rapids/tests/Snakefile

79 lines
6.6 KiB
Python

configfile: "config.yaml"
include: "../rules/packrat.snakefile"
include: "../rules/preprocessing.snakefile"
include: "../rules/features.snakefile"
include: "../rules/models.snakefile"
include: "../rules/reports.snakefile"
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["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"]))
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}_{segment}.csv", pid=config["PIDS"], call_type=config["CALLS"]["TYPES"], segment = config["CALLS"]["DAY_SEGMENTS"]))
if config["SCREEN"]["COMPUTE"]:
if config["SCREEN"]["DB_TABLE"] in config["PHONE_VALID_SENSED_BINS"]["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][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["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["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_{segment}.csv", pid=config["PIDS"], segment = config["BLUETOOTH"]["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["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["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["ACTIVITY_RECOGNITION"]["COMPUTE"]:
# TODO add files_to_compute.extend(optional_ar_input(None)), the Android or iOS table gets processed depending on each participant
files_to_compute.extend(expand("data/processed/{pid}/activity_recognition_{day_segment}.csv",pid=config["PIDS"], day_segment = config["ACTIVITY_RECOGNITION"]["DAY_SEGMENTS"]))
rule all:
input:
files_to_compute
rule clean:
shell:
"rm -rf data/raw/* && rm -rf data/interim/* && rm -rf data/processed/* && rm -rf reports/figures/* && rm -rf reports/*.zip && rm -rf reports/compliance/*"