Cr-features corrections for ACC and TEMP sensors
Primoz
parent
5638367999
commit
f62a1302dd
12
config.yaml
12
config.yaml
|
|
@ -477,11 +477,11 @@ EMPATICA_ACCELEROMETER:
|
|||
CONTAINER: ACC
|
||||
PROVIDERS:
|
||||
DBDP:
|
||||
COMPUTE: False
|
||||
COMPUTE: True
|
||||
FEATURES: ["maxmagnitude", "minmagnitude", "avgmagnitude", "medianmagnitude", "stdmagnitude"]
|
||||
SRC_SCRIPT: src/features/empatica_accelerometer/dbdp/main.py
|
||||
CR:
|
||||
COMPUTE: False
|
||||
COMPUTE: True
|
||||
FEATURES: ["fqHighestPeakFreqs", "fqHighestPeaks", "fqEnergyFeat", "fqEntropyFeat", "fqHistogramBins","fqAbsMean", "fqSkewness", "fqKurtosis", "fqInterquart", # Freq features
|
||||
"meanLow", "areaLow", "totalAbsoluteAreaBand", "totalMagnitudeBand", "entropyBand", "skewnessBand", "kurtosisBand",
|
||||
"postureDistanceLow", "absoluteMeanBand", "absoluteAreaBand", "quartilesBand", "interQuartileRangeBand", "varianceBand",
|
||||
|
|
@ -523,7 +523,7 @@ EMPATICA_TEMPERATURE:
|
|||
"sumOfSquareComponents"]
|
||||
WINDOWS:
|
||||
COMPUTE: True
|
||||
WINDOW_LENGTH: 90 # specify window length in seconds
|
||||
WINDOW_LENGTH: 600 # specify window length in seconds
|
||||
SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'max', 'min']
|
||||
SRC_SCRIPT: src/features/empatica_temperature/cr/main.py
|
||||
|
||||
|
|
@ -544,7 +544,7 @@ EMPATICA_ELECTRODERMAL_ACTIVITY:
|
|||
'signalOverallChange', 'changeDuration', 'changeRate', 'significantIncrease', 'significantDecrease']
|
||||
WINDOWS:
|
||||
COMPUTE: True
|
||||
WINDOW_LENGTH: 80 # specify window length in seconds
|
||||
WINDOW_LENGTH: 300 # specify window length in seconds
|
||||
SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'max', 'min']
|
||||
SRC_SCRIPT: src/features/empatica_electrodermal_activity/cr/main.py
|
||||
|
||||
|
|
@ -562,7 +562,7 @@ EMPATICA_BLOOD_VOLUME_PULSE:
|
|||
'VLF', 'LF', 'LFnorm', 'HF', 'HFnorm', 'LF/HF', 'fullIntegral'] # Freq features
|
||||
WINDOWS:
|
||||
COMPUTE: True
|
||||
WINDOW_LENGTH: 10 # specify window length in seconds
|
||||
WINDOW_LENGTH: 300 # specify window length in seconds
|
||||
SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'max', 'min']
|
||||
SRC_SCRIPT: src/features/empatica_blood_volume_pulse/cr/main.py
|
||||
|
||||
|
|
@ -580,7 +580,7 @@ EMPATICA_INTER_BEAT_INTERVAL:
|
|||
'VLF', 'LF', 'LFnorm', 'HF', 'HFnorm', 'LF/HF', 'fullIntegral'] # Freq features
|
||||
WINDOWS:
|
||||
COMPUTE: True
|
||||
WINDOW_LENGTH: 2000 # specify window length in seconds
|
||||
WINDOW_LENGTH: 300 # specify window length in seconds
|
||||
SECOND_ORDER_FEATURES: ['mean', 'median', 'sd', 'max', 'min']
|
||||
SRC_SCRIPT: src/features/empatica_inter_beat_interval/cr/main.py
|
||||
|
||||
|
|
|
|||
|
|
@ -111,7 +111,7 @@ dependencies:
|
|||
- biosppy==0.8.0
|
||||
- cached-property==1.5.2
|
||||
- configargparse==0.15.1
|
||||
- cr-features==0.1.8
|
||||
- cr-features==0.1.9
|
||||
- cycler==0.11.0
|
||||
- decorator==4.4.2
|
||||
- fonttools==4.33.2
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@ def extract_second_order_features(intraday_features, so_features_names):
|
|||
if "mean" in so_features_names:
|
||||
so_features = pd.concat([so_features, intraday_features.drop("level_1", axis=1).groupby(["local_segment"]).mean().add_suffix("_SO_mean")], axis=1)
|
||||
if "median" in so_features_names:
|
||||
so_features = pd.concat([so_features, intraday_features.drop("level_1", axis=1).groupby(["local_segment"]).mean().add_suffix("_SO_median")], axis=1)
|
||||
so_features = pd.concat([so_features, intraday_features.drop("level_1", axis=1).groupby(["local_segment"]).median().add_suffix("_SO_median")], axis=1)
|
||||
if "sd" in so_features_names:
|
||||
so_features = pd.concat([so_features, intraday_features.drop("level_1", axis=1).groupby(["local_segment"]).std().add_suffix("_SO_sd")], axis=1)
|
||||
if "max" in so_features_names:
|
||||
|
|
|
|||
|
|
@ -2,19 +2,11 @@ import pandas as pd
|
|||
from scipy.stats import entropy
|
||||
|
||||
from cr_features.helper_functions import convert_to2d, accelerometer_features, frequency_features
|
||||
from cr_features.calculate_features import calculate_features
|
||||
from cr_features.calculate_features_old import calculateFeatures
|
||||
from cr_features_helper_methods import get_sample_rate, extract_second_order_features
|
||||
|
||||
import sys
|
||||
|
||||
def get_sample_rate(data):
|
||||
try:
|
||||
timestamps_diff = data['timestamp'].diff().dropna().mean()
|
||||
except:
|
||||
raise Exception("Error occured while trying to get the mean sample rate from the data.")
|
||||
|
||||
return int(1000/timestamps_diff)
|
||||
|
||||
def extract_acc_features_from_intraday_data(acc_intraday_data, features, window_length, time_segment, filter_data_by_segment):
|
||||
acc_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
|
||||
|
||||
|
|
@ -30,18 +22,18 @@ def extract_acc_features_from_intraday_data(acc_intraday_data, features, window_
|
|||
# apply methods from calculate features module
|
||||
if window_length is None:
|
||||
acc_intraday_features = \
|
||||
acc_intraday_data.groupby('local_segment').apply(lambda x: calculate_features( \
|
||||
acc_intraday_data.groupby('local_segment').apply(lambda x: calculateFeatures( \
|
||||
convert_to2d(x['double_values_0'], x.shape[0]), \
|
||||
convert_to2d(x['double_values_1'], x.shape[0]), \
|
||||
convert_to2d(x['double_values_2'], x.shape[0]), \
|
||||
fs=sample_rate, feature_names=features))
|
||||
fs=sample_rate, featureNames=features))
|
||||
else:
|
||||
acc_intraday_features = \
|
||||
acc_intraday_data.groupby('local_segment').apply(lambda x: calculate_features( \
|
||||
acc_intraday_data.groupby('local_segment').apply(lambda x: calculateFeatures( \
|
||||
convert_to2d(x['double_values_0'], window_length*sample_rate), \
|
||||
convert_to2d(x['double_values_1'], window_length*sample_rate), \
|
||||
convert_to2d(x['double_values_2'], window_length*sample_rate), \
|
||||
fs=sample_rate, feature_names=features))
|
||||
fs=sample_rate, featureNames=features))
|
||||
|
||||
acc_intraday_features.reset_index(inplace=True)
|
||||
|
||||
|
|
|
|||
|
|
@ -21,8 +21,6 @@ def extract_bvp_features_from_intraday_data(bvp_intraday_data, features, window_
|
|||
|
||||
if not bvp_intraday_data.empty:
|
||||
sample_rate = get_sample_rate(bvp_intraday_data)
|
||||
|
||||
print(bvp_intraday_data.shape)
|
||||
|
||||
bvp_intraday_data = filter_data_by_segment(bvp_intraday_data, time_segment)
|
||||
|
||||
|
|
@ -30,8 +28,6 @@ def extract_bvp_features_from_intraday_data(bvp_intraday_data, features, window_
|
|||
|
||||
bvp_intraday_features = pd.DataFrame()
|
||||
|
||||
print(features)
|
||||
|
||||
# apply methods from calculate features module
|
||||
if window_length is None:
|
||||
bvp_intraday_features = \
|
||||
|
|
|
|||
|
|
@ -6,19 +6,11 @@ from cr_features.calculate_features import calculate_features
|
|||
from cr_features_helper_methods import get_sample_rate, extract_second_order_features
|
||||
|
||||
|
||||
def getSampleRate(data):
|
||||
try:
|
||||
timestamps_diff = data['timestamp'].diff().dropna().mean()
|
||||
except:
|
||||
raise Exception("Error occured while trying to get the mean sample rate from the data.")
|
||||
|
||||
return int(1000/timestamps_diff)
|
||||
|
||||
def extract_eda_features_from_intraday_data(eda_intraday_data, features, window_length, time_segment, filter_data_by_segment):
|
||||
eda_intraday_features = pd.DataFrame(columns=["local_segment"] + features)
|
||||
|
||||
if not eda_intraday_data.empty:
|
||||
sample_rate = getSampleRate(eda_intraday_data)
|
||||
sample_rate = get_sample_rate(eda_intraday_data)
|
||||
|
||||
eda_intraday_data = filter_data_by_segment(eda_intraday_data, time_segment)
|
||||
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ import pandas as pd
|
|||
from scipy.stats import entropy
|
||||
|
||||
from cr_features.helper_functions import convert_to2d, generic_features
|
||||
from cr_features.calculate_features import calculate_features
|
||||
from cr_features.calculate_features_old import calculateFeatures
|
||||
from cr_features_helper_methods import get_sample_rate, extract_second_order_features
|
||||
|
||||
import sys
|
||||
|
|
@ -31,11 +31,11 @@ def extract_temp_features_from_intraday_data(temperature_intraday_data, features
|
|||
if window_length is None:
|
||||
temperature_intraday_features = \
|
||||
temperature_intraday_data.groupby('local_segment').apply(\
|
||||
lambda x: calculate_features(convert_to2d(x['temperature'], x.shape[0]), fs=sample_rate, feature_names=features))
|
||||
lambda x: calculateFeatures(convert_to2d(x['temperature'], x.shape[0]), fs=sample_rate, featureNames=features))
|
||||
else:
|
||||
temperature_intraday_features = \
|
||||
temperature_intraday_data.groupby('local_segment').apply(\
|
||||
lambda x: calculate_features(convert_to2d(x['temperature'], window_length*sample_rate), fs=sample_rate, feature_names=features))
|
||||
lambda x: calculateFeatures(convert_to2d(x['temperature'], window_length*sample_rate), fs=sample_rate, featureNames=features))
|
||||
|
||||
temperature_intraday_features.reset_index(inplace=True)
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue