def test_stats(epochs):
"""
Test stats
"""
# with PSD from Epochs with random values
random_r1 = utils.generate_random_epoch(epochs.epo1, mu=0, sigma=0.01)
random_r2 = utils.generate_random_epoch(epochs.epo2, mu=4, sigma=0.01)
fmin = 10
fmax = 13
psd_tuple = analyses.pow(random_r1,
fmin,
fmax,
n_fft=256,
n_per_seg=None,
epochs_average=False)
psd = psd_tuple.psd
statsCondTuple = stats.statsCond(psd, random_r1, 3000, 0.05, 0.05)
assert statsCondTuple.T_obs.shape[0] == len(epochs.epo1.info['ch_names'])
for i in range(0, len(statsCondTuple.p_values)):
assert statsCondTuple.p_values[i] <= statsCondTuple.adj_p[1][i]
assert statsCondTuple.T_obs_plot.shape[0] == len(
epochs.epo1.info['ch_names'])
psd_tuple2 = analyses.pow(random_r2,
fmin,
fmax,
n_fft=256,
n_per_seg=None,
epochs_average=False)
psd2 = psd_tuple2.psd
freq_list = psd_tuple2.freq_list
data = [psd, psd2]
con_matrixTuple = stats.con_matrix(random_r1, freq_list, draw=False)
statscondClusterTuple = stats.statscondCluster(
data,
freq_list,
scipy.sparse.bsr_matrix(con_matrixTuple.ch_con_freq),
tail=0,
n_permutations=3000,
alpha=0.05)
assert statscondClusterTuple.F_obs.shape[0] == len(
epochs.epo1.info['ch_names'])
for i in range(0, len(statscondClusterTuple.clusters)):
assert len(statscondClusterTuple.clusters[i]) < len(
epochs.epo1.info['ch_names'])
assert statscondClusterTuple.cluster_p_values.shape[0] == len(
statscondClusterTuple.clusters)
assert np.mean(statscondClusterTuple.cluster_p_values) != float(0)
def test_stats(epochs):
"""
Test stats
"""
fmin = 10
fmax = 13
psd_tuple = analyses.pow(epochs.epo1,
fmin,
fmax,
n_fft=256,
n_per_seg=None,
epochs_average=False)
psd = psd_tuple.psd
statsCondTuple = stats.statsCond(psd, epochs.epo1, 3000, 0.05, 0.05)
assert statsCondTuple.T_obs.shape[0] == len(epochs.epo1.info['ch_names'])
for i in range(0, len(statsCondTuple.p_values)):
assert statsCondTuple.p_values[i] <= statsCondTuple.adj_p[1][i]
assert statsCondTuple.T_obs_plot.shape[0] == len(
epochs.epo1.info['ch_names'])
psd_tuple2 = analyses.pow(epochs.epo2,
fmin,
fmax,
n_fft=256,
n_per_seg=None,
epochs_average=False)
psd2 = psd_tuple2.psd
freq_list = psd_tuple2.freq_list
data = [psd, psd2]
con_matrixTuple = stats.con_matrix(epochs.epo1, freq_list, draw=False)
statscondClusterTuple = stats.statscondCluster(
data,
freq_list,
scipy.sparse.bsr_matrix(con_matrixTuple.ch_con_freq),
tail=0,
n_permutations=3000,
alpha=0.05)
assert statscondClusterTuple.F_obs.shape[0] == len(
epochs.epo1.info['ch_names'])
for i in range(0, len(statscondClusterTuple.clusters)):
assert len(statscondClusterTuple.clusters[i]) < len(
epochs.epo1.info['ch_names'])
assert statscondClusterTuple.cluster_p_values.shape[0] == len(
statscondClusterTuple.clusters)
def test_stats(epochs):
"""
Test stats
"""
fmin = 10
fmax = 13
freqs_mean, PSD_welch = analyses.PSD(epochs.epo1,
fmin,
fmax,
time_resolved=False)
statsCondTuple = stats.statsCond(PSD_welch, epochs.epo1, 3000, 0.05, 0.05)
assert statsCondTuple.T_obs.shape[0] == len(epochs.epo1.info['ch_names'])
# TODO: add an assert in the function to be sure PSD with epochs
# len(shape) = 3
# and retest with time_resolved=True
for i in range(0, len(statsCondTuple.p_values)):
assert statsCondTuple.p_values[i] <= statsCondTuple.adj_p[1][i]
assert statsCondTuple.T_obs_plot.shape[0] == len(
epochs.epo1.info['ch_names'])
# test T_obs_plot with viz function
_, PSD_welch2 = analyses.PSD(epochs.epo2, fmin, fmax, time_resolved=False)
data = [PSD_welch, PSD_welch2]
con_matrixTuple = stats.con_matrix(epochs.epo1, freqs_mean, draw=False)
statscondClusterTuple = stats.statscondCluster(
data,
freqs_mean,
scipy.sparse.bsr_matrix(con_matrixTuple.ch_con_freq),
tail=0,
n_permutations=3000,
alpha=0.05)
assert statscondClusterTuple.F_obs.shape[0] == len(
epochs.epo1.info['ch_names'])
for i in range(0, len(statscondClusterTuple.clusters)):
assert len(statscondClusterTuple.clusters[i]) < len(
epochs.epo1.info['ch_names'])
assert statscondClusterTuple.cluster_p_values.shape[0] == len(
statscondClusterTuple.clusters)
n_permutations=5000,
alpha=0.05,
)
# 3/ Non-parametric cluster-based permutations
# creating matrix of a priori connectivity between channels
# across space and frequencies based on their position,
# in the Alpha_Low band for example
con_matrixTuple = stats.con_matrix(preproc_S1, freqs_mean=psd1.freq_list)
ch_con_freq = con_matrixTuple.ch_con_freq
# consitute two artificial groups with 2 'participant1' and 2 'participant1'
data_group = [np.array([psd1.psd, psd1.psd]), np.array([psd2.psd, psd2.psd])]
statscondCluster = stats.statscondCluster(
data=data_group,
freqs_mean=psd1.freq_list,
ch_con_freq=scipy.sparse.bsr_matrix(ch_con_freq),
tail=0,
n_permutations=5000,
alpha=0.05,
)
# Comparing Intra-brain connectivity values between participants
# With 3/ non-parametric cluster-based permutations
# creating matrix of a priori connectivity between channels
# across space and frequencies based on their position
con_matrixTuple = stats.con_matrix(epochs=preproc_S1,
freqs_mean=np.arange(7.5, 11),
draw=False)
# Note that for connectivity, values are computed for
# choosing Alpha_Low for futher analyses for example
values_intra = alpha_low
values_intra -= np.diag(np.diag(values_intra))
# computing Cohens'D for further analyses for example
C_intra = (values_intra -
np.mean(values_intra[:])) / np.std(values_intra[:])
# can also sample CSD values directly for statistical analyses
result_intra.append(C_intra)
### Comparing inter-brain connectivity values to random signal
data = [np.array([values, values]), np.array([result_intra[0], result_intra[0]])]
statscondCluster = stats.statscondCluster(data=data,
freqs_mean=np.arange(7.5, 11),
ch_con_freq=None,
tail=0,
n_permutations=5000,
alpha=0.05)
#Visualization of interbrain connectivity in 2D
viz.viz_2D_topomap_inter(epo1, epo2, C, threshold='auto', steps=10, lab=True)
#Visualization of interbrain connectivity in 3D
viz.viz_3D_inter(epo1, epo2, C, threshold='auto', steps=10, lab=False)