rapids/tests/Snakefile

configfile: "config.yaml"
include: "../rules/packrat.snakefile"
include: "../rules/preprocessing.snakefile"
include: "../rules/features.snakefile"
include: "../rules/models.snakefile"
include: "../rules/reports.snakefile"
include: "../rules/mystudy.snakefile" # You can add snakfiles with rules tailored to your project

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"] not in config["PHONE_VALID_SENSED_BINS"]["TABLES"]:
        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/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"]:
    files_to_compute.extend(expand("data/raw/{pid}/{sensor}_raw.csv", pid=config["PIDS"], sensor=config["WIFI"]["DB_TABLE"]))
    files_to_compute.extend(expand("data/raw/{pid}/{sensor}_with_datetime.csv", pid=config["PIDS"], sensor=config["WIFI"]["DB_TABLE"]))
    files_to_compute.extend(expand("data/processed/{pid}/wifi_{day_segment}.csv", pid = config["PIDS"], day_segment = config["WIFI"]["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/*"