def test_create_epochs(self):
signal = [0] * 30 + [1] * 5 + [0] * 30 + [1] * 5 + [0] * 30
events = nk.find_events(np.array(signal))
data = nk.create_epochs(pd.DataFrame({"Signal": signal}),
events_onsets=events["onsets"],
duration=5)
self.assertEqual(len(data), 2)
def test_create_epochs(df):
df = pd.DataFrame({
"Trigger":
pd.Series(
scipy.signal.square(1 * np.pi * 5 *
np.linspace(0, 1, 2000, endpoint=False))),
"Signal":
pd.Series(np.sin(20 * np.pi * np.linspace(0, 1, 2000, endpoint=False)))
* np.random.normal(0, 1, 2000),
"Signal2":
pd.Series(np.sin(60 * np.pi * np.linspace(0, 1, 2000, endpoint=False)))
* np.random.normal(0, 2, 2000)
})
df.plot()
events = nk.find_events(df["Trigger"], cut="lower")
assert len(events) == 2
fig = nk.plot_events_in_signal(df, events["onsets"])
epochs = nk.create_epochs(df, events["onsets"], duration=0.1)
assert len(epochs) == 2
def test_find_events(self):
signal = [0] * 30 + [1] * 5 + [0] * 30 + [1] * 5 + [0] * 30
events = nk.find_events(np.array(signal))
self.assertEqual(len(events["onsets"]), 2)
# A large number of HRV indices can be found
print("HRV indices: ")
print(bio["ECG"]["HRV"])
# RSA (respiratory sinus arrithmia) algorithm -> P2T
nk.z_score(bio["df"][["ECG_Filtered", "RSP_Filtered",
"RSA"]])[1000:2500].plot()
plt.title('RSA algorithm')
plt.savefig('graphs/rsaalg')
#define condition list
condition_list = ["Negative", "Neutral", "Neutral", "Negative"]
#dict containing onsets and durations of each event --> should be 1
events = nk.find_events(df["Photosensor"], cut="lower")
print("event finding")
print(events)
#create_epoch --> epochs of data corresponding to each event (since is 1 event, is the epoch[0])
epochs = nk.create_epochs(bio["df"],
events["onsets"],
duration=700,
onset=-100)
nk.z_score(epochs[0][["ECG_Filtered", "EDA_Filtered", "Photosensor"]]).plot()
plt.title('Epoch')
plt.savefig('graphs/epoch')
# itereate through the epochs and store the interesting results in a new dict that will be, at the end, converted to a dataframe
data = {} # Initialize an empty dict
for epoch_index in epochs:
for Detector in range(len(SCRs_df['onsets']) - 2):
if ((SCRs_df['amplitudes'][Detector + 1] - SCRs_df['amplitudes'][Detector])
> 0.1):
SCRs_df['Artefacts'][Detector + 1] = 1
else:
SCRs_df['Artefacts'][Detector + 1] = 0
# Detection of artefacts related with time: onset and offset greather than duration threshold (500 ms)
for Detector2 in range(len(SCRs_df['onsets']) - 2):
if ((ts[SCRs_df['peaks'][Detector2 + 1]] -
ts[SCRs_df['onsets'][Detector2]]) > 500):
SCRs_df['Artefacts'][Detector2 + 1] = 1
else:
SCRs_df['Artefacts'][Detector2 + 1] = 0
# Identification of onset and duration of the triggers
events = nk.find_events(df["Digital input"], cut="higher")
# Definition of the dataframe of the results
Results = pd.DataFrame(
np.zeros(((len(events['onsets'])), 5)),
columns=['Trigger', 'peaks', 'amplitudes', 'latency', 'artefacts'])
for trialnr in range(len(events['onsets'])):
Temporal = SCRs_df[
(SCRs_df['onsets'] > (events['onsets'][trialnr] - 500))
& (SCRs_df['peaks'] <
(events['onsets'][trialnr] + events['durations'][trialnr] + 500))]
Results['Trigger'][trialnr] = trialnr
Results['peaks'][trialnr] = len(Temporal['peaks'])
Results['amplitudes'][trialnr] = Temporal['amplitudes'].max()
#Results['amplitudes'][trialnr] = Temporal['amplitudes'].mean()
Results['artefacts'][trialnr] = Temporal['Artefacts'].max()
