def test_cosines(self):
"""Test if cosines with defined frequencies are passed or attenuated"""
"""Parameters entered for test here: """
dc_level = .1
# passband freq should be chosen w.r.t. filter specification, changes
# for filter to filter, defined in eegProcessor.py
fcos0 = 2
fcos1 = 10
fcos2 = 20
fcos3 = 30
fcos4 = 40
fs = 256
# fs = 300
# fs = 1024
duration = 5 # in seconds for test duration
'''End of parameters'''
t = np.arange(0, duration - 1. / fs, 1. / fs) # time vector
# Cosines with different frequencies
x0 = np.cos(2 * np.pi * fcos0 * t)
x1 = np.cos(2 * np.pi * fcos1 * t)
x2 = np.cos(2 * np.pi * fcos2 * t)
x3 = np.cos(2 * np.pi * fcos3 * t)
x4 = np.cos(2 * np.pi * fcos4 * t)
x6 = dc_level
x7 = np.cos(2 * np.pi * 1 * t)
x8 = np.cos(2 * np.pi * 48 * t)
x9 = np.cos(2 * np.pi * 70 * t)
x10 = np.cos(2 * np.pi * 100 * t)
xpassband = x0 + x1 + x2 + x3 + x4
xstopband = x6 + x7 + x8 + x9 + x10
# Two channels
x = np.zeros((2, xpassband.size))
x[0][:] = xpassband + xstopband
x[1][:] = xpassband + xstopband
y = bandpass.text_filter(x, fs=fs, k=1)
MSE_perSample = np.sum(
(xpassband - y[0][:xpassband.size])**2.) / xpassband.size
MSE_perSample_norm = MSE_perSample / np.sum(x[0][:]**2)
self.assertTrue(MSE_perSample_norm * 100 < 10)
def _demo_validate_real_data():
ds_rate = 2
channel_map = [1] * 16 + [0, 0, 1, 1, 0, 1, 1, 1, 0]
data_train_folder = load_experimental_data()
mode = 'calibration'
raw_dat, stamp_time, channels, type_amp, fs = read_data_csv(
data_train_folder + '/rawdata.csv')
dat = bandpass.text_filter(raw_dat, fs=fs, k=ds_rate)
# Get data and labels
s_i, t_t_i, t_i = trigger_decoder(mode=mode,
trigger_loc=data_train_folder +
'/triggers.txt')
x_train, y_train, num_seq, _ = trial_reshaper(t_t_i,
t_i,
dat,
mode=mode,
fs=fs,
k=ds_rate,
channel_map=channel_map)
model = train_pca_rda_kde_model(x_train, y_train, k_folds=10)
fig = plt.figure()
ax = fig.add_subplot(211)
x_plot = np.linspace(np.min(model.line_el[-1]), np.max(model.line_el[-1]),
1000)[:, np.newaxis]
ax.plot(model.line_el[2][y_train == 0],
-0.005 -
0.01 * np.random.random(model.line_el[2][y_train == 0].shape[0]),
'ro',
label='class(-)')
ax.plot(model.line_el[2][y_train == 1],
-0.005 -
0.01 * np.random.random(model.line_el[2][y_train == 1].shape[0]),
'go',
label='class(+)')
for idx in range(len(model.pipeline[2].list_den_est)):
log_dens = model.pipeline[2].list_den_est[idx].score_samples(x_plot)
ax.plot(x_plot[:, 0],
np.exp(log_dens),
'r-' * (idx == 0) + 'g-' * (idx == 1),
linewidth=2.0)
ax.legend(loc='upper right')
plt.title('Training Data')
plt.ylabel('p(e|l)')
plt.xlabel('scores')
# Test
data_test_folder = load_experimental_data()
mode = 'calibration'
raw_dat, stamp_time, channels, type_amp, fs = read_data_csv(
data_test_folder + '/rawdata.csv')
dat = bandpass.text_filter(raw_dat, fs=fs, k=ds_rate)
# Get data and labels
s_i, t_t_i, t_i = trigger_decoder(mode=mode,
trigger_loc=data_test_folder +
'/triggers.txt')
x_test, y_test, num_seq, _ = trial_reshaper(t_t_i,
t_i,
dat,
mode=mode,
fs=fs,
k=ds_rate,
channel_map=channel_map)
model.transform(x_test)
ax.plot(model.line_el[2][y_test == 0],
-0.01 -
0.01 * np.random.random(model.line_el[2][y_test == 0].shape[0]),
'bo',
label='t_class(-)')
ax.plot(model.line_el[2][y_test == 1],
-0.01 -
0.01 * np.random.random(model.line_el[2][y_test == 1].shape[0]),
'ko',
label='t_class(+)')
bandwidth = 1.06 * min(np.std(model.line_el[2]),
iqr(model.line_el[2]) / 1.34) * np.power(
model.line_el[2].shape[0], -0.2)
test_kde = KernelDensityEstimate(bandwidth=bandwidth)
test_kde.fit(model.line_el[2], y_test)
for idx in range(len(model.pipeline[2].list_den_est)):
log_dens = test_kde.list_den_est[idx].score_samples(x_plot)
ax.plot(x_plot[:, 0],
np.exp(log_dens),
'b--' * (idx == 0) + 'k--' * (idx == 1),
linewidth=2.0)
ax.legend(loc='upper right')
plt.title('Training Data')
plt.ylabel('p(e|l)')
plt.xlabel('scores')
plt.show()
x6 = dcLevel
x7 = np.cos(2 * np.pi * 1 * t)
x8 = np.cos(2 * np.pi * 48 * t)
x9 = np.cos(2 * np.pi * 70 * t)
x10 = np.cos(2 * np.pi * 100 * t)
xpassband = x0 + x1 + x2 + x3 + x4
xstopband = x6 + x7 + x8 + x9 + x10
# Two channels
x = np.zeros((2, xpassband.size))
x[0][:] = xpassband + xstopband
x[1][:] = xpassband + xstopband
y = bandpass.text_filter(x, fs=fs, k=1)
MSE_perSample = np.sum(
(xpassband - y[0][:xpassband.size])**2.) / xpassband.size
MSE_perSample_norm = MSE_perSample / np.sum(x[0][:]**2)
print('MSE per sample: {} -> {}%'.format(MSE_perSample,
MSE_perSample / 5. * 100))
print('MSE normalized: {}'.format(MSE_perSample_norm * 100))
plt.figure(1)
plt.plot(t, xpassband, t, y[0][:xpassband.size])
plt.title('Sum of Pass-band Cosines')
plt.legend(('Pass-band signal', 'Filtered Signal'))
plt.show()