def test_bio_analyze():
# Example with event-related analysis
data = nk.data("bio_eventrelated_100hz")
df, info = nk.bio_process(ecg=data["ECG"],
rsp=data["RSP"],
eda=data["EDA"],
keep=data["Photosensor"],
sampling_rate=100)
events = nk.events_find(
data["Photosensor"],
threshold_keep="below",
event_conditions=["Negative", "Neutral", "Neutral", "Negative"])
epochs = nk.epochs_create(df,
events,
sampling_rate=100,
epochs_start=-0.1,
epochs_end=1.9)
event_related = nk.bio_analyze(epochs)
assert len(event_related) == len(epochs)
labels = [int(i) for i in event_related["Label"]]
assert labels == list(np.arange(1, len(epochs) + 1))
# Example with interval-related analysis
data = nk.data("bio_resting_8min_100hz")
df, info = nk.bio_process(ecg=data["ECG"],
rsp=data["RSP"],
eda=data["EDA"],
sampling_rate=100)
interval_related = nk.bio_analyze(df)
assert len(interval_related) == 1
def test_rsp_eventrelated():
rsp, info = nk.rsp_process(nk.rsp_simulate(duration=20))
epochs = nk.epochs_create(rsp,
events=[5000, 10000, 15000],
epochs_start=-0.1,
epochs_end=1.9)
rsp_eventrelated = nk.rsp_eventrelated(epochs)
# Test rate features
assert np.alltrue(
np.array(rsp_eventrelated["RSP_Rate_Min"]) < np.array(
rsp_eventrelated["RSP_Rate_Mean"]))
assert np.alltrue(
np.array(rsp_eventrelated["RSP_Rate_Mean"]) < np.array(
rsp_eventrelated["RSP_Rate_Max"]))
# Test amplitude features
assert np.alltrue(
np.array(rsp_eventrelated["RSP_Amplitude_Min"]) < np.array(
rsp_eventrelated["RSP_Amplitude_Mean"]))
assert np.alltrue(
np.array(rsp_eventrelated["RSP_Amplitude_Mean"]) < np.array(
rsp_eventrelated["RSP_Amplitude_Max"]))
assert all(elem in [
"RSP_Rate_Max", "RSP_Rate_Min", "RSP_Rate_Mean", "RSP_Rate_Max_Time",
"RSP_Rate_Min_Time", "RSP_Amplitude_Max", "RSP_Amplitude_Min",
"RSP_Amplitude_Mean", "RSP_Phase", "RSP_PhaseCompletion", "Label"
] for elem in np.array(rsp_eventrelated.columns.values, dtype=str))
def test_ecg_intervalrelated():
data = nk.data("bio_resting_5min_100hz")
df, info = nk.ecg_process(data["ECG"], sampling_rate=100)
columns = [
'ECG_Rate_Mean', 'HRV_RMSSD', 'HRV_MeanNN', 'HRV_SDNN', 'HRV_SDSD',
'HRV_CVNN', 'HRV_CVSD', 'HRV_MedianNN', 'HRV_MadNN', 'HRV_MCVNN',
'HRV_pNN50', 'HRV_pNN20', 'HRV_TINN', 'HRV_HTI', 'HRV_ULF', 'HRV_VLF',
'HRV_LF', 'HRV_HF', 'HRV_VHF', 'HRV_LFHF', 'HRV_LFn', 'HRV_HFn',
'HRV_LnHF', 'HRV_SD1', 'HRV_SD2', 'HRV_SD2SD1', 'HRV_CSI', 'HRV_CVI',
'HRV_CSI_Modified', 'HRV_SampEn'
]
# Test with signal dataframe
features_df = nk.ecg_intervalrelated(df)
assert all(elem in columns
for elem in np.array(features_df.columns.values, dtype=str))
assert features_df.shape[0] == 1 # Number of rows
# Test with dict
epochs = nk.epochs_create(df,
events=[0, 15000],
sampling_rate=100,
epochs_end=150)
features_dict = nk.ecg_intervalrelated(epochs, sampling_rate=100)
assert all(elem in columns
for elem in np.array(features_dict.columns.values, dtype=str))
assert features_dict.shape[0] == 2 # Number of rows
def test_emg_eventrelated():
emg = nk.emg_simulate(duration=20, sampling_rate=1000, burst_number=3)
emg_signals, info = nk.emg_process(emg, sampling_rate=1000)
epochs = nk.epochs_create(emg_signals,
events=[3000, 6000, 9000],
sampling_rate=1000,
epochs_start=-0.1,
epochs_end=1.9)
emg_eventrelated = nk.emg_eventrelated(epochs)
# Test amplitude features
no_activation = np.where(emg_eventrelated["EMG_Activation"] == 0)[0][0]
assert int(
pd.DataFrame(emg_eventrelated.values[no_activation]).isna().sum()) == 4
assert np.alltrue(
np.nansum(np.array(emg_eventrelated["EMG_Amplitude_Mean"])) <
np.nansum(np.array(emg_eventrelated["EMG_Amplitude_Max"])))
assert len(emg_eventrelated["Label"]) == 3
assert len(emg_eventrelated.columns) == 7
assert all(elem in [
"EMG_Activation", "EMG_Amplitude_Mean", "EMG_Amplitude_Max",
"EMG_Amplitude_Max_Time", "EMG_Bursts", "Label", "Event_Onset"
] for elem in np.array(emg_eventrelated.columns.values, dtype=str))
def test_rsp_eventrelated():
rsp, info = nk.rsp_process(nk.rsp_simulate(duration=30, random_state=42))
epochs = nk.epochs_create(rsp,
events=[5000, 10000, 15000],
epochs_start=-0.1,
epochs_end=1.9)
rsp_eventrelated = nk.rsp_eventrelated(epochs)
# Test rate features
assert np.alltrue(
np.array(rsp_eventrelated["RSP_Rate_Min"]) < np.array(
rsp_eventrelated["RSP_Rate_Mean"]))
assert np.alltrue(
np.array(rsp_eventrelated["RSP_Rate_Mean"]) < np.array(
rsp_eventrelated["RSP_Rate_Max"]))
# Test amplitude features
assert np.alltrue(
np.array(rsp_eventrelated["RSP_Amplitude_Min"]) < np.array(
rsp_eventrelated["RSP_Amplitude_Mean"]))
assert np.alltrue(
np.array(rsp_eventrelated["RSP_Amplitude_Mean"]) < np.array(
rsp_eventrelated["RSP_Amplitude_Max"]))
assert len(rsp_eventrelated["Label"]) == 3
def test_ecg_eventrelated():
ecg, info = nk.ecg_process(nk.ecg_simulate(duration=20))
epochs = nk.epochs_create(ecg,
events=[5000, 10000, 15000],
epochs_start=-0.1,
epochs_end=1.9)
ecg_eventrelated = nk.ecg_eventrelated(epochs)
# Test rate features
assert np.alltrue(
np.array(ecg_eventrelated["ECG_Rate_Min"]) < np.array(
ecg_eventrelated["ECG_Rate_Mean"]))
assert np.alltrue(
np.array(ecg_eventrelated["ECG_Rate_Mean"]) < np.array(
ecg_eventrelated["ECG_Rate_Max"]))
assert len(ecg_eventrelated["Label"]) == 3
assert len(ecg_eventrelated.columns) == 13
assert all(elem in [
"ECG_Rate_Max", "ECG_Rate_Min", "ECG_Rate_Mean", "ECG_Rate_Max_Time",
"ECG_Rate_Min_Time", "ECG_Rate_Trend_Quadratic",
"ECG_Rate_Trend_Linear", "ECG_Rate_Trend_R2", "ECG_Atrial_Phase",
"ECG_Atrial_PhaseCompletion", "ECG_Ventricular_Phase",
"ECG_Ventricular_PhaseCompletion", "Label"
] for elem in np.array(ecg_eventrelated.columns.values, dtype=str))
def test_bio_analyze():
# Example with event-related analysis
data = nk.data("bio_eventrelated_100hz")
df, info = nk.bio_process(ecg=data["ECG"],
rsp=data["RSP"],
eda=data["EDA"],
keep=data["Photosensor"],
sampling_rate=100)
events = nk.events_find(
data["Photosensor"],
threshold_keep='below',
event_conditions=["Negative", "Neutral", "Neutral", "Negative"])
epochs = nk.epochs_create(df,
events,
sampling_rate=100,
epochs_start=-0.1,
epochs_end=1.9)
event_related = nk.bio_analyze(epochs)
assert len(event_related) == len(epochs)
labels = [int(i) for i in event_related['Label']]
assert labels == list(np.arange(1, len(epochs) + 1))
assert all(elem in [
'ECG_Rate_Max', 'ECG_Rate_Min', 'ECG_Rate_Mean', 'ECG_Rate_Max_Time',
'ECG_Rate_Min_Time', 'ECG_Rate_Trend_Quadratic',
'ECG_Rate_Trend_Linear', 'ECG_Rate_Trend_R2', 'ECG_Atrial_Phase',
'ECG_Atrial_PhaseCompletion', 'ECG_Ventricular_Phase',
'ECG_Ventricular_PhaseCompletion', 'ECG_Quality_Mean', 'RSP_Rate_Max',
'RSP_Rate_Min', 'RSP_Rate_Mean', 'RSP_Rate_Max_Time',
'RSP_Rate_Min_Time', 'RSP_Amplitude_Max', 'RSP_Amplitude_Min',
'RSP_Amplitude_Mean', 'RSP_Phase', 'RSP_PhaseCompletion', 'EDA_SCR',
'EDA_Peak_Amplitude', 'SCR_Peak_Amplitude', 'SCR_Peak_Amplitude_Time',
'SCR_RiseTime', 'SCR_RecoveryTime', 'RSA_P2T', 'Label', 'Condition'
] for elem in np.array(event_related.columns.values, dtype=str))
# Example with interval-related analysis
data = nk.data("bio_resting_8min_100hz")
df, info = nk.bio_process(ecg=data["ECG"],
rsp=data["RSP"],
eda=data["EDA"],
sampling_rate=100)
interval_related = nk.bio_analyze(df)
assert len(interval_related) == 1
assert all(elem in [
'ECG_Rate_Mean', 'HRV_RMSSD', 'HRV_MeanNN', 'HRV_SDNN', 'HRV_SDSD',
'HRV_CVNN', 'HRV_CVSD', 'HRV_MedianNN', 'HRV_MadNN', 'HRV_MCVNN',
'HRV_pNN50', 'HRV_pNN20', 'HRV_TINN', 'HRV_HTI', 'HRV_ULF', 'HRV_VLF',
'HRV_LF', 'HRV_HF', 'HRV_VHF', 'HRV_LFHF', 'HRV_LFn', 'HRV_HFn',
'HRV_LnHF', 'HRV_SD1', 'HRV_SD2', 'HRV_SD2SD1', 'HRV_CSI', 'HRV_CVI',
'HRV_CSI_Modified', 'HRV_SampEn', 'RSP_Rate_Mean',
'RSP_Amplitude_Mean', 'RRV_SDBB', 'RRV_RMSSD', 'RRV_SDSD', 'RRV_VLF',
'RRV_LF', 'RRV_HF', 'RRV_LFHF', 'RRV_LFn', 'RRV_HFn', 'RRV_SD1',
'RRV_SD2', 'RRV_SD2SD1', 'RRV_ApEn', 'RRV_SampEn', 'RRV_DFA',
'RSA_P2T_Mean', 'RSA_P2T_Mean_log', 'RSA_P2T_SD', 'RSA_P2T_NoRSA',
'RSA_PorgesBohrer', 'SCR_Peaks_N', 'SCR_Peaks_Amplitude_Mean'
] for elem in np.array(interval_related.columns.values, dtype=str))
def test_ecg_eventrelated():
ecg, info = nk.ecg_process(nk.ecg_simulate(duration=20))
epochs = nk.epochs_create(ecg,
events=[5000, 10000, 15000],
epochs_start=-0.1,
epochs_end=1.9)
ecg_eventrelated = nk.ecg_eventrelated(epochs)
# Test rate features
assert np.alltrue(
np.array(ecg_eventrelated["ECG_Rate_Min"]) < np.array(
ecg_eventrelated["ECG_Rate_Mean"]))
assert np.alltrue(
np.array(ecg_eventrelated["ECG_Rate_Mean"]) < np.array(
ecg_eventrelated["ECG_Rate_Max"]))
assert len(ecg_eventrelated["Label"]) == 3
# Test warning on missing columns
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `ECG_Phase_Artrial`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["ECG_Phase_Atrial"]
nk.ecg_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an.*`ECG_Phase_Ventricular`"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["ECG_Phase_Ventricular"]
nk.ecg_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `ECG_Quality`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["ECG_Quality"]
nk.ecg_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `ECG_Rate`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["ECG_Rate"]
nk.ecg_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
# Test warning on long epochs (eventrelated_utils)
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*duration of your epochs seems.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
first_epoch_copy.index = range(len(first_epoch_copy))
nk.ecg_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
def test_ecg_eventrelated():
ecg, info = nk.ecg_process(nk.ecg_simulate(duration=20))
epochs = nk.epochs_create(ecg, events=[5000, 10000, 15000], epochs_start=-0.1, epochs_end=1.9)
ecg_eventrelated = nk.ecg_eventrelated(epochs)
# Test rate features
assert np.alltrue(np.array(ecg_eventrelated["ECG_Rate_Min"]) < np.array(ecg_eventrelated["ECG_Rate_Mean"]))
assert np.alltrue(np.array(ecg_eventrelated["ECG_Rate_Mean"]) < np.array(ecg_eventrelated["ECG_Rate_Max"]))
assert len(ecg_eventrelated["Label"]) == 3
def test_eda_eventrelated():
eda = nk.eda_simulate(duration=15, scr_number=3)
eda_signals, info = nk.eda_process(eda, sampling_rate=1000)
epochs = nk.epochs_create(eda_signals, events=[5000, 10000, 15000],
sampling_rate=1000,
epochs_start=-0.1, epochs_end=1.9)
eda_eventrelated = nk.eda_eventrelated(epochs)
no_activation = np.where(eda_eventrelated["EDA_SCR"] == 0)[0][0]
assert int(pd.DataFrame(eda_eventrelated.values
[no_activation]).isna().sum()) == 4
assert len(eda_eventrelated["Label"]) == 3
def test_eda_eventrelated():
eda = nk.eda_simulate(duration=15, scr_number=3)
eda_signals, info = nk.eda_process(eda, sampling_rate=1000)
epochs = nk.epochs_create(
eda_signals,
events=[5000, 10000, 15000],
sampling_rate=1000,
epochs_start=-0.1,
epochs_end=1.9,
)
eda_eventrelated = nk.eda_eventrelated(epochs)
no_activation = np.where(eda_eventrelated["EDA_SCR"] == 0)[0][0]
assert int(
pd.DataFrame(eda_eventrelated.values[no_activation]).isna().sum()) == 4
assert len(eda_eventrelated["Label"]) == 3
# Test warning on missing columns
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `EDA_Phasic`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["EDA_Phasic"]
nk.eda_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `SCR_Amplitude`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["SCR_Amplitude"]
nk.eda_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `SCR_RecoveryTime`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["SCR_RecoveryTime"]
nk.eda_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `SCR_RiseTime`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["SCR_RiseTime"]
nk.eda_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
def test_rsp_intervalrelated():
data = nk.data("bio_resting_5min_100hz")
df, info = nk.rsp_process(data["RSP"], sampling_rate=100)
# Test with signal dataframe
features_df = nk.rsp_intervalrelated(df)
assert features_df.shape[0] == 1 # Number of rows
# Test with dict
epochs = nk.epochs_create(df,
events=[0, 15000],
sampling_rate=100,
epochs_end=150)
features_dict = nk.rsp_intervalrelated(epochs)
assert features_dict.shape[0] == 2 # Number of rows
def test_rsp_eventrelated():
rsp, info = nk.rsp_process(nk.rsp_simulate(duration=30, random_state=42))
epochs = nk.epochs_create(rsp,
events=[5000, 10000, 15000],
epochs_start=-0.1,
epochs_end=1.9)
rsp_eventrelated = nk.rsp_eventrelated(epochs)
# Test rate features
assert np.alltrue(
np.array(rsp_eventrelated["RSP_Rate_Min"]) < np.array(
rsp_eventrelated["RSP_Rate_Mean"]))
assert np.alltrue(
np.array(rsp_eventrelated["RSP_Rate_Mean"]) < np.array(
rsp_eventrelated["RSP_Rate_Max"]))
# Test amplitude features
assert np.alltrue(
np.array(rsp_eventrelated["RSP_Amplitude_Min"]) < np.array(
rsp_eventrelated["RSP_Amplitude_Mean"]))
assert np.alltrue(
np.array(rsp_eventrelated["RSP_Amplitude_Mean"]) < np.array(
rsp_eventrelated["RSP_Amplitude_Max"]))
assert len(rsp_eventrelated["Label"]) == 3
# Test warning on missing columns
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `RSP_Amplitude`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["RSP_Amplitude"]
nk.rsp_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `RSP_Phase`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["RSP_Phase"]
nk.rsp_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
def test_emg_eventrelated():
emg = nk.emg_simulate(duration=20, sampling_rate=1000, burst_number=3)
emg_signals, info = nk.emg_process(emg, sampling_rate=1000)
epochs = nk.epochs_create(emg_signals,
events=[3000, 6000, 9000],
sampling_rate=1000,
epochs_start=-0.1,
epochs_end=1.9)
emg_eventrelated = nk.emg_eventrelated(epochs)
# Test amplitude features
no_activation = np.where(emg_eventrelated["EMG_Activation"] == 0)[0][0]
assert int(
pd.DataFrame(emg_eventrelated.values[no_activation]).isna().sum()) == 4
assert np.alltrue(
np.nansum(np.array(emg_eventrelated["EMG_Amplitude_Mean"])) <
np.nansum(np.array(emg_eventrelated["EMG_Amplitude_Max"])))
assert len(emg_eventrelated["Label"]) == 3
# Test warning on missing columns
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `EMG_Onsets`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["EMG_Onsets"]
nk.emg_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `EMG_Activity`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["EMG_Activity"]
nk.emg_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an.*`EMG_Amplitude`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["EMG_Amplitude"]
nk.emg_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
def test_eda_intervalrelated():
data = nk.data("bio_resting_8min_100hz")
df, info = nk.eda_process(data["EDA"], sampling_rate=100)
columns = ['SCR_Peaks_N', 'SCR_Peaks_Amplitude_Mean']
# Test with signal dataframe
features_df = nk.eda_intervalrelated(df)
assert all(elem in columns for elem
in np.array(features_df.columns.values, dtype=str))
assert features_df.shape[0] == 1 # Number of rows
# Test with dict
epochs = nk.epochs_create(df, events=[0, 25300],
sampling_rate=100, epochs_end=20)
features_dict = nk.eda_intervalrelated(epochs)
assert all(elem in columns for elem
in np.array(features_dict.columns.values, dtype=str))
assert features_dict.shape[0] == 2 # Number of rows
def test_eda_eventrelated():
eda = nk.eda_simulate(duration=15, scr_number=3)
eda_signals, info = nk.eda_process(eda, sampling_rate=1000)
epochs = nk.epochs_create(eda_signals,
events=[5000, 10000, 15000],
sampling_rate=1000,
epochs_start=-0.1,
epochs_end=1.9)
eda_eventrelated = nk.eda_eventrelated(epochs)
no_activation = np.where(eda_eventrelated["EDA_Activation"] == 0)[0][0]
assert int(
pd.DataFrame(eda_eventrelated.values[no_activation]).isna().sum()) == 4
assert len(eda_eventrelated["Label"]) == 3
assert len(eda_eventrelated.columns) == 6
assert all(elem in [
"EDA_Activation", "EDA_Peak_Amplitude", "EDA_Peak_Amplitude_Time",
"EDA_RiseTime", "EDA_RecoveryTime", "Label"
] for elem in np.array(eda_eventrelated.columns.values, dtype=str))
def test_ecg_intervalrelated():
data = nk.data("bio_resting_5min_100hz")
df, info = nk.ecg_process(data["ECG"], sampling_rate=100)
columns = [
'ECG_Rate_Mean', 'HRV_RMSSD', 'HRV_MeanNN', 'HRV_SDNN', 'HRV_SDSD',
'HRV_CVNN', 'HRV_CVSD', 'HRV_MedianNN', 'HRV_MadNN', 'HRV_MCVNN',
'HRV_IQRNN', 'HRV_pNN50', 'HRV_pNN20', 'HRV_TINN', 'HRV_HTI',
'HRV_ULF', 'HRV_VLF', 'HRV_LF', 'HRV_HF', 'HRV_VHF', 'HRV_LFHF',
'HRV_LFn', 'HRV_HFn', 'HRV_LnHF', 'HRV_SD1', 'HRV_SD2', 'HRV_SD1SD2',
'HRV_S', 'HRV_CSI', 'HRV_CVI', 'HRV_CSI_Modified', 'HRV_PIP',
'HRV_IALS', 'HRV_PSS', 'HRV_PAS', 'HRV_ApEn', 'HRV_SampEn', 'HRV_GI',
'HRV_SI', 'HRV_AI', 'HRV_PI', 'HRV_C1d', 'HRV_C1a', 'HRV_SD1d',
'HRV_SD1a', 'HRV_C2d', 'HRV_C2a', 'HRV_SD2d', 'HRV_SD2a', 'HRV_Cd',
'HRV_Ca', 'HRV_SDNNd', 'HRV_SDNNa'
]
# Test with signal dataframe
features_df = nk.ecg_intervalrelated(df, sampling_rate=100)
# https://github.com/neuropsychology/NeuroKit/issues/304
assert all(features_df == nk.ecg_analyze(
df, sampling_rate=100, method="interval-related"))
assert all(elem in np.array(features_df.columns.values, dtype=str)
for elem in columns)
assert features_df.shape[0] == 1 # Number of rows
# Test with dict
epochs = nk.epochs_create(df,
events=[0, 15000],
sampling_rate=100,
epochs_end=150)
features_dict = nk.ecg_intervalrelated(epochs, sampling_rate=100)
assert all(elem in columns
for elem in np.array(features_dict.columns.values, dtype=str))
assert features_dict.shape[0] == 2 # Number of rows
def test_eog_eventrelated():
eog = nk.data('eog_200hz')['vEOG']
eog_signals, info = nk.eog_process(eog, sampling_rate=200)
epochs = nk.epochs_create(eog_signals,
events=[5000, 10000, 15000],
epochs_start=-0.1,
epochs_end=1.9)
eog_eventrelated = nk.eog_eventrelated(epochs)
# Test rate features
assert np.alltrue(
np.array(eog_eventrelated["EOG_Rate_Min"]) < np.array(
eog_eventrelated["EOG_Rate_Mean"]))
assert np.alltrue(
np.array(eog_eventrelated["EOG_Rate_Mean"]) < np.array(
eog_eventrelated["EOG_Rate_Max"]))
# Test blink presence
assert np.alltrue(
np.array(eog_eventrelated["EOG_Blinks_Presence"]) == np.array(
[1, 0, 0]))
# Test warning on missing columns
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `EOG_Blinks`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["EOG_Blinks"]
nk.eog_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
with pytest.warns(nk.misc.NeuroKitWarning,
match=r".*does not have an `EOG_Rate`.*"):
first_epoch_key = list(epochs.keys())[0]
first_epoch_copy = epochs[first_epoch_key].copy()
del first_epoch_copy["EOG_Rate"]
nk.eog_eventrelated({**epochs, first_epoch_key: first_epoch_copy})
def test_eog_eventrelated():
eog = nk.data('eog_200hz')['vEOG']
eog_signals, info = nk.eog_process(eog, sampling_rate=200)
epochs = nk.epochs_create(eog_signals,
events=[5000, 10000, 15000],
epochs_start=-0.1,
epochs_end=1.9)
eog_eventrelated = nk.eog_eventrelated(epochs)
# Test rate features
assert np.alltrue(
np.array(eog_eventrelated["EOG_Rate_Min"]) < np.array(
eog_eventrelated["EOG_Rate_Mean"]))
assert np.alltrue(
np.array(eog_eventrelated["EOG_Rate_Mean"]) < np.array(
eog_eventrelated["EOG_Rate_Max"]))
# Test blink presence
assert np.alltrue(
np.array(eog_eventrelated["EOG_Blinks_Presence"]) == np.array(
[1, 0, 0]))
def test_emg_intervalrelated():
emg = nk.emg_simulate(duration=40, sampling_rate=1000, burst_number=3)
emg_signals, info = nk.emg_process(emg, sampling_rate=1000)
columns = ['EMG_Activation_N', 'EMG_Amplitude_Mean']
# Test with signal dataframe
features_df = nk.emg_intervalrelated(emg_signals)
assert all(elem in columns
for elem in np.array(features_df.columns.values, dtype=str))
assert features_df.shape[0] == 1 # Number of rows
# Test with dict
epochs = nk.epochs_create(emg_signals,
events=[0, 20000],
sampling_rate=1000,
epochs_end=20)
features_dict = nk.emg_intervalrelated(epochs)
assert all(elem in columns
for elem in np.array(features_dict.columns.values, dtype=str))
assert features_dict.shape[0] == 2 # Number of rows
def test_rsp_intervalrelated():
data = nk.data("bio_resting_5min_100hz")
df, info = nk.rsp_process(data["RSP"], sampling_rate=100)
columns = ['RSP_Rate_Mean', 'RSP_Amplitude_Mean', 'RRV_SDBB', 'RRV_RMSSD',
'RRV_SDSD', 'RRV_VLF', 'RRV_LF', 'RRV_HF', 'RRV_LFHF', 'RRV_LFn',
'RRV_HFn', 'RRV_SD1', 'RRV_SD2', 'RRV_SD2SD1', 'RRV_ApEn',
'RRV_SampEn', 'RRV_DFA']
# Test with signal dataframe
features_df = nk.rsp_intervalrelated(df)
assert all(elem in columns for elem
in np.array(features_df.columns.values, dtype=str))
assert features_df.shape[0] == 1 # Number of rows
# Test with dict
epochs = nk.epochs_create(df, events=[0, 15000],
sampling_rate=100, epochs_end=150)
features_dict = nk.rsp_intervalrelated(epochs)
assert all(elem in columns for elem
in np.array(features_dict.columns.values, dtype=str))
assert features_dict.shape[0] == 2 # Number of rows
def test_eog_intervalrelated():
eog = nk.data('eog_200hz')['vEOG']
eog_signals, info = nk.eog_process(eog, sampling_rate=200)
columns = ['EOG_Peaks_N', 'EOG_Rate_Mean']
# Test with signal dataframe
features = nk.eog_intervalrelated(eog_signals)
assert all(elem in np.array(features.columns.values, dtype=str)
for elem in columns)
assert features.shape[0] == 1 # Number of rows
# Test with dict
epochs = nk.epochs_create(eog_signals,
events=[5000, 10000, 15000],
epochs_start=-0.1,
epochs_end=1.9)
epochs_dict = nk.eog_intervalrelated(epochs)
assert all(elem in columns
for elem in np.array(epochs_dict.columns.values, dtype=str))
assert epochs_dict.shape[0] == len(epochs) # Number of rows
def process_session(self, folder, data):
"""
Process session data.
Parameters
----------
folder : str
Session data folder name.
data : DataFrame
Session data.
Returns
-------
DataFrame
Extracted event-related features for all signals.
"""
p = Path('{}/{}/epochs'.format(self.path, folder))
p.mkdir(exist_ok=True)
name = folder.split('_')
emotion = name[0]
gender = name[-1]
self.emotion_gender_dict['emotion'] += [emotion]
self.emotion_gender_dict['gender'] += [gender]
bvp = data['bvp']
eda = data['gsr']
tag = data['tag']
hr = data['hr']
ibi = data['ibi']
#epoch count / 2
count = tag.shape[0] // 2
if count == 0:
count = 1
self.samples_count += count
condition_list = ['neutral', emotion] * count
#Remove data before the first tag and after the last tag.
first_tag = tag['norm_ts'].head(1).values[0]
tag.loc[:, 'norm_ts'] -= first_tag
bvp.loc[:, 'norm_ts'] -= first_tag
eda.loc[:, 'norm_ts'] -= first_tag
hr.loc[:, 'norm_ts'] -= first_tag
ibi.loc[:, 'norm_ts'] -= first_tag
tag = tag[tag['norm_ts'] >= 0.0]
bvp = bvp[bvp['norm_ts'] >= 0.0]
eda = eda[eda['norm_ts'] >= 0.0]
hr = hr[hr['norm_ts'] >= 0.0]
ibi = ibi[ibi['norm_ts'] >= 0.0]
last_tag = tag['norm_ts'].tail(1).values[0]
tag = tag[tag['norm_ts'] < last_tag]
bvp = bvp[bvp['norm_ts'] <= last_tag]
eda = eda[eda['norm_ts'] <= last_tag]
hr = hr[hr['norm_ts'] <= last_tag]
ibi = ibi[ibi['norm_ts'] <= last_tag]
#Compute IBI miss ratio
duration = tag['timestamp'].tail(1).values[0] - tag['timestamp'].head(
1).values[0]
m_ratio = ibi_miss_ratio(ibi, duration)
self.ppg_ratio += m_ratio
self.ppg_ratio_dict[emotion][0] += 1
self.ppg_ratio_dict[emotion][1] += m_ratio
#Process the Signals
try:
eda_signals, eda_info = process_eda(eda)
bvp_signals, bvp_info, hrv_indices = process_bvp(bvp)
hrv_indices['Condition'] = emotion
hrv_indices.to_csv('{}/{}/hrv.csv'.format(self.path, folder))
except Exception as e:
print('Signal processing for {} failed.'.format(folder))
print('Raised exception: {}. Signal processing handler.'.format(e))
return None
signals = pd.concat([bvp_signals, eda_signals], axis=1, join='inner')
signals = signals.fillna(0)
signals.to_csv('{}/{}/signals.csv'.format(self.path, folder))
#reset index to start by 0.
bvp_signals.reset_index(inplace=True)
#plot HR from E4 with HR computed by NeuroKit2.
if self.show_fig and m_ratio < 0.01:
plt.plot(hr['norm_ts'] + 5, hr['value'], label='Empatica E4')
plt.plot(bvp_signals['index'][::64] / 64,
bvp_signals['PPG_Rate'][::64],
label='NeuroKit2')
plt.xlabel('Čas [s]')
plt.ylabel('Srdeční tep [bpm]')
plt.legend()
plt.show()
try:
events = find_events(signals, tag, condition_list=condition_list)
epochs = nk.epochs_create(signals,
events,
sampling_rate=64,
epochs_start=0)
except Exception as e:
print('Signal processing for {} failed.'.format(folder))
print('Raised exception: {}. Epochs creating handler.'.format(e))
return None
neutral_df, emotion_df = concat_epochs_by_condition(epochs)
neutral_df.to_csv('{}/{}/epochs/neutral_all.csv'.format(
self.path, folder))
emotion_df.to_csv('{}/{}/epochs/emotion_all.csv'.format(
self.path, folder))
save_epochs_to_csv('{}/{}'.format(self.path, folder), epochs)
if self.show_fig:
plot_epochs(folder, epochs, events)
#Extract Event Related Features
erf = extract_ERF(epochs, condition_list=condition_list)
erf['Gender'] = gender
erf.to_csv('{}/{}/features.csv'.format(self.path, folder))
return erf
print("Task: " + str(i))
data = pd.read_csv("../../data/eogdb/eogdb_task" + str(i + 1) + ".csv")
for j, participant in enumerate(np.unique(data["Participant"])[1:3]):
print(" - " + str(j + 1))
segment = data[data["Participant"] == participant]
signal = segment["vEOG"]
cleaned = nk.eog_clean(signal, sampling_rate=200, method='neurokit')
blinks = nk.signal_findpeaks(cleaned, relative_height_min=1.5)["Peaks"]
events = nk.epochs_create(cleaned,
blinks,
sampling_rate=200,
epochs_start=-0.4,
epochs_end=0.6)
events = nk.epochs_to_array(events) # Convert to 2D array
x = np.linspace(0, 100, num=len(events))
p_gamma = np.full((events.shape[1], 3), np.nan)
p_bateman = np.full((events.shape[1], 3), np.nan)
p_scr = np.full((events.shape[1], 4), np.nan)
for i in range(events.shape[1]):
if np.isnan(events[:, i]).any():
break
events[:, i] = nk.rescale(events[:, i],
to=[0, 1]) # Reshape to 0-1 scale
event_raw_index]
# find events
eda_events = nk.events_find(df_event,
threshold=0,
threshold_keep='above')
# process eda signals
eda_signals, eda_info = nk.bio_process(
eda=df_gsr, sampling_rate=hz_gsr)
# create epochs
eda_epochs_end = sc_duration if (
sc_duration -
EPOCH_START) <= EPOCH_DURATION else (
EPOCH_START + EPOCH_DURATION)
eda_epochs = nk.epochs_create(
eda_signals,
eda_events,
sampling_rate=hz_gsr,
epochs_start=EPOCH_START,
epochs_end=eda_epochs_end)
# analyze event-related features of EDA signals
# eda_analysis = nk.bio_analyze(eda_epochs, method="event-related")
# Feature SCR (Skin Conductance Response)
eda_epoch = eda_epochs['1']
eda_response_desc = eda_epoch.loc[
eda_epoch['SCR_Amplitude'] > 0,
["SCR_Amplitude"]].describe()
eda_response_count = eda_response_desc.loc[
'count'].values[0]
row['EDA_Response_Count'] = eda_response_count
eda_response_mean = eda_response_desc.loc[
'mean'].values[0]
# =============================================================================
# Epochs
# =============================================================================
# Get Events
events = mne.read_events(mne.datasets.sample.data_path() +
'/MEG/sample/sample_audvis_filt-0-40_raw-eve.fif')
events = pd.DataFrame(events[:, [0, 2]], columns=["Index", "Condition"])
# Conditions = {'audio/left': 1, 'audio/right': 2, 'visual/left': 3, 'visual/right': 4}
events = events[events["Condition"].isin([1, 2, 3, 4])]
events["Condition"].loc[events["Condition"].isin([1, 2])] = "Audio"
events["Condition"].loc[events["Condition"] != "Audio"] = "Visual"
epochs = nk.epochs_create(out["Sequence"],
events["Index"],
sampling_rate=150,
epochs_end=0.5,
event_conditions=events["Condition"])
# =============================================================================
# Results
# =============================================================================
nk.microstates_static(out["Sequence"],
sampling_rate=150)["Microstate_Average_DurationMean"]
df = [] # Initialize an empty dict
for i in epochs.keys():
data = nk.microstates_static(epochs[i]["Signal"], sampling_rate=150)
data = pd.concat([
data,
nk.microstates_dynamic(epochs[i]["Signal"]),