def test_rsp_rrv():
rsp90 = nk.rsp_simulate(duration=60,
sampling_rate=1000,
respiratory_rate=90,
random_state=42)
rsp110 = nk.rsp_simulate(duration=60,
sampling_rate=1000,
respiratory_rate=110,
random_state=42)
cleaned90 = nk.rsp_clean(rsp90, sampling_rate=1000)
_, peaks90 = nk.rsp_peaks(cleaned90)
rsp_rate90 = nk.rsp_rate(peaks90, desired_length=len(rsp90))
cleaned110 = nk.rsp_clean(rsp110, sampling_rate=1000)
_, peaks110 = nk.rsp_peaks(cleaned110)
rsp_rate110 = nk.rsp_rate(peaks110, desired_length=len(rsp110))
rsp90_rrv = nk.rsp_rrv(rsp_rate90, peaks90)
rsp110_rrv = nk.rsp_rrv(rsp_rate110, peaks110)
assert np.array(rsp90_rrv["RRV_SDBB"]) < np.array(rsp110_rrv["RRV_SDBB"])
assert np.array(rsp90_rrv["RRV_RMSSD"]) < np.array(rsp110_rrv["RRV_RMSSD"])
assert np.array(rsp90_rrv["RRV_SDSD"]) < np.array(rsp110_rrv["RRV_SDSD"])
# assert np.array(rsp90_rrv["RRV_pNN50"]) == np.array(rsp110_rrv["RRV_pNN50"]) == np.array(rsp110_rrv["RRV_pNN20"]) == np.array(rsp90_rrv["RRV_pNN20"]) == 0
# assert np.array(rsp90_rrv["RRV_TINN"]) < np.array(rsp110_rrv["RRV_TINN"])
# assert np.array(rsp90_rrv["RRV_HTI"]) > np.array(rsp110_rrv["RRV_HTI"])
assert np.array(rsp90_rrv["RRV_HF"]) < np.array(rsp110_rrv["RRV_HF"])
assert np.array(rsp90_rrv["RRV_LF"]) < np.array(rsp110_rrv["RRV_LF"])
def test_rsp_rate():
rsp = nk.rsp_simulate(duration=120, sampling_rate=1000,
respiratory_rate=15, method="sinusoidal", noise=0)
rsp_cleaned = nk.rsp_clean(rsp, sampling_rate=1000)
signals, info = nk.rsp_peaks(rsp_cleaned)
# Test with dictionary.
test_length = 30
rate = nk.rsp_rate(peaks=info, sampling_rate=1000,
desired_length=test_length)
assert rate.shape == (test_length, )
assert np.abs(rate.mean() - 15) < 0.2
# Test with DataFrame.
rate = nk.rsp_rate(signals, sampling_rate=1000)
assert rate.shape == (signals.shape[0], )
assert np.abs(rate.mean() - 15) < 0.2
def test_rsp_rate():
rsp = nk.rsp_simulate(duration=120, sampling_rate=1000,
respiratory_rate=15)
rsp_cleaned = nk.rsp_clean(rsp, sampling_rate=1000)
signals, info = nk.rsp_findpeaks(rsp_cleaned, sampling_rate=1000)
# vary desired_lenght over tests
# test with peaks only
test_length = 30
data = nk.rsp_rate(info["RSP_Peaks"], sampling_rate=1000,
desired_length=test_length)
assert data.shape == (test_length, 2)
assert np.abs(data["RSP_Rate"].mean() - 15) < 0.2
assert np.abs(data["RSP_Period"].mean() - 4) < 0.1
# test with peaks and troughs passed in separately
test_length = 300
data = nk.rsp_rate(peaks=info["RSP_Peaks"], troughs=info["RSP_Troughs"],
sampling_rate=1000, desired_length=test_length)
assert data.shape == (test_length, 3)
assert np.abs(data["RSP_Rate"].mean() - 15) < 0.2
assert np.abs(data["RSP_Period"].mean() - 4) < 0.1
assert np.abs(data["RSP_Amplitude"].mean() - 2086) < 0.5
# test with DataFrame containing peaks and troughs
data = nk.rsp_rate(signals, sampling_rate=1000)
assert data.shape == (signals.shape[0], 3)
assert np.abs(data["RSP_Rate"].mean() - 15) < 0.2
assert np.abs(data["RSP_Period"].mean() - 4) < 0.1
assert np.abs(data["RSP_Amplitude"].mean() - 2087) < 0.5
# test with dict containing peaks and troughs
test_length = 30000
data = nk.rsp_rate(info, sampling_rate=1000, desired_length=test_length)
assert data.shape == (test_length, 3)
assert np.abs(data["RSP_Rate"].mean() - 15) < 0.2
assert np.abs(data["RSP_Period"].mean() - 4) < 0.1
assert np.abs(data["RSP_Amplitude"].mean() - 2087) < 0.5
def rsp_custom_process(distorted, info, detrend_position="First", detrend_method="polynomial", detrend_order=0, detrend_regularization=500, detrend_alpha=0.75, filter_type="None", filter_order=5, filter_lowcut=None, filter_highcut=None):
sampling_rate = info["Sampling_Rate"][0]
if detrend_position in ["First", 'Both']:
distorted = nk.signal_detrend(distorted,
method=detrend_method,
order=detrend_order,
regularization=detrend_regularization,
alpha=detrend_alpha)
if filter_type != "None":
distorted = nk.signal_filter(signal=distorted,
sampling_rate=sampling_rate,
lowcut=filter_lowcut,
highcut=filter_highcut,
method=filter_type,
order=filter_order)
if detrend_position in ["Second", 'Both']:
distorted = nk.signal_detrend(distorted,
method=detrend_method,
order=int(detrend_order),
regularization=detrend_regularization,
alpha=detrend_alpha)
cleaned = distorted
extrema_signal, _ = nk.rsp_findpeaks(distorted, outlier_threshold=0)
try:
rate = nk.rsp_rate(peaks=extrema_signal, sampling_rate=sampling_rate)
except ValueError:
rate = np.full(len(distorted), np.nan)
info["Detrend_Method"] = [detrend_method]
info["Detrend_Order"] = [detrend_order]
info["Detrend_Regularization"] = [detrend_regularization]
info["Detrend_Alpha"] = [detrend_alpha]
info["Detrend_Position"] = [detrend_position]
info["Filter_Method"] = [filter_type]
if filter_type in ["Butterworth", "Bessel"]:
info["Filter_Type"] = [filter_type + "_" + str(filter_order)]
else:
info["Filter_Type"] = [filter_type]
info["Filter_Order"] = [filter_order]
info["Filter_Low"] = [filter_lowcut]
info["Filter_High"] = [filter_highcut]
if filter_lowcut is None and filter_highcut is None:
info["Filter_Band"] = "None"
else:
info["Filter_Band"] = [str(np.round(filter_lowcut, 3)) + ", " + str(np.round(filter_highcut, 3))]
return rate, info, cleaned
def rsp_custom_process(distorted,
info,
detrend_position="First",
detrend_order=0,
filter_order=5,
filter_lowcut=None,
filter_highcut=2):
sampling_rate = info["Sampling_Rate"][0]
if detrend_position == "First":
distorted = nk.signal_detrend(distorted, order=detrend_order)
if filter_lowcut == 0:
actual_filter_lowcut = None
else:
actual_filter_lowcut = filter_lowcut
distorted = nk.signal_filter(signal=distorted,
sampling_rate=sampling_rate,
lowcut=actual_filter_lowcut,
highcut=filter_highcut,
method="butterworth",
butterworth_order=filter_order)
if detrend_position == "Second":
distorted = nk.signal_detrend(distorted, order=detrend_order)
extrema_signal, _ = nk.rsp_findpeaks(distorted, outlier_threshold=0.3)
try:
rate = nk.rsp_rate(peaks=extrema_signal,
sampling_rate=sampling_rate)["RSP_Rate"]
except ValueError:
rate = np.full(len(distorted), np.nan)
info["Detrend_Order"] = [detrend_order]
info["Detrend_Position"] = [detrend_position]
info["Filter_Order"] = [filter_order]
info["Filter_Low"] = [filter_lowcut]
info["Filter_High"] = [filter_highcut]
return rate, info