rapids/rules/common.smk

45 lines
2.2 KiB
Plaintext
Raw Normal View History

# Features.smk #########################################################################################################
def find_features_files(wildcards):
feature_files = []
for provider_key, provider in config[(wildcards.sensor_key).upper()]["PROVIDERS"].items():
if provider["COMPUTE"]:
2020-10-19 21:07:12 +02:00
feature_files.extend(expand("data/interim/{{pid}}/{sensor_key}_features/{sensor_key}_{language}_{provider_key}.csv", sensor_key=wildcards.sensor_key.lower(), language=provider["SRC_LANGUAGE"].lower(), provider_key=provider_key.lower()))
return(feature_files)
def optional_steps_sleep_input(wildcards):
if config["STEP"]["EXCLUDE_SLEEP"]["EXCLUDE"] == True and config["STEP"]["EXCLUDE_SLEEP"]["TYPE"] == "FITBIT_BASED":
return "data/raw/{pid}/fitbit_sleep_summary_with_datetime.csv"
else:
return []
2020-11-25 22:34:05 +01:00
def input_merge_sensor_features_for_individual_participants(wildcards):
feature_files = []
for config_key in config.keys():
2020-12-15 02:30:34 +01:00
if config_key.startswith(("PHONE", "FITBIT", "EMPATICA")) and "PROVIDERS" in config[config_key] and isinstance(config[config_key]["PROVIDERS"], dict):
2020-11-25 22:34:05 +01:00
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
def get_phone_sensor_names():
phone_sensor_names = []
for config_key in config.keys():
if config_key.startswith(("PHONE")) and "PROVIDERS" in config[config_key]:
if config_key != "PHONE_DATA_YIELD" and config_key not in phone_sensor_names:
phone_sensor_names.append(config_key)
return phone_sensor_names
2020-12-16 00:19:11 +01:00
from pathlib import Path
def get_zip_suffixes(pid):
zipfiles = list((Path("data/external/empatica/") / Path(pid)).rglob("*.zip"))
2020-12-16 00:19:11 +01:00
suffixes = []
for zipfile in zipfiles:
suffixes.append(zipfile.stem)
2020-12-16 00:19:11 +01:00
return suffixes
def get_all_raw_empatica_sensor_files(wildcards):
suffixes = get_zip_suffixes(wildcards.pid)
files = ["data/raw/{}/empatica_{}_raw_{}.csv".format(wildcards.pid, wildcards.sensor, suffix) for suffix in suffixes]
return(files)