def test_hrv_time():
ecg_slow = nk.ecg_simulate(duration=60,
sampling_rate=1000,
heart_rate=70,
random_state=42)
ecg_fast = nk.ecg_simulate(duration=60,
sampling_rate=1000,
heart_rate=110,
random_state=42)
_, peaks_slow = nk.ecg_process(ecg_slow, sampling_rate=1000)
_, peaks_fast = nk.ecg_process(ecg_fast, sampling_rate=1000)
hrv_slow = nk.hrv_time(peaks_slow, sampling_rate=1000)
hrv_fast = nk.hrv_time(peaks_fast, sampling_rate=1000)
assert np.all(hrv_fast["HRV_RMSSD"] < hrv_slow["HRV_RMSSD"])
assert np.all(hrv_fast["HRV_MeanNN"] < hrv_slow["HRV_MeanNN"])
assert np.all(hrv_fast["HRV_SDNN"] < hrv_slow["HRV_SDNN"])
assert np.all(hrv_fast["HRV_CVNN"] < hrv_slow["HRV_CVNN"])
assert np.all(hrv_fast["HRV_CVSD"] < hrv_slow["HRV_CVSD"])
assert np.all(hrv_fast["HRV_MedianNN"] < hrv_slow["HRV_MedianNN"])
assert np.all(hrv_fast["HRV_MadNN"] < hrv_slow["HRV_MadNN"])
assert np.all(hrv_fast["HRV_MCVNN"] < hrv_slow["HRV_MCVNN"])
assert np.all(hrv_fast["HRV_pNN50"] == hrv_slow["HRV_pNN50"])
assert np.all(hrv_fast["HRV_pNN20"] < hrv_slow["HRV_pNN20"])
assert np.all(hrv_fast["HRV_TINN"] < hrv_slow["HRV_TINN"])
assert np.all(hrv_fast["HRV_HTI"] > hrv_slow["HRV_HTI"])
def showData(ecg, data, sampling_rate):
#Funkcja umożliwiająca wyświetlenie przeanalizowanych danych
a.clear()
a.plot(ecg[0], ecg[1])
a.plot(data["R_peaks"][0], data["R_peaks"][1], "ro", label = "R peaks")
a.plot(data["P_peaks"][0], data["P_peaks"][1], "bv", label = "P peaks")
a.plot(data["Q_peaks"][0], data["Q_peaks"][1], "kv", label = "Q peaks")
a.plot(data["S_peaks"][0], data["S_peaks"][1], "wv", label = "S peaks")
a.plot(data["T_peaks"][0], data["T_peaks"][1], "yv", label = "T peaks")
a.plot(data["P_onsets"][0], data["P_onsets"][1], "b^", label = "P onsets")
a.plot(data["P_offsets"][0], data["P_offsets"][1], "b^", label = "P offsets")
a.plot(data["R_onsets"][0], data["R_onsets"][1], "r^", label = "R onsets")
a.plot(data["R_offsets"][0], data["R_offsets"][1], "r^", label = "R offsets")
a.plot(data["T_onsets"][0], data["T_onsets"][1], "y^", label = "T onsets")
a.plot(data["T_offsets"][0], data["T_offsets"][1], "y^", label = "T offsets")
plt.xlabel('time [s]')
plt.ylabel('voltage [mV]')
plt.legend()
canvas.draw()
hrv_time = nk.hrv_time(data["R_peaks"][1], sampling_rate=sampling_rate, show=True)
hrv_non = nk.hrv_nonlinear(data["R_peaks"][1], sampling_rate=sampling_rate, show=True)
plt.figure(2).show()
plt.figure(3).show()
def get_HRVs_values(data, header_data):
filter_lowcut = 0.001
filter_highcut = 15.0
filter_order = 1
tmp_hea = header_data[0].split(' ')
ptID = tmp_hea[0]
num_leads = int(tmp_hea[1])
sample_Fs = int(tmp_hea[2])
gain_lead = np.zeros(num_leads)
for ii in range(num_leads):
tmp_hea = header_data[ii + 1].split(' ')
gain_lead[ii] = int(tmp_hea[2].split('/')[0])
# for testing, we included the mean age of 57 if the age is a NaN
# This value will change as more data is being released
for iline in header_data:
if iline.startswith('#Age'):
tmp_age = iline.split(': ')[1].strip()
age = int(tmp_age if tmp_age != 'NaN' else 57)
elif iline.startswith('#Sex'):
tmp_sex = iline.split(': ')[1]
if tmp_sex.strip() == 'Female':
sex = 1
else:
sex = 0
elif iline.startswith('#Dx'):
label = iline.split(': ')[1].split(',')[0]
signal = data[1]
gain = gain_lead[1]
ecg_signal = nk.ecg_clean(signal * gain,
sampling_rate=sample_Fs,
method="biosppy")
_, rpeaks = nk.ecg_peaks(ecg_signal, sampling_rate=sample_Fs)
hrv_time = nk.hrv_time(rpeaks, sampling_rate=sample_Fs)
# hrv_non = nk.hrv_nonlinear(rpeaks, sampling_rate=sample_Fs)
try:
signal_peak, waves_peak = nk.ecg_delineate(ecg_signal,
rpeaks,
sampling_rate=sample_Fs)
p_peaks = waves_peak['ECG_P_Peaks']
except ValueError:
print('Exception raised!')
pass
p_peaks = np.asarray(p_peaks, dtype=float)
p_peaks = p_peaks[~np.isnan(p_peaks)]
p_peaks = [int(a) for a in p_peaks]
mean_P_Peaks = np.mean([signal[w] for w in p_peaks])
hrv_time['mean_P_Peaks'] = mean_P_Peaks
hrv_time['age'] = age
hrv_time['label'] = label
# df = pd.concat([hrv_time, hrv_non], axis=1)
return hrv_time
def nothing():
# Quality check algorithms
# qcqrs = run_qc(signal=data.filtered, epoch_len=15, fs=fs, algorithm="averageQRS", show_plot=False)
# Removing invalid data based on QC thresholdling
#t = threshold_averageqrs_data(signal=data.filtered, qc_signal=qc, epoch_len=10, fs=fs, pad_val=0,
# thresh=.95, method='exclusive', plot_data=False)
p, pc = find_peaks(signal=data.filtered,
fs=fs,
show_plot=True,
peak_method="pantompkins1985",
clean_method='neurokit')
hrv = nk.hrv_time(peaks=pc, sampling_rate=data.sample_rate, show=False)
freq = nk.hrv_frequency(peaks=pc,
sampling_rate=data.sample_rate,
show=True)
# df_events, info = test_ecg_process_func(signal=data.filtered[15000:15000+1250], start=0, n_samples=int(10*125), fs=fs, plot_builtin=True, plot_events=False)
# heartbeats = segment_ecg(signal=d, fs=fs)
waves, sigs = nk.ecg_delineate(ecg_cleaned=data.filtered,
rpeaks=pc,
sampling_rate=data.sample_rate,
method='dwt',
show=False)
intervals, ecg_rate, ecg_hrv = nk.ecg_intervalrelated()
# TODO
# Organizing
# Signal quality in organized section --> able to pick which algorithm
def process_bvp(bvp, show_fig=False):
"""
Compute BVP signal features (more info: https://neurokit2.readthedocs.io/en/latest/functions.html#module-neurokit2.ppg).
Compute HRV indices (more info: https://neurokit2.readthedocs.io/en/latest/functions.html#module-neurokit2.hrv)
Parameters
----------
bvp : dict [timestamp : value]
EDA signal.
Returns
-------
bvp_signals : DataFrame
bvp_info : dict
"""
bvp_signals, bvp_info = nk.ppg_process(bvp['value'], sampling_rate=64)
# First 5 seconds of the signal.
# Find peaks
peaks = bvp_signals['PPG_Peaks'][:320]
# Compute HRV indices
time_hrv = nk.hrv_time(peaks, sampling_rate=64, show=show_fig)
hrv_base = time_hrv
hrv_base['type'] = 'base'
# The rest part of the signal.
# Find peaks
peaks = bvp_signals['PPG_Peaks'][320:]
# Compute HRV indices
phase_hrv = nk.hrv_frequency(peaks, sampling_rate=64, show=show_fig)
time_hrv = nk.hrv_time(peaks, sampling_rate=64, show=show_fig)
nonlinear_hrv = nk.hrv_nonlinear(peaks, sampling_rate=64, show=show_fig)
hrv_indices = pd.concat([phase_hrv, time_hrv, nonlinear_hrv], axis=1)
hrv_indices['type'] = 'stimul'
hrv_indices = pd.concat([hrv_indices, hrv_base])
return bvp_signals, bvp_info, hrv_indices
def my_hrv(peaks, sampling_rate):
result = []
result.append(nk.hrv_time(peaks, sampling_rate=sampling_rate))
result.append(
nk.hrv_frequency(peaks,
sampling_rate=sampling_rate,
vlf=(0.01, 0.04),
lf=(0.04, 0.15),
hf=(0.15, 0.4),
vhf=(0.4, 1)))
return pd.concat(result, axis=1)
import warnings
warnings.filterwarnings("ignore")
ecg_leads, ecg_labels, fs, ecg_names = load_references(
) # Importiere EKG-Dateien, zugehörige Diagnose, Sampling-Frequenz (Hz) und Name # Sampling-Frequenz 300 Hz
features = np.array([])
detectors = Detectors(fs) # Initialisierung des QRS-Detektors
labels = np.array([])
for idx, ecg_lead in enumerate(ecg_leads):
if (ecg_labels[idx] == "N") or (ecg_labels[idx] == "A"):
peaks, info = nk.ecg_peaks(ecg_lead, sampling_rate=fs)
peaks = peaks.astype('float64')
hrv = nk.hrv_time(peaks, sampling_rate=fs)
hrv = hrv.astype('float64')
features = np.append(features, [
hrv['HRV_CVNN'], hrv['HRV_CVSD'], hrv['HRV_HTI'], hrv['HRV_IQRNN'],
hrv['HRV_MCVNN'], hrv['HRV_MadNN'], hrv['HRV_MeanNN'],
hrv['HRV_MedianNN'], hrv['HRV_RMSSD'], hrv['HRV_SDNN'],
hrv['HRV_SDSD'], hrv['HRV_TINN'], hrv['HRV_pNN20'],
hrv['HRV_pNN50']
])
features = features.astype('float64')
labels = np.append(labels, ecg_labels[idx])
features = features.reshape(int(len(features) / 14), 14)
x = np.isnan(features)
# replacing NaN values with 0
features[x] = 0
def signals_analysis(signals, is_out=False, is_show=False, out_path="figs"):
"""
数据的分析 主要是特征参数的获取
:param signals: 初步处理过的数据
:param is_out:
:param is_show:
:param out_path:
:return:
"""
sampling_rate = signals["Sampling Rate"]
feature_points = signals["Feature Points"]
cleaned_pulses = feature_points["Cleaned Pulses"]
peaks = feature_points["Peaks"]
title = "Time Analysis"
hrv_time = nk.hrv_time(peaks, sampling_rate, show=is_show)
if is_out:
no = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
out_name = os.path.join("outputs",
str(out_path) + "___" + no + title + ".png")
plt.savefig(out_name, dpi=300)
if is_show:
plt.show()
title = "Frequency Analysis"
hrv_freq = nk.hrv_frequency(peaks, sampling_rate, show=is_show)
if is_out:
no = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
out_name = os.path.join("outputs",
str(out_path) + "___" + no + title + ".png")
plt.savefig(out_name, dpi=300)
if is_show:
plt.show()
title = "Nonlinear Analysis"
hrv_nonlinear = nk.hrv_nonlinear(peaks, sampling_rate, show=is_show)
if is_out:
no = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
out_name = os.path.join("outputs",
str(out_path) + "___" + no + title + ".png")
plt.savefig(out_name, dpi=300)
if is_show:
plt.show()
# 傅里叶分析 对应给的文章
xFFT = np.abs(np.fft.rfft(cleaned_pulses) / len(cleaned_pulses))
xFFT = xFFT[:600]
xFreqs = np.linspace(0, sampling_rate // 2, len(cleaned_pulses) // 2 + 1)
xFreqs = xFreqs[:600]
# 滤波处理 平滑去噪 只处理前200个信号即可
# TODO 去噪方法可以调节
cleaned_xFFT = nk.signal_smooth(xFFT, method="loess")
# 计算特征值
# F1值
cleaned_FFT = cleaned_xFFT.copy()
locmax, props = spsg.find_peaks(cleaned_xFFT)
hr_hz_index = np.argmax(cleaned_xFFT)
f1 = np.argmax(xFFT)
fmax = np.argmax(cleaned_xFFT[locmax])
cleaned_xFFT[locmax[fmax]] = np.min(cleaned_xFFT)
f2s = np.argmax(cleaned_xFFT[locmax])
if f2s - fmax != 1:
hr_hz_index = locmax[0] + int(np.sqrt(locmax[1] - locmax[0]))
# F2值
f2 = locmax[np.argmax(cleaned_xFFT[locmax])]
F1 = np.round(xFreqs[f1], 2)
F2 = np.round(xFreqs[f2], 2)
# 相位差
F2_F1 = F2 - F1
# 心率
HR_FFT = xFreqs[hr_hz_index] * 60
print(HR_FFT)
if is_show:
plt.plot(xFreqs, cleaned_FFT)
plt.scatter(xFreqs[f1],
cleaned_FFT[f1],
color="red",
label="F1 = " + str(F1) + "HZ")
plt.scatter(xFreqs[f2],
cleaned_FFT[f2],
color="orange",
label="F2 = " + str(F2) + "HZ")
plt.legend(loc="upper right")
plt.ylabel("Power")
plt.xlabel("Freq(Hz)")
title = "FFT analysis"
plt.title(title)
if is_out:
no = datetime.datetime.now().strftime("%Y%m%d%H%M%S")
out_name = os.path.join(
"outputs",
str(out_path) + "___" + no + title + ".png")
plt.savefig(out_name, dpi=300)
plt.show()
hrv_new = {
"Power": xFFT,
"Freq": cleaned_FFT,
"X": xFreqs,
"F1": F1,
"F2": F2,
"F2_F1": F2_F1,
"HR_FFT": HR_FFT
}
return {
"HRV New": hrv_new,
"HRV Time": hrv_time,
"HRV Frequency": hrv_freq,
"HRV Nonlinear": hrv_nonlinear
}
def compute_features(data, condition, sampling_rate=700, window_size=60, window_shift=0.25):
index = 0
init = time.time()
# data cleaning
## ECG
ecg_cleaned = nk.ecg_clean(data["ECG"][condition].flatten(), sampling_rate=sampling_rate)
## == OLD
# ecg_rpeaks, _ = nk.ecg_peaks(ecg_cleaned, sampling_rate=sampling_rate)
# ecg_hr = nk.signal_rate(ecg_rpeaks, sampling_rate=sampling_rate)
## ==
## EDA
## 5Hz lowpass filter
eda_highcut = 5
eda_filtered = nk.signal_filter(data['EDA'][condition].flatten(), sampling_rate=sampling_rate, highcut=eda_highcut)
eda_cleaned = nk.standardize(eda_filtered)
# TODO: not sure about the approach. cvxeda takes longer periods
# phasic_tonic = nk.eda_phasic(cleaned, sampling_rate=700, method='cvxeda')
eda_phasic_tonic = nk.eda_phasic(eda_cleaned, sampling_rate=sampling_rate)
eda_phasic_tonic['t'] = [(1 / sampling_rate) * i for i in range(eda_phasic_tonic.shape[0])]
eda_scr_peaks, scr_info = nk.eda_peaks(eda_phasic_tonic['EDA_Phasic'], sampling_rate=sampling_rate)
## EMG
## For 5 sec window signal
## More on DC Bias https://www.c-motion.com/v3dwiki/index.php/EMG:_Removing_DC_Bias
emg_lowcut = 50
emg_filtered_dc = nk.signal_filter(data['EMG'][condition].flatten(), sampling_rate=sampling_rate, lowcut=emg_lowcut)
# OR 100 Hz highpass Butterworth filter followed by a constant detrending
# filtered_dc = nk.emg_clean(chest_data_dict['EMG'][baseline].flatten(), sampling_rate=700)
## For 60 sec window signal
# 50Hz lowpass filter
emg_highcut = 50
emg_filtered = nk.signal_filter(data['EMG'][condition].flatten(), sampling_rate=sampling_rate, highcut=emg_highcut)
## Resp
## Method biosppy important to appply bandpass filter 0.1 - 0.35 Hz
resp_processed, _ = nk.rsp_process(data['Resp'][condition].flatten(), sampling_rate=sampling_rate, method='biosppy')
print('Elapsed Preprocess', str(timedelta(seconds=time.time() - init)))
init = time.time()
chest_df_5 = pd.DataFrame() # For 5 sec window size
chest_df = pd.DataFrame()
window = int(sampling_rate * window_size)
for i in range(0, data['ACC'][condition].shape[0] - window, int(sampling_rate * window_shift)):
# ACC
w_acc_data = data['ACC'][condition][i: window + i]
acc_x_mean, acc_y_mean, acc_z_mean = np.mean(w_acc_data, axis=0) # Feature
acc_x_std, acc_y_std, acc_z_std = np.std(w_acc_data, axis=0) # Feature
acc_x_peak, acc_y_peak, acc_z_peak = np.amax(w_acc_data, axis=0) # Feature
acc_x_absint, acc_y_absint, acc_z_absint = np.abs(np.trapz(w_acc_data, axis=0)) # Feature
xyz = np.sum(w_acc_data, axis=0)
xyz_mean = np.mean(xyz) # Feature
xyz_std = np.std(xyz) # Feature
xyz_absint = np.abs(np.trapz(xyz)) # Feature
# == OLD
# ## ECG
# w_ecg_rpeaks = ecg_rpeaks[i: window + i]
# # HR
# w_ecg_hr = ecg_hr[i: window + i]
# hr_mean = np.mean(w_ecg_hr) # Feature
# hr_std = np.std(w_ecg_hr) # Feature
# # HRV Time-domain Indices
# # HRV_MeanNN
# # HRV_SDNN
# # HRV_pNN50
# # HRV_RMSSD -> Root mean square of the HRV
# # HRV_HTI -> Triangular interpolation index
# hrv_time = nk.hrv_time(w_ecg_rpeaks, sampling_rate=sampling_rate, show=False)
# hrv_mean = hrv_time.loc[0, 'HRV_MeanNN'] # Feature
# hrv_std = hrv_time.loc[0, 'HRV_SDNN'] # Feature
# # TODO: NN50
# # hrv_NN50 =
# hrv_pNN50 = hrv_time.loc[0, 'HRV_pNN50'] # Feature
# hrv_TINN = hrv_time.loc[0, 'HRV_HTI'] # Feature
# hrv_rms = hrv_time.loc[0, 'HRV_RMSSD'] # Feature
# # HRV Frequency-domain Indices
# # TODO: get NaN values within windows (*)
# # HRV_ULF *
# # HRV_LF *
# # HRV_HF
# # HRV_VHF
# # HRV_LFHF - Ratio LF/HF *
# # HRV_LFn *
# # HRV_HFn
# hrv_freq = nk.hrv_frequency(w_ecg_rpeaks, sampling_rate=sampling_rate, ulf=(0.01, 0.04), lf=(0.04, 0.15), hf=(0.15, 0.4), vhf=(0.4, 1.))
# hrv_ULF = hrv_freq.loc[0, 'HRV_ULF'] # Feature
# hrv_LF = hrv_freq.loc[0, 'HRV_LF'] # Feature
# hrv_HF = hrv_freq.loc[0, 'HRV_HF'] # Feature
# hrv_VHF = hrv_freq.loc[0, 'HRV_VHF'] # Feature
# hrv_lf_hf_ratio = hrv_freq.loc[0, 'HRV_LFHF'] # Feature
# hrv_f_sum = np.nansum(np.hstack((hrv_ULF, hrv_LF, hrv_HF, hrv_VHF)))
# # TODO: rel_f
# # hrv_rel_f =
# hrv_LFn = hrv_freq.loc[0, 'HRV_LFn'] # Feature
# hrv_HFn = hrv_freq.loc[0, 'HRV_HFn'] # Feature
# ==
## ECG
w_ecg_cleaned = ecg_cleaned[i: window + i]
_, ecg_info = nk.ecg_peaks(w_ecg_cleaned, sampling_rate=sampling_rate)
w_ecg_rpeaks = ecg_info['ECG_R_Peaks']
ecg_nni = pyhrv.tools.nn_intervals(w_ecg_rpeaks)
# HR
rs_hr = pyhrv.time_domain.hr_parameters(ecg_nni)
hr_mean = rs_hr['hr_mean'] # Feature
hr_std = rs_hr['hr_std'] # Feature
# HRV-time
rs_hrv = pyhrv.time_domain.nni_parameters(ecg_nni)
hrv_mean = rs_hrv['nni_mean'] # Feature
hrv_std = pyhrv.time_domain.sdnn(ecg_nni)['sdnn'] # Feature
rs_nn50 = pyhrv.time_domain.nn50(ecg_nni)
hrv_NN50 = rs_nn50['nn50'] # Feature
hrv_pNN50 = rs_nn50['pnn50'] # Feature
hrv_time = nk.hrv_time(w_ecg_rpeaks, sampling_rate=sampling_rate, show=False)
hrv_TINN = hrv_time.loc[0, 'HRV_TINN'] # Feature
hrv_rms = pyhrv.time_domain.rmssd(ecg_nni)['rmssd'] # Feature
# HRV-freq
hrv_freq = pyhrv.frequency_domain.welch_psd(ecg_nni, fbands={'ulf': (0.01, 0.04), 'vlf': (0.04, 0.15), 'lf': (0.15, 0.4), 'hf': (0.4, 1)}, mode='dev')
# hrv_freq = hrv_freq.as_dict()
hrv_freq = hrv_freq[0]
hrv_ULF = hrv_freq['fft_abs'][0] # Feature
hrv_LF = hrv_freq['fft_abs'][1] # Feature
hrv_HF = hrv_freq['fft_abs'][2] # Feature
hrv_VHF = hrv_freq['fft_abs'][3] # Feature
hrv_lf_hf_ratio = hrv_freq['fft_ratio'] # Feature
hrv_f_sum = hrv_freq['fft_total'] # Feature
hrv_rel_ULF = hrv_freq['fft_rel'][0] # Feature
hrv_rel_LF = hrv_freq['fft_rel'][1] # Feature
hrv_rel_HF = hrv_freq['fft_rel'][2] # Feature
hrv_rel_VHF = hrv_freq['fft_rel'][3] # Feature
hrv_LFn = hrv_freq['fft_norm'][0] # Feature
hrv_HFn = hrv_freq['fft_norm'][1] # Feature
# EDA
w_eda_data = eda_cleaned[i: window + i]
w_eda_phasic_tonic = eda_phasic_tonic[i: window + i]
eda_mean = np.mean(w_eda_data) # Feature
eda_std = np.std(w_eda_data) # Feature
eda_min = np.amin(w_eda_data) # Feature
eda_max = np.amax(w_eda_data) # Feature
# dynamic range: https://en.wikipedia.org/wiki/Dynamic_range
eda_slope = get_slope(w_eda_data) # Feature
eda_drange = eda_max / eda_min # Feature
eda_scl_mean = np.mean(w_eda_phasic_tonic['EDA_Tonic']) # Feature
eda_scl_std = np.std(w_eda_phasic_tonic['EDA_Tonic']) # Feature
eda_scr_mean = np.mean(w_eda_phasic_tonic['EDA_Phasic']) # Feature
eda_scr_std = np.std(w_eda_phasic_tonic['EDA_Phasic']) # Feature
eda_corr_scl_t = nk.cor(w_eda_phasic_tonic['EDA_Tonic'], w_eda_phasic_tonic['t'], show=False) # Feature
eda_scr_no = eda_scr_peaks['SCR_Peaks'][i: window + i].sum() # Feature
# Sum amplitudes in SCR signal
ampl = scr_info['SCR_Amplitude'][i: window + i]
eda_ampl_sum = np.sum(ampl[~np.isnan(ampl)]) # Feature
# TODO:
# eda_t_sum =
scr_peaks, scr_properties = scisig.find_peaks(w_eda_phasic_tonic['EDA_Phasic'], height=0)
width_scr = scisig.peak_widths(w_eda_phasic_tonic['EDA_Phasic'], scr_peaks, rel_height=0)
ht_scr = scr_properties['peak_heights']
eda_scr_area = 0.5 * np.matmul(ht_scr, width_scr[1]) # Feature
# EMG
## 5sec
w_emg_data = emg_filtered_dc[i: window + i]
emg_mean = np.mean(w_emg_data) # Feature
emg_std = np.std(w_emg_data) # Feature
emg_min = np.amin(w_emg_data)
emg_max = np.amax(w_emg_data)
emg_drange = emg_max / emg_min # Feature
emg_absint = np.abs(np.trapz(w_emg_data)) # Feature
emg_median = np.median(w_emg_data) # Feature
emg_perc_10 = np.percentile(w_emg_data, 10) # Feature
emg_perc_90 = np.percentile(w_emg_data, 90) # Feature
emg_peak_freq, emg_mean_freq, emg_median_freq = get_freq_features(w_emg_data) # Features
# TODO: PSD -> energy in seven bands
# emg_psd =
## 60 sec
peaks, properties = scisig.find_peaks(emg_filtered[i: window + i], height=0)
emg_peak_no = peaks.shape[0]
emg_peak_amp_mean = np.mean(properties['peak_heights']) # Feature
emg_peak_amp_std = np.std(properties['peak_heights']) # Feature
emg_peak_amp_sum = np.sum(properties['peak_heights']) # Feature
emg_peak_amp_max = np.abs(np.amax(properties['peak_heights']))
# https://www.researchgate.net/post/How_Period_Normalization_and_Amplitude_normalization_are_performed_in_ECG_Signal
emg_peak_amp_norm_sum = np.sum(properties['peak_heights'] / emg_peak_amp_max) # Feature
# Resp
w_resp_data = resp_processed[i: window + i]
## Inhalation / Exhalation duration analysis
idx = np.nan
count = 0
duration = dict()
first = True
for j in w_resp_data[~w_resp_data['RSP_Phase'].isnull()]['RSP_Phase'].to_numpy():
if j != idx:
if first:
idx = int(j)
duration[1] = []
duration [0] = []
first = False
continue
# print('New value', j, count)
duration[idx].append(count)
idx = int(j)
count = 0
count += 1
resp_inhal_mean = np.mean(duration[1]) # Feature
resp_inhal_std = np.std(duration[1]) # Feature
resp_exhal_mean = np.mean(duration[0]) # Feature
resp_exhal_std = np.std(duration[0]) # Feature
resp_inhal_duration = w_resp_data['RSP_Phase'][w_resp_data['RSP_Phase'] == 1].count()
resp_exhal_duration = w_resp_data['RSP_Phase'][w_resp_data['RSP_Phase'] == 0].count()
resp_ie_ratio = resp_inhal_duration / resp_exhal_duration # Feature
resp_duration = resp_inhal_duration + resp_exhal_duration # Feature
resp_stretch = w_resp_data['RSP_Amplitude'].max() - w_resp_data['RSP_Amplitude'].min() # Feature
resp_breath_rate = len(duration[1]) # Feature
## Volume: area under the curve of the inspiration phase on a respiratory cycle
resp_peaks, resp_properties = scisig.find_peaks(w_resp_data['RSP_Clean'], height=0)
resp_width = scisig.peak_widths(w_resp_data['RSP_Clean'], resp_peaks, rel_height=0)
resp_ht = resp_properties['peak_heights']
resp_volume = 0.5 * np.matmul(resp_ht, resp_width[1]) # Feature
# Temp
w_temp_data = data['Temp'][condition][i: window + i].flatten()
temp_mean = np.mean(w_temp_data) # Feature
temp_std = np.std(w_temp_data) # Feature
temp_min = np.amin(w_temp_data) # Feature
temp_max = np.amax(w_temp_data) # Feature
temp_drange = temp_max / temp_min # Feature
temp_slope = get_slope(w_temp_data.ravel()) # Feature
# chest_df_5 = chest_df_5.append({
# 'ACC_x_mean': acc_x_mean, 'ACC_y_mean': acc_y_mean, 'ACC_z_mean': acc_z_mean, 'ACC_xzy_mean': xyz_mean,
# 'ACC_x_std': acc_x_std, 'ACC_y_std': acc_y_std, 'ACC_z_std': acc_z_std, 'ACC_xyz_std': xyz_std,
# 'ACC_x_absint': acc_x_absint, 'ACC_y_absint': acc_y_absint, 'ACC_z_absint': acc_z_absint, 'ACC_xyz_absint': xyz_absint,
# 'ACC_x_peak': acc_x_peak, 'ACC_y_peak': acc_y_peak, 'ACC_z_peak': acc_z_peak,
# 'EMG_mean': emg_mean, 'EMG_std': emg_std, 'EMG_drange': emg_drange, 'EMG_absint': emg_absint, 'EMG_median': emg_median, 'EMG_perc_10': emg_perc_10,
# 'EMG_perc_90': emg_perc_90, 'EMG_peak_freq': emg_peak_freq, 'EMG_mean_freq': emg_mean_freq, 'EMG_median_freq': emg_median_freq
# }, ignore_index=True)
chest_df = chest_df.append({
'ACC_x_mean': acc_x_mean, 'ACC_y_mean': acc_y_mean, 'ACC_z_mean': acc_z_mean, 'ACC_xzy_mean': xyz_mean,
'ACC_x_std': acc_x_std, 'ACC_y_std': acc_y_std, 'ACC_z_std': acc_z_std, 'ACC_xyz_std': xyz_std,
'ACC_x_absint': acc_x_absint, 'ACC_y_absint': acc_y_absint, 'ACC_z_absint': acc_z_absint, 'ACC_xyz_absint': xyz_absint,
'ACC_x_peak': acc_x_peak, 'ACC_y_peak': acc_y_peak, 'ACC_z_peak': acc_z_peak,
'ECG_hr_mean': hr_mean, 'ECG_hr_std': hr_std, 'ECG_hrv_NN50': hrv_NN50, 'ECG_hrv_pNN50': hrv_pNN50, 'ECG_hrv_TINN': hrv_TINN, 'ECG_hrv_RMS': hrv_rms,
'ECG_hrv_ULF': hrv_ULF, 'ECG_hrv_LF': hrv_LF, 'ECG_hrv_HF': hrv_HF, 'ECG_hrv_VHF': hrv_VHF, 'ECG_hrv_LFHF_ratio': hrv_lf_hf_ratio, 'ECG_hrv_f_sum': hrv_f_sum,
'ECG_hrv_rel_ULF': hrv_rel_ULF, 'ECG_hrv_rel_LF': hrv_rel_LF, 'ECG_hrv_rel_HF': hrv_rel_HF, 'ECG_hrv_rel_VHF': hrv_rel_VHF, 'ECG_hrv_LFn': hrv_LFn, 'ECG_hrv_HFn': hrv_HFn,
'EDA_mean': eda_mean, 'EDA_std': eda_std, 'EDA_mean': eda_mean, 'EDA_min': eda_min, 'EDA_max': eda_max, 'EDA_slope': eda_slope,
'EDA_drange': eda_drange, 'EDA_SCL_mean': eda_scl_mean, 'EDA_SCL_std': eda_scl_mean, 'EDA_SCR_mean': eda_scr_mean, 'EDA_SCR_std': eda_scr_std,
'EDA_corr_SCL_t': eda_corr_scl_t, 'EDA_SCR_no': eda_scr_no, 'EDA_ampl_sum': eda_ampl_sum, 'EDA_scr_area': eda_scr_area,
'EMG_mean': emg_mean, 'EMG_std': emg_std, 'EMG_drange': emg_drange, 'EMG_absint': emg_absint, 'EMG_median': emg_median, 'EMG_perc_10': emg_perc_10,
'EMG_perc_90': emg_perc_90, 'EMG_peak_freq': emg_peak_freq, 'EMG_mean_freq': emg_mean_freq, 'EMG_median_freq': emg_median_freq,
'EMG_peak_no': emg_peak_no, 'EMG_peak_amp_mean': emg_peak_amp_mean, 'EMG_peak_amp_std': emg_peak_amp_std, 'EMG_peak_amp_sum': emg_peak_amp_sum,
'EMG_peak_amp_norm_sum': emg_peak_amp_norm_sum,
'RESP_inhal_mean': resp_inhal_mean, 'RESP_inhal_std': resp_inhal_std, 'RESP_exhal_mean': resp_exhal_mean, 'RESP_exhal_std': resp_exhal_std,
'RESP_ie_ratio': resp_ie_ratio, 'RESP_duration': resp_duration, 'RESP_stretch': resp_stretch, 'RESP_breath_rate': resp_breath_rate, 'RESP_volume': resp_volume,
'TEMP_mean': temp_mean, 'TEMP_std': temp_std, 'TEMP_min': temp_min, 'TEMP_max': temp_max, 'TEMP_drange': temp_drange, 'TEMP_slope': temp_slope
}, ignore_index=True)
# index += 1
# if index % 10 == 0:
# break
print('Elapsed Process', condition.shape[0], str(timedelta(seconds=time.time() - init)))
return chest_df, chest_df_5
def process_epochs_neurokit(signal, window_len=300, jump_len=300):
t = datetime.now()
indexes = np.arange(0, len(signal), int(jump_len * data.sample_rate))
print(
f"\nRunning NeuroKit analysis in {window_len}-second windows with jump interval of {jump_len} seconds"
f"({len(indexes)} iterations)...")
# Within-epoch processing using NeuroKit to match Cardioscope output
df_nk = pd.DataFrame([[], [], [], [], [], [], [], [], [], [], [], [], [],
[], [], []]).transpose()
df_nk.columns = [
"Timestamp", "Index", "Quality", "HR", "meanRR", "sdRR", "meanNN",
"SDNN", "pNN20", 'pNN50', "VLF", "LF", "HF", "LF/HF", "LFn", "HFn"
]
print("\nProcessing data in epochs with NeuroKit2...")
for start in indexes:
print(f"{round(100*start/len(signal), 1)}%")
try:
s, i = nk.ecg_process(signal[start:start +
int(data.sample_rate * window_len)],
sampling_rate=data.sample_rate)
s = s.loc[s["ECG_R_Peaks"] == 1]
inds = [i for i in s.index]
hrv = nk.hrv_time(peaks=inds,
sampling_rate=data.sample_rate,
show=False)
freq = nk.hrv_frequency(peaks=inds,
sampling_rate=data.sample_rate,
show=False)
rr_ints = [(d2 - d1) / data.sample_rate
for d1, d2 in zip(inds[:], inds[1:])]
mean_rr = 1000 * np.mean(rr_ints)
sd_rr = 1000 * np.std(rr_ints)
out = [
data.timestamps[start], start, 100 * s["ECG_Quality"].mean(),
s["ECG_Rate"].mean().__round__(3), mean_rr, sd_rr,
hrv["HRV_MeanNN"].iloc[0], hrv["HRV_SDNN"].iloc[0],
hrv["HRV_pNN20"].iloc[0], hrv["HRV_pNN50"].iloc[0],
freq["HRV_VLF"].iloc[0], freq["HRV_LF"].iloc[0],
freq["HRV_HF"].iloc[0], freq["HRV_LFHF"].iloc[0],
freq["HRV_LFn"].iloc[0], freq["HRV_HFn"].iloc[0]
]
df_out = pd.DataFrame(out).transpose()
df_out.columns = df_nk.columns
df_nk = df_nk.append(df_out, ignore_index=True)
except (ValueError, IndexError):
out = [
data.timestamps[start], start, None, None, None, None, None,
None, None, None, None, None, None, None, None
]
df_out = pd.DataFrame(out).transpose()
df_out.columns = df_nk.columns
df_nk = df_nk.append(df_out, ignore_index=True)
t1 = datetime.now()
td = (t1 - t).total_seconds()
print(f"100% ({round(td, 1)} seconds)")
df_nk["Timestamp"] = pd.date_range(start=bf["Timestamp"].iloc[0],
freq=f"{jump_len}S",
periods=df_nk.shape[0])
return df_nk
def predict_labels(ecg_leads, fs, ecg_names, use_pretrained=False):
'''
Parameters
----------
model_name : str
Dateiname des Models. In Code-Pfad
ecg_leads : list of numpy-Arrays
EKG-Signale.
fs : float
Sampling-Frequenz der Signale.
ecg_names : list of str
eindeutige Bezeichnung für jedes EKG-Signal.
Returns
-------
predictions : list of tuples
ecg_name und eure Diagnose
'''
#------------------------------------------------------------------------------
# Euer Code ab hier
# model_name = "model.npy"
# if use_pretrained:
# model_name = "model_pretrained.npy"
# with open(model_name, 'rb') as f:
# th_opt = np.load(f) # Lade simples Model (1 Parameter)
#
# detectors = Detectors(fs) # Initialisierung des QRS-Detektors
#
# predictions = list()
#
# for idx,ecg_lead in enumerate(ecg_leads):
# r_peaks = detectors.hamilton_detector(ecg_lead) # Detektion der QRS-Komplexe
# sdnn = np.std(np.diff(r_peaks)/fs*1000)
# if sdnn < th_opt:
# predictions.append((ecg_names[idx], 'N'))
# else:
# predictions.append((ecg_names[idx], 'A'))
# if ((idx+1) % 100)==0:
# print(str(idx+1) + "\t Dateien wurden verarbeitet.")
#
#
# #------------------------------------------------------------------------------
# return predictions # Liste von Tupels im Format (ecg_name,label) - Muss unverändert bleiben!
# Load test-dataset
# from tqdm import tqdm
# import os
# from os import listdir
# from os.path import isfile, join
# import cv2
#####
# THRESHOLD = 0.5
# def precision(y_true, y_pred, threshold_shift=0.5 - THRESHOLD):
# # just in case
# y_pred = K.clip(y_pred, 0, 1)
# # shifting the prediction threshold from .5 if needed
# y_pred_bin = K.round(y_pred + threshold_shift)
# tp = K.sum(K.round(y_true * y_pred_bin)) + K.epsilon()
# fp = K.sum(K.round(K.clip(y_pred_bin - y_true, 0, 1)))
# precision = tp / (tp + fp)
# return precision
# def recall(y_true, y_pred, threshold_shift=0.5 - THRESHOLD):
# # just in case
# y_pred = K.clip(y_pred, 0, 1)
# # shifting the prediction threshold from .5 if needed
# y_pred_bin = K.round(y_pred + threshold_shift)
# tp = K.sum(K.round(y_true * y_pred_bin)) + K.epsilon()
# fn = K.sum(K.round(K.clip(y_true - y_pred_bin, 0, 1)))
# recall = tp / (tp + fn)
# return recall
# def fbeta(y_true, y_pred, threshold_shift=0.5 - THRESHOLD):
# beta = 1
# # just in case
# y_pred = K.clip(y_pred, 0, 1)
# # shifting the prediction threshold from .5 if needed
# y_pred_bin = K.round(y_pred + threshold_shift)
# tp = K.sum(K.round(y_true * y_pred_bin)) + K.epsilon()
# fp = K.sum(K.round(K.clip(y_pred_bin - y_true, 0, 1)))
# fn = K.sum(K.round(K.clip(y_true - y_pred, 0, 1)))
# precision = tp / (tp + fp)
# recall = tp / (tp + fn)
# beta_squared = beta ** 2
# return (beta_squared + 1) * (precision * recall) / (beta_squared * precision + recall)
#####
# ecg_leads,ecg_labels,fs,ecg_names = load_references('../test/') # Importiere EKG-Dateien, zugehörige Diagnose, Sampling-Frequenz (Hz) und Name # Sampling-Frequenz 300 Hz
# test_set = ecg_leads
# if os.path.exists("../test/ecg_images"):
# print("File exists.")
# else:
# os.mkdir("../test/ecg_images")
# for i in tqdm(range(len(test_set))):
# data = ecg_leads[i].reshape(len(ecg_leads[i]), 1)
# plt.figure(figsize=(60, 5))
# plt.xlim(0, len(ecg_leads[i]))
# # plt.plot(data, color='black', linewidth=0.1)
# plt.savefig('../test/ecg_images/{}.png'.format(ecg_names[i]))
# onlyfiles = [f for f in listdir("../test/ecg_images") if isfile(join("../test/ecg_images", f))]
# df = pd.read_csv("../test/REFERENCE.csv", header=None)
# x = []
# y = []
# name_test =[]
# for i in range(len(onlyfiles)):
# if (df.iloc[i][1] == "N") or (df.iloc[i][1] == "A"):
# image = cv2.imread("../test/ecg_images/{}".format(onlyfiles[i]))
# gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# resize_x = cv2.resize(gray, (128, 1024))
# reshape_x = np.asarray(resize_x).reshape(resize_x.shape[0], resize_x.shape[1], 1)
# x.append(reshape_x)
# y.append(df.iloc[i][1])
# name_test.append(df.iloc[i])
# for n, i in enumerate(y):
# if i == "N":
# y[n] = 0
# elif i == "A":
# y[n] = 1
# x = np.asarray(x).astype(int)
# y = np.asarray(y).astype(int)
# test_images, test_labels = x, y
# # Normalize pixel values to be between 0 and 1
# test_images = test_images / 255.0
# import keras
# import tensorflow as tf
# from keras.models import load_model
# model = load_model('./pred_model.h5', custom_objects={'fbeta': fbeta})
# model = tf.keras.models.load_model('./pred_model.h5', custom_objects={'fbeta': fbeta})
# model = tf.keras.models.load_model('./pred_model.h5', custom_objects={'fbeta': fbeta})
# converter = tf.lite.TFLiteConverter.from_keras_model(model) # .from_saved_model(saved_model_dir)
# tflite_model = converter.convert()
# open("model.tflite", "wb").write(tflite_model)
# pred_labels = model.predict_classes(test_images)
# pred_labels = np.asarray(pred_labels).astype('str')
# for n, i in enumerate(pred_labels):
# if i == '0':
# pred_labels[n] = "N"
# elif i == '1':
# pred_labels[n] = "A"
#-------------------------------------------------------------------------------
''' Gradient Boosting Classfier '''
# import warnings
# warnings.filterwarnings("ignore")
#
# test_features = np.array([])
#
# for idx, ecg_lead in enumerate(ecg_leads):
# peaks, info = nk.ecg_peaks(ecg_lead, sampling_rate= 200)
# peaks = peaks.astype('float64')
# hrv = nk.hrv_time(peaks, sampling_rate= fs)
# hrv = hrv.astype('float64')
# test_features = np.append(test_features, [hrv['HRV_CVNN'], hrv['HRV_CVSD'], hrv['HRV_HTI'], hrv['HRV_IQRNN'], hrv['HRV_MCVNN'], hrv['HRV_MadNN'], hrv['HRV_MeanNN'], hrv['HRV_MedianNN'], hrv['HRV_RMSSD'], hrv['HRV_SDNN'], hrv['HRV_SDSD'], hrv['HRV_TINN'], hrv['HRV_pNN20'],hrv['HRV_pNN50'] ])
# test_features = test_features.astype('float64')
#
# test_features= test_features.reshape(int(len(test_features)/14), 14)
# x = np.isnan(test_features)
# # replacing NaN values with 0
# test_features[x] = 0
#
# X_test = test_features
#
# # with trained model to predict
# loaded_model = joblib.load('GradientBoostingClassifier')
# pred_labels = loaded_model.predict(X_test)
# # a list of tuple
# predictions = list()
#
# for idx in range(len(X_test)):
# predictions.append((ecg_names[idx], pred_labels[idx]))
#------------------------------------------------------------------
''' Convolutional Neural Network '''
# import warnings
# warnings.filterwarnings("ignore")
# from tensorflow.keras.models import load_model
# from tensorflow.keras.optimizers import SGD
# import numpy as np
#
# ###
# def f1(y_true, y_pred):
# def recall(y_true, y_pred):
# """Recall metric.
#
# Only computes a batch-wise average of recall.
#
# Computes the recall, a metric for multi-label classification of
# how many relevant items are selected.
# """
# true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
# possible_positives = K.sum(K.round(K.clip(y_true, 0, 1)))
# recall = true_positives / (possible_positives + K.epsilon())
# return recall
#
# def precision(y_true, y_pred):
# """Precision metric.
#
# Only computes a batch-wise average of precision.
#
# Computes the precision, a metric for multi-label classification of
# how many selected items are relevant.
# """
# true_positives = K.sum(K.round(K.clip(y_true * y_pred, 0, 1)))
# predicted_positives = K.sum(K.round(K.clip(y_pred, 0, 1)))
# precision = true_positives / (predicted_positives + K.epsilon())
# return precision
#
# precision = precision(y_true, y_pred)
# recall = recall(y_true, y_pred)
# return 2 * ((precision * recall) / (precision + recall + K.epsilon()))
#
# def f1_weighted(true, pred): # shapes (batch, 4)
#
# # for metrics include these two lines, for loss, don't include them
# # these are meant to round 'pred' to exactly zeros and ones
# # predLabels = K.argmax(pred, axis=-1)
# # pred = K.one_hot(predLabels, 4)
#
# ground_positives = K.sum(true, axis=0) + K.epsilon() # = TP + FN
# pred_positives = K.sum(pred, axis=0) + K.epsilon() # = TP + FP
# true_positives = K.sum(true * pred, axis=0) + K.epsilon() # = TP
# # all with shape (4,)
#
# precision = true_positives / pred_positives
# recall = true_positives / ground_positives
# # both = 1 if ground_positives == 0 or pred_positives == 0
# # shape (4,)
#
# f1 = 2 * (precision * recall) / (precision + recall + K.epsilon())
# # still with shape (4,)
#
# weighted_f1 = f1 * ground_positives / K.sum(ground_positives)
# weighted_f1 = K.sum(weighted_f1)
#
# return 1 - weighted_f1 # for metrics, return only 'weighted_f1'
# ###
#
# cnn_best_model = load_model('cnn_best_model.h5', custom_objects={'f1_weighted': f1_weighted, 'f1': f1})
#
# sgd = SGD(lr=0.00005, decay=1e-6, momentum=0.9, nesterov=True)
# cnn_best_model.compile(optimizer=sgd, # change: use SGD
# loss=f1_weighted, # 'binary_crossentropy' #'mean_squared_error' #categorical_crossentropy
# metrics=[f1, "binary_accuracy"])
#
# test_features = np.array([])
#
# for idx, ecg_lead in enumerate(ecg_leads):
# peaks, info = nk.ecg_peaks(ecg_lead, sampling_rate= 200)
# peaks = peaks.astype('float64')
# hrv = nk.hrv_time(peaks, sampling_rate= fs)
# hrv = hrv.astype('float64')
# test_features = np.append(test_features, [hrv['HRV_CVNN'], hrv['HRV_CVSD'], hrv['HRV_HTI'], hrv['HRV_IQRNN'], hrv['HRV_MCVNN'], hrv['HRV_MadNN'], hrv['HRV_MeanNN'], hrv['HRV_MedianNN'], hrv['HRV_RMSSD'], hrv['HRV_SDNN'], hrv['HRV_SDSD'], hrv['HRV_TINN'], hrv['HRV_pNN20'],hrv['HRV_pNN50'] ])
# test_features = test_features.astype('float64')
#
# test_features= test_features.reshape(int(len(test_features)/14), 14)
# x = np.isnan(test_features)
# # replacing NaN values with 0
# test_features[x] = 0
#
# X_test = test_features
# X_test_arr = np.array(X_test).reshape(np.array(X_test).shape[0], np.array(X_test).shape[1], 1)
# # with trained model to predict
# y_pred = cnn_best_model.predict(X_test_arr)
# pred_labels = [np.argmax(y, axis=None, out=None) for y in y_pred]
#
# for n, i in enumerate(pred_labels):
# if i == 0:
# pred_labels[n] = 'N'
# if i == 1:
# pred_labels[n] = 'A'
#
# predictions = list()
#
# for idx in range(len(X_test)):
# predictions.append((ecg_names[idx], pred_labels[idx]))
# ------------------------------------------------------------------------------
# ------------------------------------------------------------------
''' AdaBoost Classifier '''
# import warnings
# warnings.filterwarnings("ignore")
#
# test_features = np.array([])
#
# for idx, ecg_lead in enumerate(ecg_leads):
# peaks, info = nk.ecg_peaks(ecg_lead, sampling_rate= 200)
# peaks = peaks.astype('float64')
# hrv = nk.hrv_time(peaks, sampling_rate= fs)
# hrv = hrv.astype('float64')
# test_features = np.append(test_features, [hrv['HRV_CVNN'], hrv['HRV_CVSD'], hrv['HRV_HTI'], hrv['HRV_IQRNN'], hrv['HRV_MCVNN'], hrv['HRV_MadNN'], hrv['HRV_MeanNN'], hrv['HRV_MedianNN'], hrv['HRV_RMSSD'], hrv['HRV_SDNN'], hrv['HRV_SDSD'], hrv['HRV_TINN'], hrv['HRV_pNN20'],hrv['HRV_pNN50'] ])
# test_features = test_features.astype('float64')
#
# test_features= test_features.reshape(int(len(test_features)/14), 14)
# x = np.isnan(test_features)
# # replacing NaN values with 0
# test_features[x] = 0
#
# X_test = test_features
#
# # with trained model to predict
# loaded_model = joblib.load('AdaBoostClassifier')
# pred_labels = loaded_model.predict(X_test)
#-----------------------------------------------------------------------------------------
''' XGBoost Classifier '''
import warnings
warnings.filterwarnings("ignore")
test_features = np.array([])
for idx, ecg_lead in enumerate(ecg_leads):
peaks, info = nk.ecg_peaks(ecg_lead, sampling_rate=fs)
peaks = peaks.astype('float64')
hrv = nk.hrv_time(peaks, sampling_rate=fs)
hrv = hrv.astype('float64')
test_features = np.append(test_features, [
hrv['HRV_CVNN'], hrv['HRV_CVSD'], hrv['HRV_HTI'], hrv['HRV_IQRNN'],
hrv['HRV_MCVNN'], hrv['HRV_MadNN'], hrv['HRV_MeanNN'],
hrv['HRV_MedianNN'], hrv['HRV_RMSSD'], hrv['HRV_SDNN'],
hrv['HRV_SDSD'], hrv['HRV_TINN'], hrv['HRV_pNN20'],
hrv['HRV_pNN50']
])
test_features = test_features.astype('float64')
test_features = test_features.reshape(int(len(test_features) / 14), 14)
x = np.isnan(test_features)
# replacing NaN values with 0
test_features[x] = 0
X_test = test_features
# with trained model to predict
loaded_model = joblib.load('XGBoostClassifier')
pred_labels = loaded_model.predict(X_test)
# a list of tuple
predictions = list()
for idx in range(len(X_test)):
predictions.append((ecg_names[idx], pred_labels[idx]))
return predictions # Liste von Tupels im Format (ecg_name,label) - Muss unverändert bleiben!
ecg_array[unique_id]['P_width_mean'] = np.nanmean(waves_cwt['ECG_P_width'])
ecg_array[unique_id]['P_width_median'] = np.nanmedian(
waves_cwt['ECG_P_width'])
ecg_array[unique_id]['P_width_std'] = np.nanstd(waves_cwt['ECG_P_width'])
ecg_array[unique_id]['P_width_min'] = np.nanmin(waves_cwt['ECG_P_width'])
ecg_array[unique_id]['P_width_max'] = np.nanmax(waves_cwt['ECG_P_width'])
ecg_array[unique_id]['QRS_width_mean'] = np.nanmean(
waves_cwt['ECG_QRS_width'])
ecg_array[unique_id]['QRS_width_median'] = np.nanmedian(
waves_cwt['ECG_QRS_width'])
ecg_array[unique_id]['QRS_width_std'] = np.nanstd(
waves_cwt['ECG_QRS_width'])
ecg_array[unique_id]['QRS_width_min'] = np.nanmin(
waves_cwt['ECG_QRS_width'])
ecg_array[unique_id]['QRS_width_max'] = np.nanmax(
waves_cwt['ECG_QRS_width'])
hrv = nk.hrv_time(rpeaks, sampling_rate=500, show=True)
ecg_array[unique_id]['HRV_MeanNN'] = hrv['HRV_MeanNN'][0]
ecg_array[unique_id]['HRV_SDNN'] = hrv['HRV_SDNN'][0]
ecg_array[unique_id]['HRV_MedianNN'] = hrv['HRV_MedianNN'][0]
ecg_array[unique_id]['label'] = df_train[df_train['unique_id'] ==
unique_id]['label'][i]
if (i % 100 == 0):
plt.cla() # Clear the current axes
plt.clf() # Clear the current figure
plt.close()
i += 1
def get_HRVs_values(data, header_data):
filter_lowcut = 0.001
filter_highcut = 15.0
filter_order = 1
tmp_hea = header_data[0].split(' ')
ptID = tmp_hea[0]
num_leads = int(tmp_hea[1])
sample_Fs= int(tmp_hea[2])
gain_lead = np.zeros(num_leads)
for ii in range(num_leads):
tmp_hea = header_data[ii+1].split(' ')
gain_lead[ii] = int(tmp_hea[2].split('/')[0])
# for testing, we included the mean age of 57 if the age is a NaN
# This value will change as more data is being released
for iline in header_data:
if iline.startswith('#Age'):
tmp_age = iline.split(': ')[1].strip()
age = int(tmp_age if tmp_age != 'NaN' else 57)
# age = int(tmp_age)
elif iline.startswith('#Sex'):
tmp_sex = iline.split(': ')[1]
if tmp_sex.strip()=='Female':
sex =1
else:
sex=0
elif iline.startswith('#Dx'):
label = iline.split(': ')[1].split(',')[0]
signal = data[1]
gain = gain_lead[1]
ecg_signal = nk.ecg_clean(signal*gain, sampling_rate=sample_Fs, method="biosppy")
_ , rpeaks = nk.ecg_peaks(ecg_signal, sampling_rate=sample_Fs)
hrv_time = nk.hrv_time(rpeaks, sampling_rate=sample_Fs)
peaks, idx = detect_peaks(signal, sample_Fs, gain)
# print(len(signal), len(idx))
rr_intervals = idx / (sample_Fs * 1000)
rr_intervals = pd.Series(rr_intervals)
rr_ma = rr_intervals.rolling(3)
try:
signal_peak, waves_peak = nk.ecg_delineate(ecg_signal, rpeaks, sampling_rate=sample_Fs)
p_peaks = waves_peak['ECG_P_Peaks']
except ValueError:
print('Exception raised!')
pass
p_peaks = np.asarray(p_peaks, dtype=float)
p_peaks = p_peaks[~np.isnan(p_peaks)]
p_peaks = [int(a) for a in p_peaks]
p_time = [x/sample_Fs for x in p_peaks]
p_diff = np.diff(p_time)
# mean_P_Peaks = np.mean([signal[w] for w in p_peaks])
hrv_time['var_P_time'] = stats.tvar(p_diff)
hrv_time['var_P_peaks'] = stats.tvar(signal[np.array(p_peaks)])
hrv_time['age'] = age
hrv_time['label'] = label
return hrv_time
