERS"][provider]["COMPUTE"]:
@ -163,6 +193,8 @@ for provider in config["FITBIT_SLEEP_SUMMARY"]["PROVIDERS"].keys():
files_to_compute.extend(expand("data/raw/{pid}/fitbit_sleep_summary_parsed_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/fitbit_sleep_summary_features/fitbit_sleep_summary_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["FITBIT_SLEEP_SUMMARY"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/fitbit_sleep_summary.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
# for provider in config["FITBIT_SLEEP_INTRADAY"]["PROVIDERS"].keys():
# if config["FITBIT_SLEEP_INTRADAY"]["PROVIDERS"][provider]["COMPUTE"]:
@ -177,6 +209,8 @@ for provider in config["FITBIT_STEPS_SUMMARY"]["PROVIDERS"].keys():
files_to_compute.extend(expand("data/raw/{pid}/fitbit_steps_summary_parsed_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/fitbit_steps_summary_features/fitbit_steps_summary_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["FITBIT_STEPS_SUMMARY"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/fitbit_steps_summary.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["FITBIT_STEPS_INTRADAY"]["PROVIDERS"].keys():
if config["FITBIT_STEPS_INTRADAY"]["PROVIDERS"][provider]["COMPUTE"]:
@ -185,12 +219,17 @@ for provider in config["FITBIT_STEPS_INTRADAY"]["PROVIDERS"].keys():
files_to_compute.extend(expand("data/raw/{pid}/fitbit_steps_intraday_parsed_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/fitbit_steps_intraday_features/fitbit_steps_intraday_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["FITBIT_STEPS_INTRADAY"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/fitbit_steps_intraday.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["FITBIT_CALORIES"]["PROVIDERS"].keys():
if config["FITBIT_CALORIES"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/fitbit_calories_{fitbit_data_type}_raw.csv", pid=config["PIDS"], fitbit_data_type=(["json"] if config["FITBIT_CALORIES"]["TABLE_FORMAT"] == "JSON" else ["summary", "intraday"])))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_calories_{fitbit_data_type}_parsed.csv", pid=config["PIDS"], fitbit_data_type=["summary", "intraday"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_calories_{fitbit_data_type}_parsed_with_datetime.csv", pid=config["PIDS"], fitbit_data_type=["summary", "intraday"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
# visualization for data exploration
# if config["HEATMAP_FEATURES_CORRELATIONS"]["PLOT"]:

493
example_profile/Snakefile
View File

@ -13,272 +13,245 @@ files_to_compute = []
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")
for provider in config["PHONE_DATA_YIELD"]["PROVIDERS"].keys():
if config["PHONE_DATA_YIELD"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=map(str.lower, config["PHONE_DATA_YIELD"]["SENSORS"])))
files_to_compute.extend(expand("data/interim/{pid}/phone_yielded_timestamps.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_yielded_timestamps_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_data_yield_features/phone_data_yield_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["PHONE_DATA_YIELD"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_data_yield.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
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 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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
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/interim/{pid}/phone_sensed_bins.csv", pid=config["PIDS"]))
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"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_calls_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_calls_with_datetime_unified.csv", pid=config["PIDS"]))
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
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",
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_SCREEN"]["PROVIDERS"].keys():
if config["PHONE_SCREEN"]["PROVIDERS"][provider]["COMPUTE"]:
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
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"],))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["PHONE_LOCATIONS"]["PROVIDERS"].keys():
if config["PHONE_LOCATIONS"]["PROVIDERS"][provider]["COMPUTE"]:
if config["PHONE_LOCATIONS"]["LOCATIONS_TO_USE"] == "FUSED_RESAMPLED":
if "PHONE_LOCATIONS" in config["PHONE_DATA_YIELD"]["SENSORS"]:
files_to_compute.extend(expand("data/interim/{pid}/phone_yielded_timestamps.csv", pid=config["PIDS"]))
else:
raise ValueError("Error: Add PHONE_LOCATIONS (and as many PHONE_SENSORS as you have) to [PHONE_DATA_YIELD][SENSORS] in config.yaml. This is necessary to compute phone_yielded_timestamps (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"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["FITBIT_HEARTRATE_SUMMARY"]["PROVIDERS"].keys():
if config["FITBIT_HEARTRATE_SUMMARY"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/fitbit_heartrate_summary_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_heartrate_summary_parsed.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_heartrate_summary_parsed_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/fitbit_heartrate_summary_features/fitbit_heartrate_summary_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["FITBIT_HEARTRATE_SUMMARY"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/fitbit_heartrate_summary.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["FITBIT_HEARTRATE_INTRADAY"]["PROVIDERS"].keys():
if config["FITBIT_HEARTRATE_INTRADAY"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/fitbit_heartrate_intraday_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_heartrate_intraday_parsed.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_heartrate_intraday_parsed_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/fitbit_heartrate_intraday_features/fitbit_heartrate_intraday_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["FITBIT_HEARTRATE_INTRADAY"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/fitbit_heartrate_intraday.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["FITBIT_SLEEP_SUMMARY"]["PROVIDERS"].keys():
if config["FITBIT_SLEEP_SUMMARY"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/fitbit_sleep_summary_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_sleep_summary_parsed.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_sleep_summary_parsed_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/fitbit_sleep_summary_features/fitbit_sleep_summary_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["FITBIT_SLEEP_SUMMARY"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/fitbit_sleep_summary.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["FITBIT_STEPS_SUMMARY"]["PROVIDERS"].keys():
if config["FITBIT_STEPS_SUMMARY"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/fitbit_steps_summary_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_steps_summary_parsed.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_steps_summary_parsed_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/fitbit_steps_summary_features/fitbit_steps_summary_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["FITBIT_STEPS_SUMMARY"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/fitbit_steps_summary.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
for provider in config["FITBIT_STEPS_INTRADAY"]["PROVIDERS"].keys():
if config["FITBIT_STEPS_INTRADAY"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/fitbit_steps_intraday_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_steps_intraday_parsed.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/fitbit_steps_intraday_parsed_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/fitbit_steps_intraday_features/fitbit_steps_intraday_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["FITBIT_STEPS_INTRADAY"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/fitbit_steps_intraday.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"]))
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
# Analysis Workflow Example
models, scalers = [], []
for model_name in config["PARAMS_FOR_ANALYSIS"]["MODEL_NAMES"]:
models = models + [model_name] * len(config["PARAMS_FOR_ANALYSIS"]["MODEL_SCALER"][model_name])
scalers = scalers + config["PARAMS_FOR_ANALYSIS"]["MODEL_SCALER"][model_name]
results = config["PARAMS_FOR_ANALYSIS"]["RESULT_COMPONENTS"]
# Demographic features
files_to_compute.extend(expand("data/raw/{pid}/participant_info_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/features/{pid}/demographic_features.csv", pid=config["PIDS"]))
# Targets
files_to_compute.extend(expand("data/raw/{pid}/participant_target_raw.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/participant_target_with_datetime.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/targets/{pid}/parsed_targets.csv", pid=config["PIDS"]))
# Individual model
files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features_cleaned.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/models/individual_model/{pid}/input.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/models/individual_model/{pid}/output_{cv_method}/baselines.csv", pid=config["PIDS"], cv_method=config["PARAMS_FOR_ANALYSIS"]["CV_METHODS"]))
files_to_compute.extend(expand(
expand("data/processed/models/individual_model/{pid}/output_{cv_method}/{{model}}/{{scaler}}/{result}.csv",
pid=config["PIDS"],
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"]))
cv_method=config["PARAMS_FOR_ANALYSIS"]["CV_METHODS"],
result = results),
zip,
model=models,
scaler=scalers))
if config["MESSAGES"]["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/processed/{pid}/messages_{messages_type}_{day_segment}.csv", pid=config["PIDS"], messages_type = config["MESSAGES"]["TYPES"], day_segment = config["MESSAGES"]["DAY_SEGMENTS"]))
# Population model
files_to_compute.append("data/processed/features/all_participants/all_sensor_features_cleaned.csv")
files_to_compute.append("data/processed/models/population_model/input.csv")
files_to_compute.extend(expand("data/processed/models/population_model/output_{cv_method}/baselines.csv", cv_method=config["PARAMS_FOR_ANALYSIS"]["CV_METHODS"]))
files_to_compute.extend(expand(
expand("data/processed/models/population_model/output_{cv_method}/{{model}}/{{scaler}}/{result}.csv",
cv_method=config["PARAMS_FOR_ANALYSIS"]["CV_METHODS"],
result = results),
zip,
model=models,
scaler=scalers))
if config["CALLS"]["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/processed/{pid}/calls_{call_type}_{day_segment}.csv", pid=config["PIDS"], call_type=config["CALLS"]["TYPES"], day_segment = config["CALLS"]["DAY_SEGMENTS"]))
if config["BARNETT_LOCATION"]["COMPUTE"]:
if config["BARNETT_LOCATION"]["LOCATIONS_TO_USE"] == "RESAMPLE_FUSED":
if config["BARNETT_LOCATION"]["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"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_resampled.csv", pid=config["PIDS"], sensor=config["BARNETT_LOCATION"]["DB_TABLE"]))
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}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["BARNETT_LOCATION"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["BARNETT_LOCATION"]["DB_TABLE"]))
files_to_compute.extend(expand("data/processed/{pid}/location_barnett_{day_segment}.csv", pid=config["PIDS"], day_segment = config["BARNETT_LOCATION"]["DAY_SEGMENTS"]))
if config["BLUETOOTH"]["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/processed/{pid}/bluetooth_{day_segment}.csv", pid=config["PIDS"], day_segment = config["BLUETOOTH"]["DAY_SEGMENTS"]))
if config["ACTIVITY_RECOGNITION"]["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["ACTIVITY_RECOGNITION"]["DB_TABLE"]["ANDROID"], config["ACTIVITY_RECOGNITION"]["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/processed/{pid}/{sensor}_deltas.csv", pid=pids, sensor=table))
files_to_compute.extend(expand("data/processed/{pid}/activity_recognition_{day_segment}.csv",pid=config["PIDS"], day_segment = config["ACTIVITY_RECOGNITION"]["DAY_SEGMENTS"]))
if config["BATTERY"]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["BATTERY"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["BATTERY"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime_unified.csv", pid=config["PIDS"], sensor=config["BATTERY"]["DB_TABLE"]))
files_to_compute.extend(expand("data/processed/{pid}/battery_deltas.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/{pid}/battery_{day_segment}.csv", pid = config["PIDS"], day_segment = config["BATTERY"]["DAY_SEGMENTS"]))
if config["SCREEN"]["COMPUTE"]:
if config["SCREEN"]["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 screen 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)")
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["SCREEN"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["SCREEN"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime_unified.csv", pid=config["PIDS"], sensor=config["SCREEN"]["DB_TABLE"]))
files_to_compute.extend(expand("data/processed/{pid}/screen_deltas.csv", pid=config["PIDS"]))
files_to_compute.extend(expand("data/processed/{pid}/screen_{day_segment}.csv", pid = config["PIDS"], day_segment = config["SCREEN"]["DAY_SEGMENTS"]))
if config["LIGHT"]["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/processed/{pid}/light_{day_segment}.csv", pid = config["PIDS"], day_segment = config["LIGHT"]["DAY_SEGMENTS"]))
if config["ACCELEROMETER"]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["ACCELEROMETER"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["ACCELEROMETER"]["DB_TABLE"]))
files_to_compute.extend(expand("data/processed/{pid}/accelerometer_{day_segment}.csv", pid = config["PIDS"], day_segment = config["ACCELEROMETER"]["DAY_SEGMENTS"]))
if config["APPLICATIONS_FOREGROUND"]["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/interim/{pid}/{sensor}_with_datetime_with_genre.csv", pid=config["PIDS"], sensor=config["APPLICATIONS_FOREGROUND"]["DB_TABLE"]))
files_to_compute.extend(expand("data/processed/{pid}/applications_foreground_{day_segment}.csv", pid = config["PIDS"], day_segment = config["APPLICATIONS_FOREGROUND"]["DAY_SEGMENTS"]))
if config["WIFI"]["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/processed/{pid}/wifi_{day_segment}.csv", pid = config["PIDS"], day_segment = config["WIFI"]["DAY_SEGMENTS"]))
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/processed/{pid}/wifi_{day_segment}.csv", pid = config["PIDS"], day_segment = config["WIFI"]["DAY_SEGMENTS"]))
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"]))
if config["CONVERSATION"]["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/processed/{pid}/conversation_{day_segment}.csv",pid=config["PIDS"], day_segment = config["CONVERSATION"]["DAY_SEGMENTS"]))
if config["DORYAB_LOCATION"]["COMPUTE"]:
if config["DORYAB_LOCATION"]["LOCATIONS_TO_USE"] == "RESAMPLE_FUSED":
if config["DORYAB_LOCATION"]["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"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_resampled.csv", pid=config["PIDS"], sensor=config["DORYAB_LOCATION"]["DB_TABLE"]))
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}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["DORYAB_LOCATION"]["DB_TABLE"]))
files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["DORYAB_LOCATION"]["DB_TABLE"]))
files_to_compute.extend(expand("data/processed/{pid}/location_doryab_{segment}.csv", pid=config["PIDS"], segment = config["DORYAB_LOCATION"]["DAY_SEGMENTS"]))
# 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"]))
# analysis example
if config["PARAMS_FOR_ANALYSIS"]["COMPUTE"]:
rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"]
cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"]
models, scalers, rows_nan_thresholds, cols_nan_thresholds = [], [], [], []
for model_name in config["PARAMS_FOR_ANALYSIS"]["MODEL_NAMES"]:
models = models + [model_name] * len(config["PARAMS_FOR_ANALYSIS"]["MODEL_SCALER"][model_name]) * len(rows_nan_threshold)
scalers = scalers + config["PARAMS_FOR_ANALYSIS"]["MODEL_SCALER"][model_name] * len(rows_nan_threshold)
rows_nan_thresholds = rows_nan_thresholds + list(itertools.chain.from_iterable([threshold] * len(config["PARAMS_FOR_ANALYSIS"]["MODEL_SCALER"][model_name]) for threshold in rows_nan_threshold))
cols_nan_thresholds = cols_nan_thresholds + list(itertools.chain.from_iterable([threshold] * len(config["PARAMS_FOR_ANALYSIS"]["MODEL_SCALER"][model_name]) for threshold in cols_nan_threshold))
results = config["PARAMS_FOR_ANALYSIS"]["RESULT_COMPONENTS"] + ["merged_population_model_results"]
files_to_compute.extend(expand("data/processed/{pid}/data_for_individual_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{source}_{day_segment}_original.csv",
pid = config["PIDS"],
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"],
source = config["PARAMS_FOR_ANALYSIS"]["SOURCES"],
day_segment = config["PARAMS_FOR_ANALYSIS"]["DAY_SEGMENTS"]))
files_to_compute.extend(expand("data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{source}_{day_segment}_original.csv",
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"],
source = config["PARAMS_FOR_ANALYSIS"]["SOURCES"],
day_segment = config["PARAMS_FOR_ANALYSIS"]["DAY_SEGMENTS"]))
files_to_compute.extend(expand(
expand("data/processed/{pid}/data_for_individual_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_clean.csv",
pid = config["PIDS"],
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"],
days_before_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_BEFORE_THRESHOLD"],
days_after_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_AFTER_THRESHOLD"],
cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
source = config["PARAMS_FOR_ANALYSIS"]["SOURCES"],
day_segment = config["PARAMS_FOR_ANALYSIS"]["DAY_SEGMENTS"]),
zip,
rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"],
cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"]))
files_to_compute.extend(expand(
expand("data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_clean.csv",
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"],
days_before_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_BEFORE_THRESHOLD"],
days_after_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_AFTER_THRESHOLD"],
cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
source = config["PARAMS_FOR_ANALYSIS"]["SOURCES"],
day_segment = config["PARAMS_FOR_ANALYSIS"]["DAY_SEGMENTS"]),
zip,
rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"],
cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"]))
files_to_compute.extend(expand("data/processed/data_for_population_model/demographic_features.csv"))
files_to_compute.extend(expand("data/processed/data_for_population_model/targets_{summarised}.csv",
summarised = config["PARAMS_FOR_ANALYSIS"]["SUMMARISED"]))
files_to_compute.extend(expand(
expand("data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_nancellsratio.csv",
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"],
days_before_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_BEFORE_THRESHOLD"],
days_after_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_AFTER_THRESHOLD"],
cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
source = config["PARAMS_FOR_ANALYSIS"]["SOURCES"],
day_segment = config["PARAMS_FOR_ANALYSIS"]["DAY_SEGMENTS"]),
zip,
rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"],
cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"]))
files_to_compute.extend(expand(
expand("data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}.csv",
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"],
days_before_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_BEFORE_THRESHOLD"],
days_after_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_AFTER_THRESHOLD"],
cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
source = config["PARAMS_FOR_ANALYSIS"]["SOURCES"],
day_segment = config["PARAMS_FOR_ANALYSIS"]["DAY_SEGMENTS"],
summarised = config["PARAMS_FOR_ANALYSIS"]["SUMMARISED"]),
zip,
rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"],
cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"]))
files_to_compute.extend(expand(
expand("data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/baseline/{cv_method}/{source}_{day_segment}_{summarised}.csv",
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"],
days_before_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_BEFORE_THRESHOLD"],
days_after_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_AFTER_THRESHOLD"],
cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
cv_method = config["PARAMS_FOR_ANALYSIS"]["CV_METHODS"],
source = config["PARAMS_FOR_ANALYSIS"]["SOURCES"],
day_segment = config["PARAMS_FOR_ANALYSIS"]["DAY_SEGMENTS"],
summarised = config["PARAMS_FOR_ANALYSIS"]["SUMMARISED"]),
zip,
rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"],
cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"]))
files_to_compute.extend(expand(
expand("data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{{rows_nan_threshold}}|{{cols_nan_threshold}}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{{model}}/{cv_method}/{source}_{day_segment}_{summarised}_{{scaler}}/{result}.csv",
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"],
days_before_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_BEFORE_THRESHOLD"],
days_after_threshold = config["PARAMS_FOR_ANALYSIS"]["PARTICIPANT_DAYS_AFTER_THRESHOLD"],
cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
cv_method = config["PARAMS_FOR_ANALYSIS"]["CV_METHODS"],
source = config["PARAMS_FOR_ANALYSIS"]["SOURCES"],
day_segment = config["PARAMS_FOR_ANALYSIS"]["DAY_SEGMENTS"],
summarised = config["PARAMS_FOR_ANALYSIS"]["SUMMARISED"],
result = results),
zip,
rows_nan_threshold = rows_nan_thresholds,
cols_nan_threshold = cols_nan_thresholds,
model = models,
scaler = scalers))
rule all:
input:

562
example_profile/example_config.yaml
View File

@ -1,313 +1,365 @@
# Participants to include in the analysis
# You must create a file for each participant named pXXX containing their device_id. This can be done manually or automatically
PIDS: [example01, example02]
# See https://www.rapids.science/setup/configuration/#database-credentials
DATABASE_GROUP: &database_group
RAPIDS_EXAMPLE
# Global var with common day segments
DAY_SEGMENTS: &day_segments
[daily]
# 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.
# See https://www.rapids.science/setup/configuration/#timezone-of-your-study
TIMEZONE: &timezone
America/New_York
DATABASE_GROUP: &database_group
MY_GROUP
# See https://www.rapids.science/setup/configuration/#participant-files
PIDS: [t01, t02]
DOWNLOAD_PARTICIPANTS:
IGNORED_DEVICE_IDS: [] # for example "5a1dd68c-6cd1-48fe-ae1e-14344ac5215f"
GROUP: *database_group
# 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: []
# Download data config
DOWNLOAD_DATASET:
GROUP: *database_group
# See https://www.rapids.science/setup/configuration/#day-segments
DAY_SEGMENTS: &day_segments
TYPE: PERIODIC # FREQUENCY, PERIODIC, EVENT
FILE: "example_profile/exampleworkflow_daysegments.csv"
INCLUDE_PAST_PERIODIC_SEGMENTS: FALSE # Only relevant if TYPE=PERIODIC, see docs
# Readable datetime config
READABLE_DATETIME:
FIXED_TIMEZONE: *timezone
# See https://www.rapids.science/setup/configuration/#device-data-source-configuration
DEVICE_DATA:
PHONE:
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
FITBIT:
SOURCE:
TYPE: DATABASE # DATABASE or FILES (set each FITBIT_SENSOR TABLE attribute accordingly with a table name or a file path)
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
PHONE_VALID_SENSED_BINS:
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 sensor tables 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's location features, screen and locations tables are mandatory.
DB_TABLES: [messages, calls, locations, plugin_google_activity_recognition, plugin_ios_activity_recognition, battery, screen, light, applications_foreground, plugin_studentlife_audio_android, plugin_studentlife_audio, wifi, sensor_wifi, bluetooth, applications_notifications, aware_log, ios_status_monitor, push_notification, significant, timezone, touch, keyboard]
############## PHONE ###########################################################
################################################################################
PHONE_VALID_SENSED_DAYS:
COMPUTE: False
MIN_VALID_HOURS_PER_DAY: &min_valid_hours_per_day [16, 20] # (out of 24) MIN_HOURS_PER_DAY
MIN_VALID_BINS_PER_HOUR: &min_valid_bins_per_hour [12] # (out of 60min/BIN_SIZE bins)
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
# Communication SMS features config, TYPES and FEATURES keys need to match
MESSAGES:
COMPUTE: True
DB_TABLE: messages
TYPES : [received, sent]
FEATURES:
received: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
sent: [count, distinctcontacts, timefirstmessage, timelastmessage, countmostfrequentcontact]
DAY_SEGMENTS: *day_segments
PHONE_MESSAGES:
TABLE: messages
PROVIDERS:
RAPIDS:
COMPUTE: True
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
# Communication call features config, TYPES and FEATURES keys need to match
CALLS:
COMPUTE: True
DB_TABLE: calls
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]
DAY_SEGMENTS: *day_segments
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
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_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"
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: 720 # minutes, only replicate location samples to consecutive sensed bins if they were logged within this threshold after a valid location row
TIMEZONE: *timezone
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"
BARNETT_LOCATION:
COMPUTE: False
DB_TABLE: locations
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
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
PHONE_BLUETOOTH:
TABLE: bluetooth
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_bluetooth
SRC_LANGUAGE: "r"
DORYAB_LOCATION:
COMPUTE: True
DB_TABLE: locations
DAY_SEGMENTS: *day_segments
FEATURES: ["locationvariance","loglocationvariance","totaldistance","averagespeed","varspeed","circadianmovement","numberofsignificantplaces","numberlocationtransitions","radiusgyration","timeattop1location","timeattop2location","timeattop3location","movingtostaticratio","outlierstimepercent","maxlengthstayatclusters","minlengthstayatclusters","meanlengthstayatclusters","stdlengthstayatclusters","locationentropy","normalizedlocationentropy"]
LOCATIONS_TO_USE: RESAMPLE_FUSED # ALL, ALL_EXCEPT_FUSED OR RESAMPLE_FUSED
DBSCAN_EPS: 10 # meters
DBSCAN_MINSAMPLES: 5
THRESHOLD_STATIC : 1 # km/h
MAXIMUM_GAP_ALLOWED: 300
MINUTES_DATA_USED: False
BLUETOOTH:
COMPUTE: True
DB_TABLE: bluetooth
DAY_SEGMENTS: *day_segments
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
ACTIVITY_RECOGNITION:
COMPUTE: True
DB_TABLE:
PHONE_ACTIVITY_RECOGNITION:
TABLE:
ANDROID: plugin_google_activity_recognition
IOS: plugin_ios_activity_recognition
DAY_SEGMENTS: *day_segments
FEATURES: ["count","mostcommonactivity","countuniqueactivities","activitychangecount","sumstationary","summobile","sumvehicle"]
EPISODE_THRESHOLD_BETWEEN_ROWS: 5 # minutes. Max time difference for two consecutive rows to be considered within the same battery episode.
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"
BATTERY:
COMPUTE: True
DB_TABLE: battery
DAY_SEGMENTS: *day_segments
FEATURES: ["countdischarge", "sumdurationdischarge", "countcharge", "sumdurationcharge", "avgconsumptionrate", "maxconsumptionrate"]
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"
SCREEN:
COMPUTE: True
DB_TABLE: screen
DAY_SEGMENTS: *day_segments
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_DELTAS: ["countepisode", "episodepersensedminutes", "sumduration", "maxduration", "minduration", "avgduration", "stdduration", "firstuseafter"]
EPISODE_TYPES: ["unlock"]
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"
LIGHT:
COMPUTE: True
DB_TABLE: light
DAY_SEGMENTS: *day_segments
FEATURES: ["count", "maxlux", "minlux", "avglux", "medianlux", "stdlux"]
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"
ACCELEROMETER:
COMPUTE: False
DB_TABLE: accelerometer
DAY_SEGMENTS: *day_segments
FEATURES:
MAGNITUDE: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
EXERTIONAL_ACTIVITY_EPISODE: ["sumduration", "maxduration", "minduration", "avgduration", "medianduration", "stdduration"]
NONEXERTIONAL_ACTIVITY_EPISODE: ["sumduration", "maxduration", "minduration", "avgduration", "medianduration", "stdduration"]
VALID_SENSED_MINUTES: True
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"
APPLICATIONS_FOREGROUND:
COMPUTE: True
DB_TABLE: applications_foreground
DAY_SEGMENTS: *day_segments
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"]
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: 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"
HEARTRATE:
COMPUTE: True
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"]
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"
STEP:
COMPUTE: True
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
PHONE_WIFI_CONNECTED:
TABLE: "sensor_wifi"
PROVIDERS:
RAPIDS:
COMPUTE: True
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
SRC_FOLDER: "rapids" # inside src/features/phone_wifi_connected
SRC_LANGUAGE: "r"
SLEEP:
COMPUTE: True
DB_TABLE: fitbit_data
DAY_SEGMENTS: *day_segments
SLEEP_TYPES: ["main", "nap", "all"]
SUMMARY_FEATURES: ["sumdurationafterwakeup", "sumdurationasleep", "sumdurationawake", "sumdurationtofallasleep", "sumdurationinbed", "avgefficiency", "countepisode"]
WIFI:
COMPUTE: True
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 ""
DAY_SEGMENTS: *day_segments
FEATURES: ["countscans", "uniquedevices", "countscansmostuniquedevice"]
CONVERSATION:
COMPUTE: True
DB_TABLE:
PHONE_CONVERSATION:
TABLE:
ANDROID: plugin_studentlife_audio_android
IOS: plugin_studentlife_audio
DAY_SEGMENTS: *day_segments
FEATURES: ["minutessilence", "minutesnoise", "minutesvoice", "minutesunknown","sumconversationduration","avgconversationduration",
"sdconversationduration","minconversationduration","maxconversationduration","timefirstconversation","timelastconversation","sumenergy",
"avgenergy","sdenergy","minenergy","maxenergy","silencesensedfraction","noisesensedfraction",
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"]
RECORDINGMINUTES: 1
PAUSEDMINUTES : 3
RECORDING_MINUTES: 1
PAUSED_MINUTES : 3
SRC_FOLDER: "rapids" # inside src/features/phone_conversation
SRC_LANGUAGE: "python"
### Visualizations ################################################################
HEATMAP_FEATURES_CORRELATIONS:
PLOT: True
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: [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"}
############## FITBIT ##########################################################
################################################################################
HISTOGRAM_VALID_SENSED_HOURS:
PLOT: True
MIN_VALID_HOURS_PER_DAY: *min_valid_hours_per_day
MIN_VALID_BINS_PER_HOUR: *min_valid_bins_per_hour
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"
HEATMAP_DAYS_BY_SENSORS:
PLOT: True
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: [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]
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_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"
HEATMAP_SENSED_BINS:
PLOT: True
BIN_SIZE: *bin_size
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"
OVERALL_COMPLIANCE_HEATMAP:
PLOT: True
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
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"
### Analysis Workflow Example ##################################################
################################################################################
### Example Analysis ################################################################
PARAMS_FOR_ANALYSIS:
COMPUTE: True
GROUNDTRUTH_TABLE: participant_info
TARGET_TABLE: participant_target
SOURCES: &sources ["phone_features", "fitbit_features", "phone_fitbit_features"]
DAY_SEGMENTS: *day_segments
PHONE_FEATURES: [activity_recognition, applications_foreground, battery, bluetooth, calls_incoming, calls_missed, calls_outgoing, conversation, light, location_doryab, messages_received, messages_sent, screen, wifi]
FITBIT_FEATURES: [fitbit_heartrate, fitbit_step, fitbit_sleep]
PHONE_FITBIT_FEATURES: "" # This array is merged in the input_merge_features_of_single_participant function in models.snakefile
DEMOGRAPHIC_FEATURES: [age, gender, inpatientdays]
CATEGORICAL_DEMOGRAPHIC_FEATURES: ["gender"]
FEATURES_EXCLUDE_DAY_IDX: True
CATEGORICAL_OPERATORS: [mostcommon]
# 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: 6 #15
DAYS_IN_HOSPITAL: F # T or F
DAYS_AFTER_DISCHARGE: 5 #7
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
# Cleaning Parameters
COLS_NAN_THRESHOLD: [0.1, 0.3]
COLS_NAN_THRESHOLD: 0.3
COLS_VAR_THRESHOLD: True
ROWS_NAN_THRESHOLD: [0.1, 0.3]
PARTICIPANT_DAYS_BEFORE_THRESHOLD: 3
PARTICIPANT_DAYS_AFTER_THRESHOLD: 3
# Extract summarised features from daily features with any of the following substrings
NUMERICAL_OPERATORS: ["count", "sum", "length", "avg", "restinghr"]
CATEGORICAL_OPERATORS: ["mostcommon"]
MODEL_NAMES: ["LogReg", "kNN", "SVM", "DT", "RF", "GB", "XGBoost", "LightGBM"]
CV_METHODS: ["LeaveOneOut"]
SUMMARISED: ["notsummarised"] # "summarised" or "notsummarised"
RESULT_COMPONENTS: ["fold_predictions", "fold_metrics", "overall_results", "fold_feature_importances"]
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]
MODEL_SCALER:
LogReg: ["notnormalized", "minmaxscaler", "standardscaler", "robustscaler"]
kNN: ["minmaxscaler", "standardscaler", "robustscaler"]
SVM: ["minmaxscaler", "standardscaler", "robustscaler"]
DT: ["notnormalized"]
RF: ["notnormalized"]
GB: ["notnormalized"]
XGBoost: ["notnormalized"]
LightGBM: ["notnormalized"]
LogReg: [notnormalized, minmaxscaler, standardscaler, robustscaler]
kNN: [minmaxscaler, standardscaler, robustscaler]
SVM: [minmaxscaler, standardscaler, robustscaler]
DT: [notnormalized]
RF: [notnormalized]
GB: [notnormalized]
XGBoost: [notnormalized]
LightGBM: [notnormalized]
MODEL_HYPERPARAMS:
LogReg:
{"clf__C": [0.01, 0.1, 1, 10, 100], "clf__solver": ["newton-cg", "lbfgs", "liblinear", "saga"], "clf__penalty": ["l2"]}
kNN:
{"clf__n_neighbors": [1, 3, 5], "clf__weights": ["uniform", "distance"], "clf__metric": ["euclidean", "manhattan", "minkowski"]}
{"clf__n_neighbors": [3, 5, 7], "clf__weights": ["uniform", "distance"], "clf__metric": ["euclidean", "manhattan", "minkowski"]}
SVM:
{"clf__C": [0.01, 0.1, 1, 10, 100], "clf__gamma": ["scale", "auto"], "clf__kernel": ["rbf", "poly", "sigmoid"]}
DT:
{"clf__criterion": ["gini", "entropy"], "clf__max_depth": [null, 3, 5, 7, 9], "clf__max_features": [null, "auto", "sqrt", "log2"]}
{"clf__criterion": ["gini", "entropy"], "clf__max_depth": [null, 3, 7, 15], "clf__max_features": [null, "auto", "sqrt", "log2"]}
RF:
{"clf__n_estimators": [2, 5, 10, 100],"clf__max_depth": [null, 3, 5, 7, 9]}
{"clf__n_estimators": [10, 100, 200],"clf__max_depth": [null, 3, 7, 15]}
GB:
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [5, 10, 100, 200], "clf__subsample": [0.5, 0.7, 1.0], "clf__max_depth": [3, 5, 7, 9]}
{"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]}
XGBoost:
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [5, 10, 100, 200], "clf__num_leaves": [5, 16, 31, 62]}
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [10, 100, 200], "clf__max_depth": [3, 5, 7]}
LightGBM:
{"clf__learning_rate": [0.01, 0.1, 1], "clf__n_estimators": [5, 10, 100, 200], "clf__num_leaves": [5, 16, 31, 62]}
{"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]}

2
example_profile/exampleworkflow_daysegments.csv 100644
View File

@ -0,0 +1,2 @@
label,start_time,length,repeats_on,repeats_value
daily,00:00:00,23H 59M 59S,every_day,0
1 label start_time length repeats_on repeats_value
2 daily 00:00:00 23H 59M 59S every_day 0

33
rules/common.smk
View File

@ -28,30 +28,15 @@ def optional_steps_sleep_input(wildcards):
else:
return []
# Models.smk ###########################################################################################################
def input_merge_features_of_single_participant(wildcards):
if wildcards.source == "phone_fitbit_features":
return expand("data/processed/{pid}/{features}_{day_segment}.csv", pid=wildcards.pid, features=config["PARAMS_FOR_ANALYSIS"]["PHONE_FEATURES"] + config["PARAMS_FOR_ANALYSIS"]["FITBIT_FEATURES"], day_segment=wildcards.day_segment)
else:
return expand("data/processed/{pid}/{features}_{day_segment}.csv", pid=wildcards.pid, features=config["PARAMS_FOR_ANALYSIS"][wildcards.source.upper()], day_segment=wildcards.day_segment)
def optional_input_days_to_include(wildcards):
if config["PARAMS_FOR_ANALYSIS"]["DAYS_TO_ANALYSE"]["ENABLED"]:
# This input automatically trigers the rule days_to_analyse in mystudy.snakefile
return ["data/interim/{pid}/days_to_analyse" + \
"_" + str(config["PARAMS_FOR_ANALYSIS"]["DAYS_TO_ANALYSE"]["DAYS_BEFORE_SURGERY"]) + \
"_" + str(config["PARAMS_FOR_ANALYSIS"]["DAYS_TO_ANALYSE"]["DAYS_IN_HOSPITAL"]) + \
"_" + str(config["PARAMS_FOR_ANALYSIS"]["DAYS_TO_ANALYSE"]["DAYS_AFTER_DISCHARGE"]) + ".csv"]
else:
return []
def optional_input_valid_sensed_days(wildcards):
if config["PARAMS_FOR_ANALYSIS"]["DROP_VALID_SENSED_DAYS"]["ENABLED"]:
# This input automatically trigers the rule phone_valid_sensed_days in preprocessing.snakefile
return ["data/interim/{pid}/phone_valid_sensed_days_{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins.csv"]
else:
return []
def input_merge_sensor_features_for_individual_participants(wildcards):
feature_files = []
for config_key in config.keys():
if config_key.startswith(("PHONE", "FITBIT")) and "PROVIDERS" in config[config_key]:
for provider_key, provider in config[config_key]["PROVIDERS"].items():
if "COMPUTE" in provider.keys() and provider["COMPUTE"]:
feature_files.append("data/processed/features/{pid}/" + config_key.lower() + ".csv")
break
return feature_files
# Reports.smk ###########################################################################################################

33
rules/features.smk
View File

@ -1,10 +1,12 @@
rule join_features_from_providers:
input:
location_features = find_features_files
sensor_features = find_features_files
wildcard_constraints:
sensor_key = '(phone|fitbit).*'
output:
"data/processed/features/{pid}/{sensor_key}.csv"
script:
"../src/features/join_features_from_providers.R"
"../src/features/utils/join_features_from_providers.R"
rule phone_data_yield_python_features:
input:
@ -528,15 +530,18 @@ rule fitbit_sleep_summary_r_features:
script:
"../src/features/entry.R"
# rule fitbit_sleep_features:
# input:
# sleep_summary_data = "data/raw/{pid}/fitbit_sleep_summary_with_datetime.csv",
# sleep_intraday_data = "data/raw/{pid}/fitbit_sleep_intraday_with_datetime.csv"
# params:
# day_segment = "{day_segment}",
# summary_features = config["SLEEP"]["SUMMARY_FEATURES"],
# sleep_types = config["SLEEP"]["SLEEP_TYPES"]
# output:
# "data/processed/{pid}/fitbit_sleep_{day_segment}.csv"
# script:
# "../src/features/fitbit_sleep_features.py"
rule merge_sensor_features_for_individual_participants:
input:
feature_files = input_merge_sensor_features_for_individual_participants
output:
"data/processed/features/{pid}/all_sensor_features.csv"
script:
"../src/features/utils/merge_sensor_features_for_individual_participants.R"
rule merge_sensor_features_for_all_participants:
input:
feature_files = expand("data/processed/features/{pid}/all_sensor_features.csv", pid=config["PIDS"])
output:
"data/processed/features/all_participants/all_sensor_features.csv"
script:
"../src/features/utils/merge_sensor_features_for_all_participants.R"

248
rules/models.smk
View File

@ -1,174 +1,174 @@
ruleorder: nan_cells_ratio_of_cleaned_features > merge_features_and_targets
rule days_to_analyse:
rule download_demographic_data:
input:
participant_info = "data/raw/{pid}/" + config["PARAMS_FOR_ANALYSIS"]["GROUNDTRUTH_TABLE"] + "_raw.csv"
participant_file = "data/external/participant_files/{pid}.yaml"
params:
days_before_surgery = "{days_before_surgery}",
days_in_hospital = "{days_in_hospital}",
days_after_discharge= "{days_after_discharge}"
source = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC"]["SOURCE"],
table = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC"]["TABLE"],
output:
"data/interim/{pid}/days_to_analyse_{days_before_surgery}_{days_in_hospital}_{days_after_discharge}.csv"
"data/raw/{pid}/participant_info_raw.csv"
script:
"../src/models/select_days_to_analyse.py"
rule targets:
input:
participant_info = "data/raw/{pid}/" + config["PARAMS_FOR_ANALYSIS"]["TARGET_TABLE"] + "_raw.csv"
params:
pid = "{pid}",
summarised = "{summarised}"
output:
"data/processed/{pid}/targets_{summarised}.csv"
script:
"../src/models/targets.py"
"../src/data/workflow_example/download_demographic_data.R"
rule demographic_features:
input:
participant_info = "data/raw/{pid}/" + config["PARAMS_FOR_ANALYSIS"]["GROUNDTRUTH_TABLE"] + "_raw.csv"
participant_info = "data/raw/{pid}/participant_info_raw.csv"
params:
pid = "{pid}",
features = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC_FEATURES"]
features = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC"]["FEATURES"]
output:
"data/processed/{pid}/demographic_features.csv"
"data/processed/features/{pid}/demographic_features.csv"
script:
"../src/features/demographic_features.py"
"../src/features/workflow_example/demographic_features.py"
rule merge_features_for_individual_model:
rule download_target_data:
input:
feature_files = input_merge_features_of_single_participant,
phone_valid_sensed_days = optional_input_valid_sensed_days,
days_to_include = optional_input_days_to_include
participant_file = "data/external/participant_files/{pid}.yaml"
params:
source = "{source}"
source = config["PARAMS_FOR_ANALYSIS"]["TARGET"]["SOURCE"],
table = config["PARAMS_FOR_ANALYSIS"]["TARGET"]["TABLE"],
output:
"data/processed/{pid}/data_for_individual_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{source}_{day_segment}_original.csv"
"data/raw/{pid}/participant_target_raw.csv"
script:
"../src/models/merge_features_for_individual_model.R"
"../src/data/workflow_example/download_target_data.R"
rule merge_features_for_population_model:
rule target_readable_datetime:
input:
feature_files = expand("data/processed/{pid}/data_for_individual_model/{{min_valid_hours_per_day}}hours_{{min_valid_bins_per_hour}}bins/{{source}}_{{day_segment}}_original.csv", pid=config["PIDS"])
output:
"data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{source}_{day_segment}_original.csv"
script:
"../src/models/merge_features_for_population_model.R"
rule merge_demographicfeatures_for_population_model:
input:
data_files = expand("data/processed/{pid}/demographic_features.csv", pid=config["PIDS"])
output:
"data/processed/data_for_population_model/demographic_features.csv"
script:
"../src/models/merge_data_for_population_model.py"
rule merge_targets_for_population_model:
input:
data_files = expand("data/processed/{pid}/targets_{{summarised}}.csv", pid=config["PIDS"])
output:
"data/processed/data_for_population_model/targets_{summarised}.csv"
script:
"../src/models/merge_data_for_population_model.py"
rule clean_features_for_individual_model:
input:
rules.merge_features_for_individual_model.output
sensor_input = "data/raw/{pid}/participant_target_raw.csv",
day_segments = "data/interim/day_segments/{pid}_day_segments.csv"
params:
features_exclude_day_idx = config["PARAMS_FOR_ANALYSIS"]["FEATURES_EXCLUDE_DAY_IDX"],
cols_nan_threshold = "{cols_nan_threshold}",
cols_var_threshold = "{cols_var_threshold}",
days_before_threshold = "{days_before_threshold}",
days_after_threshold = "{days_after_threshold}",
rows_nan_threshold = "{rows_nan_threshold}",
fixed_timezone = config["PARAMS_FOR_ANALYSIS"]["TARGET"]["SOURCE"]["TIMEZONE"],
day_segments_type = config["DAY_SEGMENTS"]["TYPE"],
include_past_periodic_segments = config["DAY_SEGMENTS"]["INCLUDE_PAST_PERIODIC_SEGMENTS"]
output:
"data/processed/{pid}/data_for_individual_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_clean.csv"
"data/raw/{pid}/participant_target_with_datetime.csv"
script:
"../src/models/clean_features_for_model.R"
"../src/data/readable_datetime.R"
rule clean_features_for_population_model:
rule parse_targets:
input:
rules.merge_features_for_population_model.output
params:
features_exclude_day_idx = config["PARAMS_FOR_ANALYSIS"]["FEATURES_EXCLUDE_DAY_IDX"],
cols_nan_threshold = "{cols_nan_threshold}",
cols_var_threshold = "{cols_var_threshold}",
days_before_threshold = "{days_before_threshold}",
days_after_threshold = "{days_after_threshold}",
rows_nan_threshold = "{rows_nan_threshold}",
targets = "data/raw/{pid}/participant_target_with_datetime.csv",
day_segments_labels = "data/interim/day_segments/{pid}_day_segments_labels.csv"
output:
"data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_clean.csv"
"data/processed/targets/{pid}/parsed_targets.csv"
script:
"../src/models/clean_features_for_model.R"
"../src/models/workflow_example/parse_targets.py"
rule nan_cells_ratio_of_cleaned_features:
rule clean_sensor_features_for_individual_participants:
input:
cleaned_features = "data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_clean.csv"
output:
"data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_nancellsratio.csv"
script:
"../src/models/nan_cells_ratio_of_cleaned_features.py"
rule merge_features_and_targets:
input:
cleaned_features = "data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_clean.csv",
demographic_features = "data/processed/data_for_population_model/demographic_features.csv",
targets = "data/processed/data_for_population_model/targets_{summarised}.csv",
rules.merge_sensor_features_for_individual_participants.output
params:
summarised = "{summarised}",
cols_var_threshold = "{cols_var_threshold}",
numerical_operators = config["PARAMS_FOR_ANALYSIS"]["NUMERICAL_OPERATORS"],
categorical_operators = config["PARAMS_FOR_ANALYSIS"]["CATEGORICAL_OPERATORS"],
features_exclude_day_idx = config["PARAMS_FOR_ANALYSIS"]["FEATURES_EXCLUDE_DAY_IDX"],
cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"],
cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"],
data_yielded_hours_ratio_threshold = config["PARAMS_FOR_ANALYSIS"]["DATA_YIELDED_HOURS_RATIO_THRESHOLD"],
output:
"data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}.csv"
"data/processed/features/{pid}/all_sensor_features_cleaned.csv"
script:
"../src/models/merge_features_and_targets.py"
rule baseline:
"../src/models/workflow_example/clean_sensor_features.R"
rule clean_sensor_features_for_all_participants:
input:
"data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}.csv"
rules.merge_sensor_features_for_all_participants.output
params:
cols_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_NAN_THRESHOLD"],
cols_var_threshold = config["PARAMS_FOR_ANALYSIS"]["COLS_VAR_THRESHOLD"],
rows_nan_threshold = config["PARAMS_FOR_ANALYSIS"]["ROWS_NAN_THRESHOLD"],
data_yielded_hours_ratio_threshold = config["PARAMS_FOR_ANALYSIS"]["DATA_YIELDED_HOURS_RATIO_THRESHOLD"],
output:
"data/processed/features/all_participants/all_sensor_features_cleaned.csv"
script:
"../src/models/workflow_example/clean_sensor_features.R"
rule merge_features_and_targets_for_individual_model:
input:
cleaned_sensor_features = "data/processed/features/{pid}/all_sensor_features_cleaned.csv",
targets = "data/processed/targets/{pid}/parsed_targets.csv",
output:
"data/processed/models/individual_model/{pid}/input.csv"
script:
"../src/models/workflow_example/merge_features_and_targets_for_individual_model.py"
rule merge_features_and_targets_for_population_model:
input:
cleaned_sensor_features = "data/processed/features/all_participants/all_sensor_features_cleaned.csv",
demographic_features = expand("data/processed/features/{pid}/demographic_features.csv", pid=config["PIDS"]),
targets = expand("data/processed/targets/{pid}/parsed_targets.csv", pid=config["PIDS"]),
output:
"data/processed/models/population_model/input.csv"
script:
"../src/models/workflow_example/merge_features_and_targets_for_population_model.py"
rule baselines_for_individual_model:
input:
"data/processed/models/individual_model/{pid}/input.csv"
params:
cv_method = "{cv_method}",
rowsnan_colsnan_days_colsvar_threshold = "{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}",
demographic_features = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC_FEATURES"]
colnames_demographic_features = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC"]["FEATURES"],
output:
"data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/baseline/{cv_method}/{source}_{day_segment}_{summarised}.csv"
"data/processed/models/individual_model/{pid}/output_{cv_method}/baselines.csv"
log:
"data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/baseline/{cv_method}/{source}_{day_segment}_{summarised}_notes.log"
"data/processed/models/individual_model/{pid}/output_{cv_method}/baselines_notes.log"
script:
"../src/models/baseline.py"
rule modeling:
"../src/models/workflow_example/baselines.py"
rule baselines_for_population_model:
input:
data = "data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_{summarised}.csv"
"data/processed/models/population_model/input.csv"
params:
cv_method = "{cv_method}",
colnames_demographic_features = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC"]["FEATURES"],
output:
"data/processed/models/population_model/output_{cv_method}/baselines.csv"
log:
"data/processed/models/population_model/output_{cv_method}/baselines_notes.log"
script:
"../src/models/workflow_example/baselines.py"
rule modeling_for_individual_participants:
input:
data = "data/processed/models/individual_model/{pid}/input.csv"
params:
model = "{model}",
cv_method = "{cv_method}",
source = "{source}",
day_segment = "{day_segment}",
summarised = "{summarised}",
scaler = "{scaler}",
categorical_operators = config["PARAMS_FOR_ANALYSIS"]["CATEGORICAL_OPERATORS"],
categorical_demographic_features = config["PARAMS_FOR_ANALYSIS"]["CATEGORICAL_DEMOGRAPHIC_FEATURES"],
categorical_demographic_features = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC"]["CATEGORICAL_FEATURES"],
model_hyperparams = config["PARAMS_FOR_ANALYSIS"]["MODEL_HYPERPARAMS"],
rowsnan_colsnan_days_colsvar_threshold = "{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}"
output:
fold_predictions = "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/fold_predictions.csv",
fold_metrics = "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/fold_metrics.csv",
overall_results = "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/overall_results.csv",
fold_feature_importances = "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/fold_feature_importances.csv"
fold_predictions = "data/processed/models/individual_model/{pid}/output_{cv_method}/{model}/{scaler}/fold_predictions.csv",
fold_metrics = "data/processed/models/individual_model/{pid}/output_{cv_method}/{model}/{scaler}/fold_metrics.csv",
overall_results = "data/processed/models/individual_model/{pid}/output_{cv_method}/{model}/{scaler}/overall_results.csv",
fold_feature_importances = "data/processed/models/individual_model/{pid}/output_{cv_method}/{model}/{scaler}/fold_feature_importances.csv"
log:
"data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/notes.log"
"data/processed/models/individual_model/{pid}/output_{cv_method}/{model}/{scaler}/notes.log"
script:
"../src/models/modeling.py"
"../src/models/workflow_example/modeling.py"
rule merge_population_model_results:
rule modeling_for_all_participants:
input:
overall_results = "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/overall_results.csv",
nan_cells_ratio = "data/processed/data_for_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{source}_{day_segment}_nancellsratio.csv",
baseline = "data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/baseline/{cv_method}/{source}_{day_segment}_{summarised}.csv"
data = "data/processed/models/population_model/input.csv"
params:
model = "{model}",
cv_method = "{cv_method}",
scaler = "{scaler}",
categorical_operators = config["PARAMS_FOR_ANALYSIS"]["CATEGORICAL_OPERATORS"],
categorical_demographic_features = config["PARAMS_FOR_ANALYSIS"]["DEMOGRAPHIC"]["CATEGORICAL_FEATURES"],
model_hyperparams = config["PARAMS_FOR_ANALYSIS"]["MODEL_HYPERPARAMS"],
output:
"data/processed/output_population_model/{min_valid_hours_per_day}hours_{min_valid_bins_per_hour}bins/{rows_nan_threshold}|{cols_nan_threshold}_{days_before_threshold}|{days_after_threshold}_{cols_var_threshold}/{model}/{cv_method}/{source}_{day_segment}_{summarised}_{scaler}/merged_population_model_results.csv"
fold_predictions = "data/processed/models/population_model/output_{cv_method}/{model}/{scaler}/fold_predictions.csv",
fold_metrics = "data/processed/models/population_model/output_{cv_method}/{model}/{scaler}/fold_metrics.csv",
overall_results = "data/processed/models/population_model/output_{cv_method}/{model}/{scaler}/overall_results.csv",
fold_feature_importances = "data/processed/models/population_model/output_{cv_method}/{model}/{scaler}/fold_feature_importances.csv"
log:
"data/processed/models/population_model/output_{cv_method}/{model}/{scaler}/notes.log"
script:
"../src/models/merge_population_model_results.py"
"../src/models/workflow_example/modeling.py"

22
src/data/workflow_example/download_demographic_data.R 100644
View File

@ -0,0 +1,22 @@
source("renv/activate.R")
library(RMySQL)
library("dplyr", warn.conflicts = F)
library(readr)
library(stringr)
library(yaml)
participant_file <- snakemake@input[["participant_file"]]
source <- snakemake@params[["source"]]
table <- snakemake@params[["table"]]
sensor_file <- snakemake@output[[1]]
participant <- read_yaml(participant_file)
record_id <- participant$PHONE$LABEL
dbEngine <- dbConnect(MySQL(), default.file = "./.env", group = source$DATABASE_GROUP)
query <- paste0("SELECT * FROM ", table, " WHERE record_id = '", record_id, "'")
sensor_data <- dbGetQuery(dbEngine, query)
dbDisconnect(dbEngine)
write_csv(sensor_data, sensor_file)

26
src/data/workflow_example/download_target_data.R 100644
View File

@ -0,0 +1,26 @@
source("renv/activate.R")
library(RMySQL)
library("dplyr", warn.conflicts = F)
library(readr)
library(stringr)
library(yaml)
library(lubridate)
participant_file <- snakemake@input[["participant_file"]]
source <- snakemake@params[["source"]]
table <- snakemake@params[["table"]]
sensor_file <- snakemake@output[[1]]
participant <- read_yaml(participant_file)
record_id <- participant$PHONE$LABEL
dbEngine <- dbConnect(MySQL(), default.file = "./.env", group = source$DATABASE_GROUP)
query <- paste0("SELECT * FROM ", table, " WHERE record_id = '", record_id, "'")
sensor_data <- dbGetQuery(dbEngine, query)
dbDisconnect(dbEngine)
# generate timestamp based on local_date
sensor_data$timestamp <- as.numeric(ymd_hms(paste(sensor_data$local_date, "00:00:00"), tz=source$TIMEZONE, quiet=TRUE)) * 1000
write_csv(sensor_data, sensor_file)

0
src/features/__init__.py
View File

85
src/features/features_utils.py
View File

@ -1,85 +0,0 @@
import pandas as pd
from datetime import datetime, timedelta, time
SEGMENT = {"night": 0, "morning": 1, "afternoon": 2, "evening": 3}
EPOCH_TIMES = {"night": [0,5], "morning": [6,11], "afternoon": [12,17], "evening": [18,23]}
def truncateTime(df, segment_column, new_day_segment, datetime_column, date_column, new_time):
df.loc[:, segment_column] = new_day_segment
df.loc[:, datetime_column] = df[date_column].apply(lambda date: datetime.combine(date, new_time))
return df
# calculate truncated time differences and truncated extra_cols if it is not empty
def computeTruncatedDifferences(df, extra_cols):
df["truncated_time_diff"] = df["local_end_date_time"] - df["local_start_date_time"]
df["truncated_time_diff"] = df["truncated_time_diff"].apply(lambda time: time.total_seconds()/60)
if extra_cols:
for extra_col in extra_cols:
df[extra_col] = df[extra_col] * (df["truncated_time_diff"] / df["time_diff"])
del df["time_diff"]
df.rename(columns={"truncated_time_diff": "time_diff"}, inplace=True)
return df
def splitOvernightEpisodes(sensor_deltas, extra_cols, fixed_cols):
overnight = sensor_deltas[(sensor_deltas["local_start_date"] + timedelta(days=1)) == sensor_deltas["local_end_date"]]
not_overnight = sensor_deltas[sensor_deltas["local_start_date"] == sensor_deltas["local_end_date"]]
if not overnight.empty:
today = overnight[extra_cols + fixed_cols + ["time_diff", "local_start_date_time", "local_start_date", "local_start_day_segment"]].copy()
tomorrow = overnight[extra_cols + fixed_cols + ["time_diff", "local_end_date_time", "local_end_date", "local_end_day_segment"]].copy()
# truncate the end time of all overnight periods to midnight
today = truncateTime(today, "local_end_day_segment", "evening", "local_end_date_time", "local_start_date", time(23,59,59))
today["local_end_date"] = overnight["local_start_date"]
# set the start time of all periods after midnight to midnight
tomorrow = truncateTime(tomorrow, "local_start_day_segment", "night", "local_start_date_time", "local_end_date", time(0,0,0))
tomorrow["local_start_date"] = overnight["local_end_date"]
overnight = pd.concat([today, tomorrow], axis=0, sort=False)
# calculate new time_diff and extra_cols for split overnight periods
overnight = computeTruncatedDifferences(overnight, extra_cols)
# sort by local_start_date_time and reset the index
days = pd.concat([not_overnight, overnight], axis=0, sort=False)
days = days.sort_values(by=['local_start_date_time']).reset_index(drop=True)
return days
def splitMultiSegmentEpisodes(sensor_deltas, day_segment, extra_cols):
# extract episodes that start and end at the same epochs
exact_segments = sensor_deltas.query("local_start_day_segment == local_end_day_segment and local_start_day_segment == @day_segment").copy()
# extract episodes that start and end at different epochs
across_segments = sensor_deltas.query("local_start_day_segment != local_end_day_segment").copy()
# 1) if start time is in current day_segment
start_segment = across_segments[across_segments["local_start_day_segment"] == day_segment].copy()
if not start_segment.empty:
start_segment = truncateTime(start_segment, "local_end_day_segment", day_segment, "local_end_date_time", "local_end_date", time(EPOCH_TIMES[day_segment][1],59,59))
# 2) if end time is in current day_segment
end_segment = across_segments[across_segments["local_end_day_segment"] == day_segment].copy()
if not end_segment.empty:
end_segment = truncateTime(end_segment, "local_start_day_segment", day_segment, "local_start_date_time", "local_start_date", time(EPOCH_TIMES[day_segment][0],0,0))
# 3) if current episode comtains day_segment
across_segments.loc[:,"start_segment"] = across_segments["local_start_day_segment"].apply(lambda seg: SEGMENT[seg])
across_segments.loc[:,"end_segment"] = across_segments["local_end_day_segment"].apply(lambda seg: SEGMENT[seg])
day_segment_num = SEGMENT[day_segment]
within_segments = across_segments.query("start_segment < @day_segment_num and end_segment > @day_segment_num")
del across_segments["start_segment"], across_segments["end_segment"]
del within_segments["start_segment"], within_segments["end_segment"]
if not within_segments.empty:
within_segments = truncateTime(within_segments, "local_start_day_segment", day_segment, "local_start_date_time", "local_start_date", time(EPOCH_TIMES[day_segment][0],0,0))
within_segments = truncateTime(within_segments, "local_end_day_segment", day_segment, "local_end_date_time", "local_end_date", time(EPOCH_TIMES[day_segment][1],59,59))
across_segments = pd.concat([start_segment, end_segment, within_segments], axis=0, sort=False)
if not across_segments.empty:
accross_segments = computeTruncatedDifferences(across_segments, extra_cols)
# sort by local_start_date_time and reset the index
segments = pd.concat([exact_segments, across_segments], axis=0, sort=False)
segments = segments.sort_values(by=['local_start_date_time']).reset_index(drop=True)
return segments

2
src/features/phone_bluetooth/rapids/main.R
View File

@ -46,7 +46,7 @@ rapids_features <- function(sensor_data_files, day_segment, provider){
features <- merge(features, feature, by="local_segment", all = TRUE)
}
features <- features %>% mutate_at(vars(contains("countscansmostuniquedevice")), list( ~ replace_na(., 0))) %>% select(-local_segment)
features <- features %>% mutate_at(vars(contains("countscansmostuniquedevice")), list( ~ replace_na(., 0)))
return(features)
}

2
src/features/join_features_from_providers.R → src/features/utils/join_features_from_providers.R
View File

@ -3,7 +3,7 @@ source("renv/activate.R")
library("tidyr")
library("dplyr", warn.conflicts = F)
location_features_files <- snakemake@input[["location_features"]]
location_features_files <- snakemake@input[["sensor_features"]]
location_features <- setNames(data.frame(matrix(ncol = 1, nrow = 0)), c("local_segment"))

2
src/models/merge_features_for_population_model.R → src/features/utils/merge_sensor_features_for_all_participants.R
View File

@ -9,7 +9,7 @@ feature_files <- snakemake@input[["feature_files"]]
features_of_all_participants <- tibble(filename = feature_files) %>% # create a data frame
mutate(file_contents = map(filename, ~ read.csv(., stringsAsFactors = F, colClasses = c(local_date = "character"))),
mutate(file_contents = map(filename, ~ read.csv(., stringsAsFactors = F, colClasses = c(local_segment = "character", local_segment_label = "character", local_segment_start_datetime="character", local_segment_end_datetime="character"))),
pid = str_match(filename, ".*/([a-zA-Z]+?[0-9]+?)/.*")[,2]) %>%
unnest(cols = c(file_contents)) %>%
select(-filename)

22
src/features/utils/merge_sensor_features_for_individual_participants.R 100644
View File

@ -0,0 +1,22 @@
source("renv/activate.R")
library(tidyr)
library(purrr)
library("dplyr", warn.conflicts = F)
library("methods")
library("mgm")
library("qgraph")
library("dplyr", warn.conflicts = F)
library("scales")
library("ggplot2")
library("purrr")
library("tidyr")
library("reshape2")
feature_files <- snakemake@input[["feature_files"]]
features_for_individual_model <- feature_files %>%
map(read.csv, stringsAsFactors = F, colClasses = c(local_segment = "character", local_segment_label = "character", local_segment_start_datetime="character", local_segment_end_datetime="character")) %>%
reduce(full_join, by=c("local_segment","local_segment_label","local_segment_start_datetime","local_segment_end_datetime"))
write.csv(features_for_individual_model, snakemake@output[[1]], row.names = FALSE)

3
src/features/demographic_features.py → src/features/workflow_example/demographic_features.py
View File

@ -2,10 +2,9 @@ import pandas as pd
pid = snakemake.params["pid"]
requested_features = snakemake.params["features"]
demographic_features = pd.DataFrame(columns=["pid"] + requested_features)
demographic_features = pd.DataFrame(columns=requested_features)
participant_info = pd.read_csv(snakemake.input["participant_info"], parse_dates=["surgery_date", "discharge_date"])
demographic_features.loc[0, "pid"] = pid
if not participant_info.empty:
if "age" in requested_features:
demographic_features.loc[0, "age"] = participant_info.loc[0, "age"]

0
src/models/__init__.py
View File

61
src/models/clean_features_for_model.R
View File

@ -1,61 +0,0 @@
source("renv/activate.R")
library(tidyr)
library("dplyr", warn.conflicts = F)
filter_participant_without_enough_days <- function(clean_features, days_before_threshold, days_after_threshold){
clean_features$day_type <- ifelse(clean_features$day_idx < 0, -1, ifelse(clean_features$day_idx > 0, 1, 0))
if("pid" %in% colnames(clean_features)){
clean_features <- clean_features %>%
group_by(pid) %>%
add_count(pid, day_type) # this adds a new column "n"
} else {
clean_features <- clean_features %>% add_count(day_type < 0)
}
# Only keep participants with enough days before surgery and after discharge
clean_features <- clean_features %>%
mutate(count_before = ifelse(day_type == -1, n, NA), # before surgery
count_after = ifelse(day_type == 1, n, NA)) %>% # after discharge
fill(count_before, .direction = "downup") %>%
fill(count_after, .direction = "downup") %>%
filter(count_before >= days_before_threshold & count_after >= days_after_threshold) %>%
select(-n, -count_before, -count_after, -day_type) %>%
ungroup()
return(clean_features)
}
clean_features <- read.csv(snakemake@input[[1]])
cols_nan_threshold <- as.numeric(snakemake@params[["cols_nan_threshold"]])
drop_zero_variance_columns <- as.logical(snakemake@params[["cols_var_threshold"]])
rows_nan_threshold <- as.numeric(snakemake@params[["rows_nan_threshold"]])
days_before_threshold <- as.numeric(snakemake@params[["days_before_threshold"]])
days_after_threshold <- as.numeric(snakemake@params[["days_after_threshold"]])
features_exclude_day_idx <- as.logical(snakemake@params[["features_exclude_day_idx"]])
# We have to do this before and after dropping rows, that's why is duplicated
clean_features <- filter_participant_without_enough_days(clean_features, days_before_threshold, days_after_threshold)
# drop columns with a percentage of NA values above cols_nan_threshold
if(nrow(clean_features))
clean_features <- clean_features %>% select_if(~ sum(is.na(.)) / length(.) <= cols_nan_threshold )
if(drop_zero_variance_columns)
clean_features <- clean_features %>% select_if(grepl("pid|local_date",names(.)) | sapply(., n_distinct, na.rm = T) > 1)
# drop rows with a percentage of NA values above rows_nan_threshold
clean_features <- clean_features %>%
mutate(percentage_na = rowSums(is.na(.)) / ncol(.)) %>%
filter(percentage_na < rows_nan_threshold) %>%
select(-percentage_na)
if(nrow(clean_features) != 0){
clean_features <- filter_participant_without_enough_days(clean_features, days_before_threshold, days_after_threshold)
# include "day_idx" as features or not
if(features_exclude_day_idx)
clean_features <- clean_features %>% select(-day_idx)
}
write.csv(clean_features, snakemake@output[[1]], row.names = FALSE)

8
src/models/merge_data_for_population_model.py
View File

@ -1,8 +0,0 @@
import pandas as pd
data_all_participants = pd.DataFrame()
for data_file in snakemake.input["data_files"]:
data_single_participant = pd.read_csv(data_file)
data_all_participants = pd.concat([data_all_participants, data_single_participant], axis=0)
data_all_participants.to_csv(snakemake.output[0], index=False)

66
src/models/merge_features_and_targets.py
View File

@ -1,66 +0,0 @@
import pandas as pd
import numpy as np
from modeling_utils import getMatchingColNames, dropZeroVarianceCols
def summarisedNumericalFeatures(col_names, features):
numerical_features = features.groupby(["pid"])[col_names].var()
numerical_features.columns = numerical_features.columns.str.replace("daily", "overallvar")
return numerical_features
def summarisedCategoricalFeatures(col_names, features):
categorical_features = features.groupby(["pid"])[col_names].agg(lambda x: int(pd.Series.mode(x)[0]))
categorical_features.columns = categorical_features.columns.str.replace("daily", "overallmode")
return categorical_features
def summariseFeatures(features, numerical_operators, categorical_operators, cols_var_threshold):
numerical_col_names = getMatchingColNames(numerical_operators, features)
categorical_col_names = getMatchingColNames(categorical_operators, features)
numerical_features = summarisedNumericalFeatures(numerical_col_names, features)
categorical_features = summarisedCategoricalFeatures(categorical_col_names, features)
features = pd.concat([numerical_features, categorical_features], axis=1)
if cols_var_threshold == "True": # double check the categorical features
features = dropZeroVarianceCols(features)
elif cols_var_threshold == "Flase":
pass
else:
ValueError("COLS_VAR_THRESHOLD parameter in config.yaml can only be 'True' or 'False'")
return features
summarised = snakemake.params["summarised"]
cols_var_threshold = snakemake.params["cols_var_threshold"]
numerical_operators = snakemake.params["numerical_operators"]
categorical_operators = snakemake.params["categorical_operators"]
features_exclude_day_idx = snakemake.params["features_exclude_day_idx"]
# Extract summarised features based on daily features:
# for categorical features: calculate variance across all days
# for numerical features: calculate mode across all days
if summarised == "summarised":
features = pd.read_csv(snakemake.input["cleaned_features"], parse_dates=["local_date"])
demographic_features = pd.read_csv(snakemake.input["demographic_features"], index_col=["pid"])
targets = pd.read_csv(snakemake.input["targets"], index_col=["pid"])
features = summariseFeatures(features, numerical_operators, categorical_operators, cols_var_threshold)
data = pd.concat([features, demographic_features, targets], axis=1, join="inner")
elif summarised == "notsummarised":
features = pd.read_csv(snakemake.input["cleaned_features"])
demographic_features = pd.read_csv(snakemake.input["demographic_features"])
features = features.merge(demographic_features, on="pid", how="left").set_index(["pid", "local_date"])
targets = pd.read_csv(snakemake.input["targets"], index_col=["pid", "local_date"])
data = pd.concat([features, targets], axis=1, join="inner")
else:
raise ValueError("SUMMARISED parameter in config.yaml can only be 'summarised' or 'notsummarised'")
if features_exclude_day_idx and ("day_idx" in data.columns):
del data["day_idx"]
data.to_csv(snakemake.output[0], index=True)

35
src/models/merge_features_for_individual_model.R
View File

@ -1,35 +0,0 @@
source("renv/activate.R")
library(tidyr)
library(purrr)
library("dplyr", warn.conflicts = F)
library("methods")
library("mgm")
library("qgraph")
library("dplyr", warn.conflicts = F)
library("scales")
library("ggplot2")
library("purrr")
library("tidyr")
library("reshape2")
feature_files <- snakemake@input[["feature_files"]]
phone_valid_sensed_days <- snakemake@input[["phone_valid_sensed_days"]]
days_to_include <- snakemake@input[["days_to_include"]]
source <- snakemake@params[["source"]]
features_for_individual_model <- feature_files %>%
map(read.csv, stringsAsFactors = F, colClasses = c(local_date = "character")) %>%
reduce(full_join, by="local_date")
if(!is.null(phone_valid_sensed_days) && source %in% c("phone_features", "phone_fitbit_features")){
valid_days <- read.csv(phone_valid_sensed_days)
valid_days <- valid_days[valid_days$is_valid_sensed_day == TRUE, ]
features_for_individual_model <- merge(features_for_individual_model, valid_days, by="local_date") %>% select(-valid_sensed_hours, -is_valid_sensed_day)
}
if(!is.null(days_to_include)){
features_for_individual_model <- merge(features_for_individual_model, read.csv(days_to_include), by="local_date")
}
write.csv(features_for_individual_model, snakemake@output[[1]], row.names = FALSE)

16
src/models/merge_population_model_results.py
View File

@ -1,16 +0,0 @@
import pandas as pd
overall_results = pd.read_csv(snakemake.input["overall_results"])
nan_cells_ratio = pd.read_csv(snakemake.input["nan_cells_ratio"])
baseline = pd.read_csv(snakemake.input["baseline"], index_col=["method"])
# add nan cells ratio
overall_results.insert(3, "nan_cells_ratio", nan_cells_ratio["nan_cells_ratio"])
# add baseline
baseline = baseline.stack().to_frame().T
baseline.columns = ['{}_{}'.format(*col) for col in baseline.columns]
baseline = baseline.add_prefix('b_')
results = pd.concat([overall_results, baseline], axis=1)
results.to_csv(snakemake.output[0], index=False)

8
src/models/nan_cells_ratio_of_cleaned_features.py
View File

@ -1,8 +0,0 @@
import pandas as pd
features = pd.read_csv(snakemake.input["cleaned_features"], parse_dates=["local_date"])
# Compute the proportion of missing value cells among all features
nan_cells_ratio = features.isnull().sum().sum() / (features.shape[0] * features.shape[1])
pd.DataFrame({"nan_cells_ratio": [nan_cells_ratio]}).to_csv(snakemake.output[0], index=False)

43
src/models/select_days_to_analyse.py
View File

@ -1,43 +0,0 @@
import numpy as np
import pandas as pd
from datetime import timedelta
def appendDaysInRange(days_to_analyse, start_date, end_date, day_type):
num_of_days = (end_date - start_date).days
if np.isnan(num_of_days):
return days_to_analyse
for day in range(num_of_days + 1):
if day_type == -1:
day_idx = (num_of_days - day + 1) * day_type
elif day_type == 1:
day_idx = day + 1
else:
day_idx = 0
days_to_analyse = days_to_analyse.append({"local_date": start_date + timedelta(days = day), "day_idx": day_idx}, ignore_index=True)
return days_to_analyse
days_before_surgery = int(snakemake.params["days_before_surgery"])
days_in_hospital = str(snakemake.params["days_in_hospital"])
days_after_discharge = int(snakemake.params["days_after_discharge"])
participant_info = pd.read_csv(snakemake.input["participant_info"], parse_dates=["surgery_date", "discharge_date"])
days_to_analyse = pd.DataFrame(columns = ["local_date", "day_idx"])
try:
surgery_date, discharge_date = participant_info["surgery_date"].iloc[0].date(), participant_info["discharge_date"].iloc[0].date()
except:
pass
else:
start_date = surgery_date - timedelta(days = days_before_surgery)
end_date = discharge_date + timedelta(days = days_after_discharge)
# days before surgery: -1; in hospital: 0; after discharge: 1
days_to_analyse = appendDaysInRange(days_to_analyse, start_date, surgery_date - timedelta(days = 1), -1)
if days_in_hospital == "T":
days_to_analyse = appendDaysInRange(days_to_analyse, surgery_date, discharge_date, 0)
days_to_analyse = appendDaysInRange(days_to_analyse, discharge_date + timedelta(days = 1), end_date, 1)
days_to_analyse.to_csv(snakemake.output[0], index=False)

18
src/models/targets.py
View File

@ -1,18 +0,0 @@
import pandas as pd
import numpy as np
pid = snakemake.params["pid"]
summarised = snakemake.params["summarised"]
participant_info = pd.read_csv(snakemake.input["participant_info"])
if summarised == "summarised":
raise ValueError("Do not support summarised features for example dataset.")
elif summarised == "notsummarised":
targets = participant_info[["local_date", "target"]]
targets.insert(0, "pid", pid)
else:
raise ValueError("SUMMARISED parameter in config.yaml can only be 'summarised' or 'notsummarised'")
targets.to_csv(snakemake.output[0], index=False)

66
src/models/baseline.py → src/models/workflow_example/baselines.py
View File

@ -10,18 +10,18 @@ from sklearn.model_selection import LeaveOneOut
def baselineAccuracyOfMajorityClassClassifier(targets):
majority_class = targets["target"].value_counts().idxmax()
pred_y = [majority_class] * targets.shape[0]
pred_y_prob = pred_y
metrics = getMetrics(pred_y, pred_y_prob, targets["target"].values.ravel().tolist())
pred_y_proba = pred_y
metrics = getMetrics(pred_y, pred_y_proba, targets["target"].values.ravel().tolist())
return metrics, majority_class
def baselineMetricsOfRandomWeightedClassifier(targets, majority_ratio, majority_class, iter_times):
metrics_all_iters = {"accuracy": [], "precision0":[], "recall0": [], "f10": [], "precision1": [], "recall1": [], "f11": [], "auc": [], "kappa": []}
metrics_all_iters = {"accuracy": [], "precision0":[], "recall0": [], "f10": [], "precision1": [], "recall1": [], "f11": [], "f1_macro": [], "auc": [], "kappa": []}
probabilities = [0, 0]
probabilities[majority_class], probabilities[1 - majority_class] = majority_ratio, 1 - majority_ratio
for i in range(iter_times):
pred_y = np.random.RandomState(i).multinomial(1, probabilities, targets.shape[0])[:,1].tolist()
pred_y_prob = pred_y
metrics = getMetrics(pred_y, pred_y_prob, targets["target"].values.ravel().tolist())
pred_y_proba = pred_y
metrics = getMetrics(pred_y, pred_y_proba, targets["target"].values.ravel().tolist())
for key in metrics_all_iters.keys():
metrics_all_iters[key].append(metrics[key].item())
# Calculate average metrics across all iterations
@ -38,21 +38,25 @@ def baselineMetricsOfDTWithDemographicFeatures(cv_method, data_x, data_y, oversa
clf = createPipeline("DT", oversampler_type)
clf.fit(train_x, train_y.values.ravel())
pred_y = pred_y + clf.predict(test_x).ravel().tolist()
pred_y_prob = pred_y
pred_y_proba = pred_y
true_y = true_y + test_y.values.ravel().tolist()
return getMetrics(pred_y, pred_y_prob, true_y)
return getMetrics(pred_y, pred_y_proba, true_y)
cv_method = globals()[snakemake.params["cv_method"]]()
colnames_demographic_features = snakemake.params["demographic_features"]
rowsnan_colsnan_days_colsvar_threshold = snakemake.params["rowsnan_colsnan_days_colsvar_threshold"]
colnames_demographic_features = snakemake.params["colnames_demographic_features"]
data = pd.read_csv(snakemake.input[0])
index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
if "pid" in data.columns:
index_columns.append("pid")
data.set_index(index_columns, inplace=True)
data = pd.read_csv(snakemake.input[0], index_col=["pid"])
data_x, data_y = data.drop("target", axis=1), data[["target"]]
targets_value_counts = data_y["target"].value_counts()
baseline_metrics = pd.DataFrame(columns=["method", "fullMethodName", "accuracy", "precision0", "recall0", "f10", "precision1", "recall1", "f11", "auc", "kappa"])
baseline_metrics = pd.DataFrame(columns=["method", "fullMethodName", "accuracy", "precision0", "recall0", "f10", "precision1", "recall1", "f11", "f1_macro", "auc", "kappa"])
if len(targets_value_counts) < 2:
fout = open(snakemake.log[0], "w")
fout.write(targets_value_counts.to_string())
@ -69,21 +73,33 @@ else:
majority_ratio = baseline1_metrics["accuracy"]
# Baseline 2: random weighted classifier => random classifier with binomial distribution
baseline2_metrics = baselineMetricsOfRandomWeightedClassifier(data_y, majority_ratio, majority_class, 1000)
# Baseline 3: decision tree with demographic features
baseline3_metrics = baselineMetricsOfDTWithDemographicFeatures(cv_method, data_x[colnames_demographic_features], data_y, oversampler_type)
baselines = [baseline1_metrics, baseline2_metrics, baseline3_metrics]
if "pid" in index_columns:
# Baseline 3: decision tree with demographic features
baseline3_metrics = baselineMetricsOfDTWithDemographicFeatures(cv_method, data_x[colnames_demographic_features], data_y, oversampler_type)
baselines = [baseline1_metrics, baseline2_metrics, baseline3_metrics]
methods = ["majority", "rwc", "dt"]
fullMethodNames = ["MajorityClassClassifier", "RandomWeightedClassifier", "DecisionTreeWithDemographicFeatures"]
else:
# Only have 2 baselines
baselines = [baseline1_metrics, baseline2_metrics]
methods = ["majority", "rwc"]
fullMethodNames = ["MajorityClassClassifier", "RandomWeightedClassifier"]
baseline_metrics = pd.DataFrame({"method": methods,
"fullMethodName": fullMethodNames,
"accuracy": [baseline["accuracy"] for baseline in baselines],
"precision0": [baseline["precision0"] for baseline in baselines],
"recall0": [baseline["recall0"] for baseline in baselines],
"f10": [baseline["f10"] for baseline in baselines],
"precision1": [baseline["precision1"] for baseline in baselines],
"recall1": [baseline["recall1"] for baseline in baselines],
"f11": [baseline["f11"] for baseline in baselines],
"f1_macro": [baseline["f1_macro"] for baseline in baselines],
"auc": [baseline["auc"] for baseline in baselines],
"kappa": [baseline["kappa"] for baseline in baselines]})
baseline_metrics = pd.DataFrame({"method": ["majority", "rwc", "dt"],
"fullMethodName": ["MajorityClassClassifier", "RandomWeightedClassifier", "DecisionTreeWithDemographicFeatures"],
"accuracy": [baseline["accuracy"] for baseline in baselines],
"precision0": [baseline["precision0"] for baseline in baselines],
"recall0": [baseline["recall0"] for baseline in baselines],
"f10": [baseline["f10"] for baseline in baselines],
"precision1": [baseline["precision1"] for baseline in baselines],
"recall1": [baseline["recall1"] for baseline in baselines],
"f11": [baseline["f11"] for baseline in baselines],
"auc": [baseline["auc"] for baseline in baselines],
"kappa": [baseline["kappa"] for baseline in baselines]})
baseline_metrics.to_csv(snakemake.output[0], index=False)

29
src/models/workflow_example/clean_sensor_features.R 100644
View File

@ -0,0 +1,29 @@
source("renv/activate.R")
library(tidyr)
library("dplyr", warn.conflicts = F)
clean_features <- read.csv(snakemake@input[[1]])
cols_nan_threshold <- as.numeric(snakemake@params[["cols_nan_threshold"]])
drop_zero_variance_columns <- as.logical(snakemake@params[["cols_var_threshold"]])
rows_nan_threshold <- as.numeric(snakemake@params[["rows_nan_threshold"]])
data_yielded_hours_ratio_threshold <- as.numeric(snakemake@params[["data_yielded_hours_ratio_threshold"]])
# drop rows with the value of "phone_data_yield_rapids_ratiovalidyieldedhours" column less than data_yielded_hours_ratio_threshold
clean_features <- clean_features %>%
filter(phone_data_yield_rapids_ratiovalidyieldedhours > data_yielded_hours_ratio_threshold)
# drop columns with a percentage of NA values above cols_nan_threshold
if(nrow(clean_features))
clean_features <- clean_features %>% select_if(~ sum(is.na(.)) / length(.) <= cols_nan_threshold )
if(drop_zero_variance_columns)
clean_features <- clean_features %>% select_if(grepl("pid|local_segment|local_segment_label|local_segment_start_datetime|local_segment_end_datetime",names(.)) | sapply(., n_distinct, na.rm = T) > 1)
# drop rows with a percentage of NA values above rows_nan_threshold
clean_features <- clean_features %>%
mutate(percentage_na = rowSums(is.na(.)) / ncol(.)) %>%
filter(percentage_na < rows_nan_threshold) %>%
select(-percentage_na)
write.csv(clean_features, snakemake@output[[1]], row.names = FALSE)

10
src/models/workflow_example/merge_features_and_targets_for_individual_model.py 100644
View File

@ -0,0 +1,10 @@
import pandas as pd
import numpy as np
index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
sensor_features = pd.read_csv(snakemake.input["cleaned_sensor_features"], index_col=index_columns)
targets = pd.read_csv(snakemake.input["targets"], index_col=index_columns)
data = pd.concat([sensor_features, targets[["target"]]], axis=1, join="inner")
data.to_csv(snakemake.output[0], index=True)

27
src/models/workflow_example/merge_features_and_targets_for_population_model.py 100644
View File

@ -0,0 +1,27 @@
import pandas as pd
import numpy as np
merge_keys = ["pid", "local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
sensor_features = pd.read_csv(snakemake.input["cleaned_sensor_features"])
all_demographic_features = pd.DataFrame()
for demographic_features_path in snakemake.input["demographic_features"]:
pid = demographic_features_path.split("/")[3]
demographic_features = pd.read_csv(demographic_features_path)
demographic_features = demographic_features.assign(pid=pid)
all_demographic_features = pd.concat([all_demographic_features, demographic_features], axis=0)
# merge sensor features and demographic features
features = sensor_features.merge(all_demographic_features, on="pid", how="left")
all_targets = pd.DataFrame()
for targets_path in snakemake.input["targets"]:
pid = targets_path.split("/")[3]
targets = pd.read_csv(targets_path)
targets = targets.assign(pid=pid)
all_targets = pd.concat([all_targets, targets], axis=0)
# merge features and targets
data = features.merge(all_targets[["target"] + merge_keys], on=merge_keys, how="inner")
data.to_csv(snakemake.output[0], index=False)

51
src/models/modeling.py → src/models/workflow_example/modeling.py
View File

@ -1,7 +1,7 @@
import pandas as pd
import numpy as np
from modeling_utils import getMatchingColNames, dropZeroVarianceCols, getNormAllParticipantsScaler, getMetrics, getFeatureImportances, createPipeline
from sklearn.model_selection import train_test_split, LeaveOneOut, GridSearchCV, cross_val_score, KFold
from modeling_utils import getMatchingColNames, getNormAllParticipantsScaler, getMetrics, getFeatureImportances, createPipeline
from sklearn.model_selection import LeaveOneOut, GridSearchCV
@ -25,7 +25,8 @@ def preprocessCategoricalFeatures(categorical_features, mode_categorical_feature
categorical_features = categorical_features.fillna(mode_categorical_features)
# one-hot encoding
categorical_features = categorical_features.apply(lambda col: col.astype("category"))
categorical_features = pd.get_dummies(categorical_features)
if not categorical_features.empty:
categorical_features = pd.get_dummies(categorical_features)
return categorical_features
def splitNumericalCategoricalFeatures(features, categorical_feature_colnames):
@ -48,32 +49,32 @@ def preprocesFeatures(train_numerical_features, test_numerical_features, categor
# Step 4. Save results, parameters, and metrics to CSV files
##############################################################
# For reproducibility
np.random.seed(0)
# Step 1. Read parameters and data
# Read parameters
model = snakemake.params["model"]
source = snakemake.params["source"]
summarised = snakemake.params["summarised"]
day_segment = snakemake.params["day_segment"]
scaler = snakemake.params["scaler"]
cv_method = snakemake.params["cv_method"]
categorical_operators = snakemake.params["categorical_operators"]
categorical_colnames_demographic_features = snakemake.params["categorical_demographic_features"]
model_hyperparams = snakemake.params["model_hyperparams"][model]
rowsnan_colsnan_days_colsvar_threshold = snakemake.params["rowsnan_colsnan_days_colsvar_threshold"] # thresholds for data cleaning
# Read data and split
if summarised == "summarised":
data = pd.read_csv(snakemake.input["data"], index_col=["pid"])
elif summarised == "notsummarised":
data = pd.read_csv(snakemake.input["data"], index_col=["pid", "local_date"])
else:
raise ValueError("SUMMARISED parameter in config.yaml can only be 'summarised' or 'notsummarised'")
data = pd.read_csv(snakemake.input["data"])
index_columns = ["local_segment", "local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]
if "pid" in data.columns:
index_columns.append("pid")
data.set_index(index_columns, inplace=True)
data_x, data_y = data.drop("target", axis=1), data[["target"]]
categorical_feature_colnames = categorical_colnames_demographic_features + getMatchingColNames(categorical_operators, data_x)
if "pid" in index_columns:
categorical_feature_colnames = categorical_colnames_demographic_features + getMatchingColNames(categorical_operators, data_x)
else:
categorical_feature_colnames = getMatchingColNames(categorical_operators, data_x)
@ -82,7 +83,7 @@ cv_class = globals()[cv_method]
inner_cv = cv_class()
outer_cv = cv_class()
fold_id, pid, best_params, true_y, pred_y, pred_y_prob = [], [], [], [], [], []
fold_id, pid, best_params, true_y, pred_y, pred_y_proba = [], [], [], [], [], []
feature_importances_all_folds = pd.DataFrame()
fold_count = 1
@ -99,7 +100,7 @@ for train_index, test_index in outer_cv.split(data_x):
mode_categorical_features = train_categorical_features.mode().iloc[0]
train_x = preprocesFeatures(train_numerical_features, None, train_categorical_features, mode_categorical_features, scaler, "train")
test_x = preprocesFeatures(train_numerical_features, test_numerical_features, test_categorical_features, mode_categorical_features, scaler, "test")
train_x, test_x = train_x.align(test_x, join='outer', axis=1, fill_value=0) # in case we get rid off categorical columns
train_x, test_x = train_x.align(test_x, join="outer", axis=1, fill_value=0) # in case we get rid off categorical columns
# Compute number of participants and features
# values do not change between folds
@ -129,7 +130,7 @@ for train_index, test_index in outer_cv.split(data_x):
pred_y = pred_y + cur_fold_pred
proba_of_two_categories = clf.predict_proba(test_x).tolist()
pred_y_prob = pred_y_prob + [probabilities[clf.classes_.tolist().index(1)] for probabilities in proba_of_two_categories]
pred_y_proba = pred_y_proba + [probabilities[clf.classes_.tolist().index(1)] for probabilities in proba_of_two_categories]
true_y = true_y + test_y.values.ravel().tolist()
pid = pid + test_y.index.tolist() # each test partition (fold) in the outer cv is a participant (LeaveOneOut cv)
@ -140,16 +141,16 @@ for train_index, test_index in outer_cv.split(data_x):
# Step 3. Model evaluation
if len(pred_y) > 1:
metrics = getMetrics(pred_y, pred_y_prob, true_y)
metrics = getMetrics(pred_y, pred_y_proba, true_y)
else:
metrics = {"accuracy": None, "precision0": None, "recall0": None, "f10": None, "precision1": None, "recall1": None, "f11": None, "auc": None, "kappa": None}
metrics = {"accuracy": None, "precision0": None, "recall0": None, "f10": None, "precision1": None, "recall1": None, "f11": None, "f1_macro": None, "auc": None, "kappa": None}
# Step 4. Save results, parameters, and metrics to CSV files
fold_predictions = pd.DataFrame({"fold_id": fold_id, "pid": pid, "hyperparameters": best_params, "true_y": true_y, "pred_y": pred_y, "pred_y_prob": pred_y_prob})
fold_metrics = pd.DataFrame({"fold_id":[], "accuracy":[], "precision0": [], "recall0": [], "f10": [], "precision1": [], "recall1": [], "f11": [], "auc": [], "kappa": []})
overall_results = pd.DataFrame({"num_of_rows": [num_of_rows], "num_of_features": [num_of_features], "rowsnan_colsnan_days_colsvar_threshold": [rowsnan_colsnan_days_colsvar_threshold], "model": [model], "cv_method": [cv_method], "source": [source], "scaler": [scaler], "day_segment": [day_segment], "summarised": [summarised], "accuracy": [metrics["accuracy"]], "precision0": [metrics["precision0"]], "recall0": [metrics["recall0"]], "f10": [metrics["f10"]], "precision1": [metrics["precision1"]], "recall1": [metrics["recall1"]], "f11": [metrics["f11"]], "auc": [metrics["auc"]], "kappa": [metrics["kappa"]]})
feature_importances_all_folds.insert(loc=0, column='fold_id', value=fold_id)
feature_importances_all_folds.insert(loc=1, column='pid', value=pid)
fold_predictions = pd.DataFrame({"fold_id": fold_id, "pid": pid, "hyperparameters": best_params, "true_y": true_y, "pred_y": pred_y, "pred_y_proba": pred_y_proba})
fold_metrics = pd.DataFrame({"fold_id":[], "accuracy":[], "precision0": [], "recall0": [], "f10": [], "precision1": [], "recall1": [], "f11": [], "f1_macro": [], "auc": [], "kappa": []})
overall_results = pd.DataFrame({"num_of_rows": [num_of_rows], "num_of_features": [num_of_features], "model": [model], "cv_method": [cv_method], "scaler": [scaler], "accuracy": [metrics["accuracy"]], "precision0": [metrics["precision0"]], "recall0": [metrics["recall0"]], "f10": [metrics["f10"]], "precision1": [metrics["precision1"]], "recall1": [metrics["recall1"]], "f11": [metrics["f11"]], "f1_macro": [metrics["f1_macro"]], "auc": [metrics["auc"]], "kappa": [metrics["kappa"]]})
feature_importances_all_folds.insert(loc=0, column="fold_id", value=fold_id)
feature_importances_all_folds.insert(loc=1, column="pid", value=pid)
fold_predictions.to_csv(snakemake.output["fold_predictions"], index=False)
fold_metrics.to_csv(snakemake.output["fold_metrics"], index=False)

25
src/models/modeling_utils.py → src/models/workflow_example/modeling_utils.py
View File

@ -1,4 +1,5 @@
import pandas as pd
import numpy as np
from sklearn.preprocessing import MinMaxScaler, StandardScaler, RobustScaler
from sklearn.metrics import accuracy_score, f1_score, precision_score, recall_score, classification_report, confusion_matrix
from sklearn.metrics import precision_recall_fscore_support
@ -44,24 +45,24 @@ def getNormAllParticipantsScaler(features, scaler_flag):
scaler.fit(features)
return scaler
# get metrics: accuracy, precision1, recall1, f11, auc, kappa
def getMetrics(pred_y, pred_y_prob, true_y):
# get metrics: accuracy, precision0, recall0, f10, precision1, recall1, f11, f1_macro, auc, kappa
def getMetrics(pred_y, pred_y_proba, true_y):
metrics = {}
count = len(np.unique(true_y))
label= np.unique(true_y)[0]
# metrics for all categories
metrics["accuracy"] = accuracy_score(true_y, pred_y)
try:
metrics["auc"] = roc_auc_score(true_y, pred_y_prob)
except:
metrics["auc"] = None
metrics["f1_macro"] = f1_score(true_y, pred_y, average="macro") # unweighted mean
metrics["auc"] = np.nan if count == 1 else roc_auc_score(true_y, pred_y_proba)
metrics["kappa"] = cohen_kappa_score(true_y, pred_y)
# metrics for label 0
metrics["precision0"] = precision_score(true_y, pred_y, average=None, labels=[0,1], zero_division=0)[0]
metrics["recall0"] = recall_score(true_y, pred_y, average=None, labels=[0,1])[0]
metrics["f10"] = f1_score(true_y, pred_y, average=None, labels=[0,1])[0]
metrics["precision0"] = np.nan if (count == 1 and label == 1) else precision_score(true_y, pred_y, average=None, labels=[0,1], zero_division=0)[0]
metrics["recall0"] = np.nan if (count == 1 and label == 1) else recall_score(true_y, pred_y, average=None, labels=[0,1])[0]
metrics["f10"] = np.nan if (count == 1 and label == 1) else f1_score(true_y, pred_y, average=None, labels=[0,1])[0]
# metrics for label 1
metrics["precision1"] = precision_score(true_y, pred_y, average=None, labels=[0,1], zero_division=0)[1]
metrics["recall1"] = recall_score(true_y, pred_y, average=None, labels=[0,1])[1]
metrics["f11"] = f1_score(true_y, pred_y, average=None, labels=[0,1])[1]
metrics["precision1"] = np.nan if (count == 1 and label == 0) else precision_score(true_y, pred_y, average=None, labels=[0,1], zero_division=0)[1]
metrics["recall1"] = np.nan if (count == 1 and label == 0) else recall_score(true_y, pred_y, average=None, labels=[0,1])[1]
metrics["f11"] = np.nan if (count == 1 and label == 0) else f1_score(true_y, pred_y, average=None, labels=[0,1])[1]
return metrics

28
src/models/workflow_example/parse_targets.py 100644
View File

@ -0,0 +1,28 @@
import pandas as pd
import numpy as np
from importlib import import_module, util
from pathlib import Path
# import filter_data_by_segment from src/features/utils/utils.py
spec = util.spec_from_file_location("util", str(Path(snakemake.scriptdir).parent.parent / "features" / "utils" / "utils.py"))
mod = util.module_from_spec(spec)
spec.loader.exec_module(mod)
filter_data_by_segment = getattr(mod, "filter_data_by_segment")
targets = pd.read_csv(snakemake.input["targets"])
day_segments_labels = pd.read_csv(snakemake.input["day_segments_labels"], header=0)
all_targets = pd.DataFrame(columns=["local_segment"])
for day_segment in day_segments_labels["label"]:
filtered_targets = filter_data_by_segment(targets, day_segment)
all_targets = all_targets.merge(filtered_targets, how="outer")
segment_colums = pd.DataFrame()
split_segemnt_columns = all_targets["local_segment"].str.split(pat="(.*)#(.*),(.*)", expand=True)
new_segment_columns = split_segemnt_columns.iloc[:,1:4] if split_segemnt_columns.shape[1] == 5 else pd.DataFrame(columns=["local_segment_label", "local_segment_start_datetime","local_segment_end_datetime"])
segment_colums[["local_segment_label", "local_segment_start_datetime", "local_segment_end_datetime"]] = new_segment_columns
for i in range(segment_colums.shape[1]):
all_targets.insert(1 + i, segment_colums.columns[i], segment_colums[segment_colums.columns[i]])
all_targets.to_csv(snakemake.output[0], index=False)