def features(Signal=None, SamplingRate=1000., Filter={}):
"""
Retrieves relevant ECG signal features.
Kwargs:
Signal (array): input ECG signal.
SamplingRate (float): Sampling frequency (Hz).
Filter (dict): Filter parameters.
Kwrvals:
R (array): ECG R-peak indexes (or instants in seconds if sampling rate is defined)
mean (float): mean
std (float): standard deviation
var (float): variance
skew (ndarry): skewness
kurtosis (array): kurtosis
ad (float): absolute deviation
Configurable fields:{"name": "ecg.features", "config": {"SamplingRate": "1000."}, "inputs": ["Signal", "Filter"], "outputs": ["R", "mean", "std", "var", "skew", "kurtosis", "ad"]}
See Also:
filt
models.hamilton
tls.statsf
Notes:
Example:
References:
.. [1]
"""
# Check
if Signal is None:
raise TypeError, "An input signal is needed."
if Filter:
Filter.update({'Signal': Signal})
if not Filter.has_key('SamplingRate'):
Filter.update({'SamplingRate': SamplingRate})
Signal = filt(**Filter)['Signal']
# Init
kwrvals = {}
# Feature Extraction
res = ecg(Signal=Signal, SamplingRate=SamplingRate)
for k in res:
kwrvals[k] = res[k]
res = tls.statsf(Signal=Signal)
for k in res:
kwrvals[k] = res[k]
# Out
return kwrvals
def features(Signal=None, SamplingRate=1000., Filter={}):
"""
Retrieves relevant BVP signal features.
Kwargs:
Signal (array): input signal.
SamplingRate (float): sampling frequency (Hz).
Filter (dict): filter parameters.
Kwrvals:
Signal (array): output filtered signal (see notes 1).
Amplitude (array): signal pulses amplitudes (in the units of the input signal).(TODO)
Onset (array): indexes (or instants in seconds, see notes 2.b) of the pulses onsets.
Peak (array): indexes (or instants in seconds, see notes 2.b) of the pulses peaks. (TODO)
DicroticNotch (array): indexes (or instants in seconds, see notes 2.b) of the pulses dicrotic notchs. (TODO)
IBI (array): Inter-Beat Intervals in msec (see notes 2.a).
HR (array): Instantaneous Heart Rates in b.p.m. (see notes 2.a).
mean (float): mean
std (float): standard deviation
var (float): variance
skew (ndarry): skewness
kurtosis (array): kurtosis
ad (float): absolute deviation
Configurable fields:{"name": "bvp.features", "config": {"SamplingRate": "1000."}, "inputs": ["Signal", "Filter"], "outputs": ["Signal", "Amplitude", "Onset", "Peak", "DicroticNotch", "IBI", "HR", "mean", "std", "var", "skew", "kurtosis", "ad"]}
See Also:
filt
pulse
tls.statsf
Notes:
1 - If a filter is given as a parameter, then the returned keyworded values dict has a 'Signal' key.
2 - If the sampling rate is defined, then:
a) the returned keyworded values dict has keys 'IBI' and 'HR'.
b) keys 'onset', 'peak', and 'DicroticNotch' are converted to instants of occurrence in seconds.
Example:
bvp = ...
SamplingRate = ...
res = pulse(Signal=bvp, SamplingRate=SamplingRate)
References:
.. [1]
"""
# Check
if Signal is None:
raise TypeError, "An input signal is needed."
if Filter:
Filter.update({'Signal': Signal})
if not Filter.has_key('SamplingRate'):
Filter.update({'SamplingRate': SamplingRate})
Signal = filt(**Filter)['Signal']
# Init
kwrvals = {}
# Feature Extraction
res = pulse(Signal=Signal, SamplingRate=SamplingRate)
for k in res:
kwrvals[k] = res[k]
res = tls.statsf(Signal=Signal)
for k in res:
kwrvals[k] = res[k]
# Out
return kwrvals
def features(Signal=None, SamplingRate=1000., Filter={}):
"""
Retrieves relevant EDA signal features.
Kwargs:
Signal (array): input EDA signal
SamplingRate (float): sampling frequency (Hz)
Filter (dict): Filter parameters
Kwrvals:
Signal (array): output filtered signal (see notes 1)
Amplitude (array): signal pulses amplitudes (in the units of the input signal)
Onset (array): indexes (or instants in seconds, see notes 2.a) of the SCRs onsets
Peak (array): indexes (or instants in seconds, see notes 2.a) of the SCRs peaks
Rise (array): SCRs rise times (in seconds)
HalfRecovery (array): SCRs half-recovery times (in seconds)
mean (float): mean
std (float): standard deviation
var (float): variance
skew (ndarry): skewness
kurtosis (array): kurtosis
ad (float): absolute deviation
Configurable fields:{"name": "eda.features", "config": {"SamplingRate": "1000."}, "inputs": ["Signal", "Filter"], "outputs": ["Signal", "Amplitude", "Onset", "Peak", "Rise", "HalfRecovery", "mean", "std", "var", "skew", "kurtosis", "ad"]}
See Also:
filt
models.basicSCR
tls.statsf
Notes:
1 - If a filter is given as a parameter, then the returned keyworded values dict has a 'Signal' key.
2 - If the sampling rate is defined, then:
a) keys 'onset', and 'peak' are converted to instants of occurrence in seconds.
Example:
References:
.. [1]
"""
# Check
if Signal is None:
raise TypeError, "An input signal is needed."
if Filter:
Filter.update({'Signal': Signal})
if not Filter.has_key('SamplingRate'):
Filter.update({'SamplingRate': SamplingRate})
Signal = filt(**Filter)['Signal']
# Init
kwrvals = {}
# Feature Extraction
res = scr(Signal=Signal, SamplingRate=SamplingRate)
for k in res:
kwrvals[k] = res[k]
res = tls.statsf(Signal=Signal)
for k in res:
kwrvals[k] = res[k]
# Out
return kwrvals