Integrate phone_speech into rapids pipeline.

sociality-task
Primoz 2023-01-17 14:00:14 +00:00
parent 3e6b34babc
commit 75b054d358
3 changed files with 25 additions and 3 deletions

View File

@ -178,9 +178,10 @@ for provider in config["PHONE_SPEECH"]["PROVIDERS"].keys():
if config["PHONE_SPEECH"]["PROVIDERS"][provider]["COMPUTE"]: if config["PHONE_SPEECH"]["PROVIDERS"][provider]["COMPUTE"]:
files_to_compute.extend(expand("data/raw/{pid}/phone_speech_raw.csv",pid=config["PIDS"])) files_to_compute.extend(expand("data/raw/{pid}/phone_speech_raw.csv",pid=config["PIDS"]))
files_to_compute.extend(expand("data/raw/{pid}/phone_speech_with_datetime.csv",pid=config["PIDS"])) files_to_compute.extend(expand("data/raw/{pid}/phone_speech_with_datetime.csv",pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_speech_clean.csv",pid=config["PIDS"]))
files_to_compute.extend(expand("data/interim/{pid}/phone_speech_features/phone_speech_{language}_{provider_key}.csv",pid=config["PIDS"],language=get_script_language(config["PHONE_SPEECH"]["PROVIDERS"][provider]["SRC_SCRIPT"]),provider_key=provider.lower())) files_to_compute.extend(expand("data/interim/{pid}/phone_speech_features/phone_speech_{language}_{provider_key}.csv",pid=config["PIDS"],language=get_script_language(config["PHONE_SPEECH"]["PROVIDERS"][provider]["SRC_SCRIPT"]),provider_key=provider.lower()))
files_to_compute.extend(expand("data/processed/features/{pid}/phone_speech.csv", pid=config["PIDS"])) files_to_compute.extend(expand("data/processed/features/{pid}/phone_speech.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")
# We can delete these if's as soon as we add feature PROVIDERS to any of these sensors # We can delete these if's as soon as we add feature PROVIDERS to any of these sensors
if isinstance(config["PHONE_APPLICATIONS_CRASHES"]["PROVIDERS"], dict): if isinstance(config["PHONE_APPLICATIONS_CRASHES"]["PROVIDERS"], dict):

View File

@ -347,12 +347,12 @@ rule esm_features:
rule phone_speech_python_features: rule phone_speech_python_features:
input: input:
sensor_data = "data/interim/{pid}/phone_speech_with_datetime.csv", sensor_data = "data/raw/{pid}/phone_speech_with_datetime.csv",
time_segments_labels = "data/interim/time_segments/{pid}_time_segments_labels.csv" time_segments_labels = "data/interim/time_segments/{pid}_time_segments_labels.csv"
params: params:
provider = lambda wildcards: config["PHONE_SPEECH"]["PROVIDERS"][wildcards.provider_key.upper()], provider = lambda wildcards: config["PHONE_SPEECH"]["PROVIDERS"][wildcards.provider_key.upper()],
provider_key = "{provider_key}", provider_key = "{provider_key}",
sensor_key = "phone_speech", sensor_key = "phone_speech"
output: output:
"data/interim/{pid}/phone_speech_features/phone_speech_python_{provider_key}.csv" "data/interim/{pid}/phone_speech_features/phone_speech_python_{provider_key}.csv"
script: script:

View File

@ -349,3 +349,24 @@ PHONE_WIFI_VISIBLE:
COLUMN_MAPPINGS: COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data SCRIPTS: # List any python or r scripts that mutate your raw data
PHONE_SPEECH:
ANDROID:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
SPEECH_PROPORTION: speech_proportion
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data
IOS:
RAPIDS_COLUMN_MAPPINGS:
TIMESTAMP: timestamp
DEVICE_ID: device_id
SPEECH_PROPORTION: speech_proportion
MUTATION:
COLUMN_MAPPINGS:
SCRIPTS: # List any python or r scripts that mutate your raw data