rapids/rules/preprocessing.smk

224 lines
10 KiB
Plaintext
Raw Normal View History

2020-08-03 23:30:15 +02:00
rule create_example_participant_files:
output:
expand("data/external/participant_files/{pid}.yaml", pid = ["example01", "example02"])
2020-08-03 23:30:15 +02:00
shell:
"echo 'PHONE:\n DEVICE_IDS: [a748ee1a-1d0b-4ae9-9074-279a2b6ba524]\n PLATFORMS: [android]\n LABEL: test-01\n START_DATE: 2020-04-23 00:00:00\n END_DATE: 2020-05-04 23:59:59\nFITBIT:\n DEVICE_IDS: [a748ee1a-1d0b-4ae9-9074-279a2b6ba524]\n LABEL: test-01\n START_DATE: 2020-04-23 00:00:00\n END_DATE: 2020-05-04 23:59:59\n' >> ./data/external/participant_files/example01.yaml && echo 'PHONE:\n DEVICE_IDS: [13dbc8a3-dae3-4834-823a-4bc96a7d459d]\n PLATFORMS: [ios]\n LABEL: test-02\n START_DATE: 2020-04-23 00:00:00\n END_DATE: 2020-05-04 23:59:59\nFITBIT:\n DEVICE_IDS: [13dbc8a3-dae3-4834-823a-4bc96a7d459d]\n LABEL: test-02\n START_DATE: 2020-04-23 00:00:00\n END_DATE: 2020-05-04 23:59:59\n' >> ./data/external/participant_files/example02.yaml"
2020-08-03 23:30:15 +02:00
rule create_participants_files:
input:
participants_file = config["CREATE_PARTICIPANT_FILES"]["CSV_FILE_PATH"]
params:
config = config["CREATE_PARTICIPANT_FILES"]
script:
"../src/data/create_participants_files.R"
rule pull_phone_data:
input: unpack(pull_phone_data_input_with_mutation_scripts)
params:
data_configuration = config["PHONE_DATA_STREAMS"][config["PHONE_DATA_STREAMS"]["USE"]],
sensor = "phone_" + "{sensor}",
2021-03-13 00:14:49 +01:00
tables = lambda wildcards: config["PHONE_" + str(wildcards.sensor).upper()]["CONTAINER"],
output:
"data/raw/{pid}/phone_{sensor}_raw.csv"
script:
"../src/data/streams/pull_phone_data.R"
2021-03-23 00:15:13 +01:00
rule process_time_segments:
input:
2021-03-23 00:15:13 +01:00
segments_file = config["TIME_SEGMENTS"]["FILE"],
participant_file = "data/external/participant_files/{pid}.yaml"
params:
2020-12-03 00:41:03 +01:00
time_segments_type = config["TIME_SEGMENTS"]["TYPE"],
2020-09-14 20:21:36 +02:00
pid = "{pid}"
output:
2020-12-03 00:41:03 +01:00
segments_file = "data/interim/time_segments/{pid}_time_segments.csv",
segments_labels_file = "data/interim/time_segments/{pid}_time_segments_labels.csv",
script:
2021-03-23 00:15:13 +01:00
"../src/data/datetime/process_time_segments.R"
2020-10-19 21:07:12 +02:00
rule phone_readable_datetime:
2019-10-24 22:08:05 +02:00
input:
2020-10-19 21:07:12 +02:00
sensor_input = "data/raw/{pid}/phone_{sensor}_raw.csv",
2021-03-05 23:49:37 +01:00
time_segments = "data/interim/time_segments/{pid}_time_segments.csv",
pid_file = "data/external/participant_files/{pid}.yaml",
tzcodes_file = input_tzcodes_file,
2019-10-24 22:08:05 +02:00
params:
2021-03-05 23:49:37 +01:00
device_type = "phone",
timezone_parameters = config["TIMEZONE"],
pid = "{pid}",
2020-12-03 00:41:03 +01:00
time_segments_type = config["TIME_SEGMENTS"]["TYPE"],
include_past_periodic_segments = config["TIME_SEGMENTS"]["INCLUDE_PAST_PERIODIC_SEGMENTS"]
2019-10-24 22:08:05 +02:00
output:
2020-10-19 21:07:12 +02:00
"data/raw/{pid}/phone_{sensor}_with_datetime.csv"
2019-10-24 22:08:05 +02:00
script:
2021-03-05 23:49:37 +01:00
"../src/data/datetime/readable_datetime.R"
2019-11-05 18:34:22 +01:00
2020-11-25 01:12:16 +01:00
rule phone_yielded_timestamps:
2019-11-05 18:34:22 +01:00
input:
2020-11-25 01:12:16 +01:00
all_sensors = expand("data/raw/{{pid}}/{sensor}_raw.csv", sensor = map(str.lower, config["PHONE_DATA_YIELD"]["SENSORS"]))
params:
sensors = config["PHONE_DATA_YIELD"]["SENSORS"] # not used but needed so the rule is triggered if this array changes
2019-11-05 18:34:22 +01:00
output:
2020-11-25 01:12:16 +01:00
"data/interim/{pid}/phone_yielded_timestamps.csv"
2019-11-05 18:34:22 +01:00
script:
2020-11-25 01:12:16 +01:00
"../src/data/phone_yielded_timestamps.R"
2020-11-25 01:12:16 +01:00
rule phone_yielded_timestamps_with_datetime:
2020-10-07 17:51:31 +02:00
input:
2020-11-25 01:12:16 +01:00
sensor_input = "data/interim/{pid}/phone_yielded_timestamps.csv",
2021-03-05 23:49:37 +01:00
time_segments = "data/interim/time_segments/{pid}_time_segments.csv",
pid_file = "data/external/participant_files/{pid}.yaml",
tzcodes_file = input_tzcodes_file,
2020-11-25 01:12:16 +01:00
params:
2021-03-05 23:49:37 +01:00
device_type = "phone",
timezone_parameters = config["TIMEZONE"],
pid = "{pid}",
2020-12-03 00:41:03 +01:00
time_segments_type = config["TIME_SEGMENTS"]["TYPE"],
include_past_periodic_segments = config["TIME_SEGMENTS"]["INCLUDE_PAST_PERIODIC_SEGMENTS"]
2020-10-07 17:51:31 +02:00
output:
2020-11-25 01:12:16 +01:00
"data/interim/{pid}/phone_yielded_timestamps_with_datetime.csv"
2020-10-07 17:51:31 +02:00
script:
2021-03-05 23:49:37 +01:00
"../src/data/datetime/readable_datetime.R"
2020-10-07 17:51:31 +02:00
rule unify_ios_android:
input:
sensor_data = "data/raw/{pid}/{sensor}_with_datetime.csv",
participant_info = "data/external/participant_files/{pid}.yaml"
params:
sensor = "{sensor}",
output:
"data/raw/{pid}/{sensor}_with_datetime_unified.csv"
script:
2019-12-10 00:23:00 +01:00
"../src/data/unify_ios_android.R"
rule process_phone_locations_types:
2019-12-10 00:23:00 +01:00
input:
2020-10-19 21:07:12 +02:00
locations = "data/raw/{pid}/phone_locations_raw.csv",
phone_sensed_timestamps = "data/interim/{pid}/phone_yielded_timestamps.csv",
2019-12-10 00:23:00 +01:00
params:
2020-10-19 21:07:12 +02:00
consecutive_threshold = config["PHONE_LOCATIONS"]["FUSED_RESAMPLED_CONSECUTIVE_THRESHOLD"],
time_since_valid_location = config["PHONE_LOCATIONS"]["FUSED_RESAMPLED_TIME_SINCE_VALID_LOCATION"],
locations_to_use = config["PHONE_LOCATIONS"]["LOCATIONS_TO_USE"]
2019-12-10 00:23:00 +01:00
output:
2020-10-19 21:07:12 +02:00
"data/interim/{pid}/phone_locations_processed.csv"
2019-12-10 00:23:00 +01:00
script:
"../src/data/process_location_types.R"
2020-01-15 23:18:10 +01:00
rule phone_locations_processed_with_datetime:
2020-10-07 17:51:31 +02:00
input:
2020-10-19 21:07:12 +02:00
sensor_input = "data/interim/{pid}/phone_locations_processed.csv",
2021-03-05 23:49:37 +01:00
time_segments = "data/interim/time_segments/{pid}_time_segments.csv",
pid_file = "data/external/participant_files/{pid}.yaml",
tzcodes_file = input_tzcodes_file,
2020-10-07 17:51:31 +02:00
params:
2021-03-05 23:49:37 +01:00
device_type = "phone",
timezone_parameters = config["TIMEZONE"],
pid = "{pid}",
2020-12-03 00:41:03 +01:00
time_segments_type = config["TIME_SEGMENTS"]["TYPE"],
include_past_periodic_segments = config["TIME_SEGMENTS"]["INCLUDE_PAST_PERIODIC_SEGMENTS"]
2020-10-07 17:51:31 +02:00
output:
2020-10-19 21:07:12 +02:00
"data/interim/{pid}/phone_locations_processed_with_datetime.csv"
2020-10-07 17:51:31 +02:00
script:
2021-03-05 23:49:37 +01:00
"../src/data/datetime/readable_datetime.R"
2020-10-07 17:51:31 +02:00
rule phone_locations_processed_with_datetime_with_home:
input:
sensor_input = "data/interim/{pid}/phone_locations_processed_with_datetime.csv"
params:
dbscan_eps = config["PHONE_LOCATIONS"]["HOME_INFERENCE"]["DBSCAN_EPS"],
dbscan_minsamples = config["PHONE_LOCATIONS"]["HOME_INFERENCE"]["DBSCAN_MINSAMPLES"],
threshold_static = config["PHONE_LOCATIONS"]["HOME_INFERENCE"]["THRESHOLD_STATIC"],
clustering_algorithm = config["PHONE_LOCATIONS"]["HOME_INFERENCE"]["CLUSTERING_ALGORITHM"]
output:
"data/interim/{pid}/phone_locations_processed_with_datetime_with_home.csv"
script:
"../src/data/infer_home_location.py"
rule resample_episodes:
input:
"data/interim/{pid}/{sensor}_episodes.csv"
output:
"data/interim/{pid}/{sensor}_episodes_resampled.csv"
script:
"../src/features/utils/resample_episodes.R"
rule resample_episodes_with_datetime:
2020-01-15 23:18:10 +01:00
input:
sensor_input = "data/interim/{pid}/{sensor}_episodes_resampled.csv",
2021-03-05 23:49:37 +01:00
time_segments = "data/interim/time_segments/{pid}_time_segments.csv",
pid_file = "data/external/participant_files/{pid}.yaml",
tzcodes_file = input_tzcodes_file,
2020-01-15 23:18:10 +01:00
params:
2021-03-05 23:49:37 +01:00
device_type = lambda wildcards: wildcards.sensor.split("_")[0],
timezone_parameters = config["TIMEZONE"],
pid = "{pid}",
2020-12-03 00:41:03 +01:00
time_segments_type = config["TIME_SEGMENTS"]["TYPE"],
include_past_periodic_segments = config["TIME_SEGMENTS"]["INCLUDE_PAST_PERIODIC_SEGMENTS"]
2020-01-15 23:18:10 +01:00
output:
"data/interim/{pid}/{sensor}_episodes_resampled_with_datetime.csv"
2020-01-15 23:18:10 +01:00
script:
2021-03-05 23:49:37 +01:00
"../src/data/datetime/readable_datetime.R"
rule phone_application_categories:
input:
"data/raw/{pid}/phone_applications_{type}_with_datetime.csv"
params:
catalogue_source = lambda wildcards: config["PHONE_APPLICATIONS_" + str(wildcards.type).upper()]["APPLICATION_CATEGORIES"]["CATALOGUE_SOURCE"],
catalogue_file = lambda wildcards: config["PHONE_APPLICATIONS_" + str(wildcards.type).upper()]["APPLICATION_CATEGORIES"]["CATALOGUE_FILE"],
update_catalogue_file = lambda wildcards: config["PHONE_APPLICATIONS_" + str(wildcards.type).upper()]["APPLICATION_CATEGORIES"]["UPDATE_CATALOGUE_FILE"],
scrape_missing_genres = lambda wildcards: config["PHONE_APPLICATIONS_" + str(wildcards.type).upper()]["APPLICATION_CATEGORIES"]["SCRAPE_MISSING_CATEGORIES"]
output:
"data/raw/{pid}/phone_applications_{type}_with_datetime_with_categories.csv"
script:
"../src/data/application_categories.R"
2021-03-09 22:42:02 +01:00
rule pull_wearable_data:
input: unpack(pull_wearable_data_input_with_mutation_scripts)
2020-10-22 19:08:52 +02:00
params:
2021-03-09 22:42:02 +01:00
data_configuration = lambda wildcards: config[wildcards.device_type.upper() +"_DATA_STREAMS"][config[wildcards.device_type.upper() +"_DATA_STREAMS"]["USE"]],
device_type = "{device_type}",
sensor = "{device_type}" + "_" + "{sensor}",
pid = "{pid}",
2021-03-13 00:14:49 +01:00
tables = lambda wildcards: config[wildcards.device_type.upper() + "_" + str(wildcards.sensor).upper()]["CONTAINER"],
2021-03-09 22:42:02 +01:00
wildcard_constraints:
device_type="(empatica|fitbit)"
2020-10-22 19:08:52 +02:00
output:
2021-03-09 22:42:02 +01:00
"data/raw/{pid}/{device_type}_{sensor}_raw.csv"
2020-10-22 19:08:52 +02:00
script:
2021-03-09 22:42:02 +01:00
"../src/data/streams/pull_wearable_data.R"
2021-03-09 17:20:21 +01:00
rule fitbit_readable_datetime:
input:
2021-03-09 17:20:21 +01:00
sensor_input = "data/raw/{pid}/fitbit_{sensor}_raw.csv",
time_segments = "data/interim/time_segments/{pid}_time_segments.csv",
pid_file = "data/external/participant_files/{pid}.yaml",
tzcodes_file = input_tzcodes_file,
params:
2021-03-09 17:20:21 +01:00
device_type = "fitbit",
timezone_parameters = config["TIMEZONE"],
pid = "{pid}",
time_segments_type = config["TIME_SEGMENTS"]["TYPE"],
include_past_periodic_segments = config["TIME_SEGMENTS"]["INCLUDE_PAST_PERIODIC_SEGMENTS"]
output:
2021-03-09 17:20:21 +01:00
"data/raw/{pid}/fitbit_{sensor}_with_datetime.csv"
script:
2021-03-09 17:20:21 +01:00
"../src/data/datetime/readable_datetime.R"
2020-12-15 02:30:34 +01:00
rule empatica_readable_datetime:
input:
sensor_input = "data/raw/{pid}/empatica_{sensor}_raw.csv",
time_segments = "data/interim/time_segments/{pid}_time_segments.csv",
pid_file = "data/external/participant_files/{pid}.yaml",
tzcodes_file = input_tzcodes_file,
2020-12-15 02:30:34 +01:00
params:
device_type = "empatica",
timezone_parameters = config["TIMEZONE"],
pid = "{pid}",
2020-12-15 02:30:34 +01:00
time_segments_type = config["TIME_SEGMENTS"]["TYPE"],
include_past_periodic_segments = config["TIME_SEGMENTS"]["INCLUDE_PAST_PERIODIC_SEGMENTS"]
output:
"data/raw/{pid}/empatica_{sensor}_with_datetime.csv"
script:
"../src/data/datetime/readable_datetime.R"