Add statistic features for empatica accelerometer
parent
5f5f19866f
commit
3bb0230bac
12
Snakefile
12
Snakefile
|
@ -294,12 +294,12 @@ for provider in config["EMPATICA_ACCELEROMETER"]["PROVIDERS"].keys():
|
||||||
suffixes = get_zip_suffixes(pid)
|
suffixes = get_zip_suffixes(pid)
|
||||||
files_to_compute.extend(expand("data/raw/{pid}/empatica_accelerometer_unzipped_{suffix}.csv", pid=pid, suffix=suffixes))
|
files_to_compute.extend(expand("data/raw/{pid}/empatica_accelerometer_unzipped_{suffix}.csv", pid=pid, suffix=suffixes))
|
||||||
files_to_compute.extend(expand("data/raw/{pid}/empatica_accelerometer_raw_{suffix}.csv", pid=pid, suffix=suffixes))
|
files_to_compute.extend(expand("data/raw/{pid}/empatica_accelerometer_raw_{suffix}.csv", pid=pid, suffix=suffixes))
|
||||||
# files_to_compute.extend(expand("data/raw/{pid}/empatica_accelerometer_joined.csv", pid=config["PIDS"]))
|
files_to_compute.extend(expand("data/raw/{pid}/empatica_accelerometer_joined.csv", pid=config["PIDS"]))
|
||||||
# files_to_compute.extend(expand("data/raw/{pid}/empatica_accelerometer_with_datetime.csv", pid=config["PIDS"]))
|
files_to_compute.extend(expand("data/raw/{pid}/empatica_accelerometer_with_datetime.csv", pid=config["PIDS"]))
|
||||||
# files_to_compute.extend(expand("data/interim/{pid}/empatica_accelerometer_features/empatica_accelerometer_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["EMPATICA_ACCELEROMETER"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
|
files_to_compute.extend(expand("data/interim/{pid}/empatica_accelerometer_features/empatica_accelerometer_{language}_{provider_key}.csv", pid=config["PIDS"], language=config["EMPATICA_ACCELEROMETER"]["PROVIDERS"][provider]["SRC_LANGUAGE"].lower(), provider_key=provider.lower()))
|
||||||
# files_to_compute.extend(expand("data/processed/features/{pid}/empatica_accelerometer.csv", pid=config["PIDS"]))
|
files_to_compute.extend(expand("data/processed/features/{pid}/empatica_accelerometer.csv", pid=config["PIDS"]))
|
||||||
# files_to_compute.extend(expand("data/processed/features/{pid}/all_sensor_features.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")
|
files_to_compute.append("data/processed/features/all_participants/all_sensor_features.csv")
|
||||||
|
|
||||||
for provider in config["EMPATICA_HEARTRATE"]["PROVIDERS"].keys():
|
for provider in config["EMPATICA_HEARTRATE"]["PROVIDERS"].keys():
|
||||||
if config["EMPATICA_HEARTRATE"]["PROVIDERS"][provider]["COMPUTE"]:
|
if config["EMPATICA_HEARTRATE"]["PROVIDERS"][provider]["COMPUTE"]:
|
||||||
|
|
|
@ -427,8 +427,8 @@ EMPATICA_ACCELEROMETER:
|
||||||
TABLE: acc
|
TABLE: acc
|
||||||
PROVIDERS:
|
PROVIDERS:
|
||||||
DBDP:
|
DBDP:
|
||||||
COMPUTE: True
|
COMPUTE: False
|
||||||
FEATURES: []
|
FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
|
||||||
SRC_FOLDER: "dbdp" # inside src/features/empatica_accelerometer
|
SRC_FOLDER: "dbdp" # inside src/features/empatica_accelerometer
|
||||||
SRC_LANGUAGE: "python"
|
SRC_LANGUAGE: "python"
|
||||||
|
|
||||||
|
|
|
@ -3,19 +3,34 @@ import numpy as np
|
||||||
|
|
||||||
def dbdp_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
|
def dbdp_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
|
||||||
|
|
||||||
sensor_data = pd.read_csv(sensor_data_files["sensor_data"])
|
acc_data = pd.read_csv(sensor_data_files["sensor_data"])
|
||||||
requested_features = provider["FEATURES"]
|
requested_features = provider["FEATURES"]
|
||||||
# name of the features this function can compute
|
# name of the features this function can compute
|
||||||
base_features_names = [] # ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
|
base_features_names = ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
|
||||||
# the subset of requested features this function can compute
|
# the subset of requested features this function can compute
|
||||||
features_to_compute = list(set(requested_features) & set(base_features_names))
|
features_to_compute = list(set(requested_features) & set(base_features_names))
|
||||||
|
|
||||||
features = pd.DataFrame(columns=["local_segment"] + features_to_compute)
|
acc_features = pd.DataFrame(columns=["local_segment"] + features_to_compute)
|
||||||
if not sensor_data.empty:
|
if not acc_data.empty:
|
||||||
sensor_data = filter_data_by_segment(sensor_data, time_segment)
|
acc_data = filter_data_by_segment(acc_data, time_segment)
|
||||||
|
|
||||||
if not sensor_data.empty:
|
if not acc_data.empty:
|
||||||
features = pd.DataFrame()
|
acc_features = pd.DataFrame()
|
||||||
|
# get magnitude related features: magnitude = sqrt(x^2+y^2+z^2)
|
||||||
|
magnitude = acc_data.apply(lambda row: np.sqrt(row["x"] ** 2 + row["y"] ** 2 + row["z"] ** 2), axis=1)
|
||||||
|
acc_data = acc_data.assign(magnitude = magnitude.values)
|
||||||
|
|
||||||
|
if "maxmagnitude" in features_to_compute:
|
||||||
|
acc_features["maxmagnitude"] = acc_data.groupby(["local_segment"])["magnitude"].max()
|
||||||
|
if "minmagnitude" in features_to_compute:
|
||||||
|
acc_features["minmagnitude"] = acc_data.groupby(["local_segment"])["magnitude"].min()
|
||||||
|
if "avgmagnitude" in features_to_compute:
|
||||||
|
acc_features["avgmagnitude"] = acc_data.groupby(["local_segment"])["magnitude"].mean()
|
||||||
|
if "medianmagnitude" in features_to_compute:
|
||||||
|
acc_features["medianmagnitude"] = acc_data.groupby(["local_segment"])["magnitude"].median()
|
||||||
|
if "stdmagnitude" in features_to_compute:
|
||||||
|
acc_features["stdmagnitude"] = acc_data.groupby(["local_segment"])["magnitude"].std()
|
||||||
|
|
||||||
return features
|
acc_features = acc_features.reset_index()
|
||||||
|
|
||||||
|
return acc_features
|
Loading…
Reference in New Issue