86 lines
4.2 KiB
Python
86 lines
4.2 KiB
Python
import pandas as pd
|
|
from scipy.stats import entropy
|
|
|
|
from CalculatingFeatures.helper_functions import convert3DEmpaticaToArray, convertInputInto2d, gsrFeatureNames
|
|
from CalculatingFeatures.calculate_features import calculateFeatures
|
|
|
|
|
|
def getSampleRate(data):
|
|
try:
|
|
timestamps_diff = data['timestamp'].iloc[1] - data['timestamp'].iloc[0]
|
|
except:
|
|
raise Exception("Error occured while trying to get the sample rate from the first two sequential timestamps.")
|
|
|
|
return 1000/timestamps_diff
|
|
|
|
def extractAccFeaturesFromIntradayData(acc_intraday_data, features, time_segment, filter_data_by_segment):
|
|
acc_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
|
|
|
|
if not acc_intraday_data.empty:
|
|
sample_rate = getSampleRate(acc_intraday_data)
|
|
|
|
acc_intraday_data = filter_data_by_segment(acc_intraday_data, time_segment)
|
|
|
|
if not acc_intraday_data.empty:
|
|
|
|
acc_intraday_features = pd.DataFrame()
|
|
|
|
# apply methods from calculate features module
|
|
acc_intraday_features = \
|
|
acc_intraday_data.groupby('local_segment').apply(\
|
|
lambda x: calculateFeatures(convertInputInto2d(x['accelerometer'], x.shape[0]), fs=sample_rate, featureNames=features))
|
|
|
|
acc_intraday_features.reset_index(inplace=True)
|
|
|
|
return acc_intraday_features
|
|
|
|
|
|
def cf_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
|
|
eda_intraday_data = pd.read_csv(sensor_data_files["sensor_data"])
|
|
|
|
requested_intraday_features = provider["FEATURES"]
|
|
# name of the features this function can compute
|
|
base_intraday_features_names = gsrFeatureNames
|
|
# the subset of requested features this function can compute
|
|
intraday_features_to_compute = list(set(requested_intraday_features) & set(base_intraday_features_names))
|
|
|
|
# extract features from intraday data
|
|
eda_intraday_features = extractAccFeaturesFromIntradayData(eda_intraday_data,
|
|
intraday_features_to_compute, time_segment,
|
|
filter_data_by_segment)
|
|
|
|
return eda_intraday_features
|
|
|
|
def dbdp_features(sensor_data_files, time_segment, provider, filter_data_by_segment, *args, **kwargs):
|
|
|
|
acc_data = pd.read_csv(sensor_data_files["sensor_data"])
|
|
requested_features = provider["FEATURES"]
|
|
# name of the features this function can compute
|
|
base_features_names = ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
|
|
# the subset of requested features this function can compute
|
|
features_to_compute = list(set(requested_features) & set(base_features_names))
|
|
|
|
acc_features = pd.DataFrame(columns=["local_segment"] + features_to_compute)
|
|
if not acc_data.empty:
|
|
acc_data = filter_data_by_segment(acc_data, time_segment)
|
|
|
|
if not acc_data.empty:
|
|
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["double_values_0"] ** 2 + row["double_values_1"] ** 2 + row["double_values_2"] ** 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()
|
|
|
|
acc_features = acc_features.reset_index()
|
|
|
|
return acc_features |