data = np.random.randn(n, p)
I = np.where(np.square(XYZ - XYZ.max(axis=1).reshape(-1, 1) / 2).sum(
axis=0) <= r ** 2)[0]
data[:, I] += signal
vardata = np.random.randn(n, p) ** 2
if axis == 1:
data = data.T
vardata = vardata.T
return data, vardata, XYZ
###############################################################################
# Example for using permutation_test_onesample class
data, vardata, XYZ = make_data()
# rfx calibration
P = PT.permutation_test_onesample(data, XYZ)
# clusters definition (height threshold, max diameter)
c = [(P.random_Tvalues[P.ndraws * (0.95)], None)]
# regions definition (label vector)
r = np.ones(data.shape[1], int)
r[data.shape[1]/2.:] *= 10
voxel_results, cluster_results, region_results = \
P.calibrate(nperms=100, clusters=c, regions=[r])
# mfx calibration
P = PT.permutation_test_onesample(data, XYZ, vardata=vardata,
stat_id="student_mfx")
voxel_results, cluster_results, region_results = \
P.calibrate(nperms=100, clusters=c, regions=[r])
import numpy as np
from nipy.labs.group.permutation_test import permutation_test_onesample
from nipy.utils import example_data
# Get group data
group_data = example_data.get_filename('neurospin', 'language_babies',
'offset_002.npz')
f = np.load(group_data)
data, vardata, xyz = f['mat'], f['var'], f['xyz']
# Create one-sample permutation test instance
ptest = permutation_test_onesample(data, xyz, stat_id='wilcoxon')
# Cluster definition: (threshold, diameter)
# Note that a list of definitions can be passed to ptest.calibrate
cluster_def = (ptest.height_threshold(0.01), None)
print cluster_def
# Multiple calibration
# To get accurate pvalues, don't pass nperms (default is 1e4)
# Yet it will take longer to run
voxel_res, cluster_res, region_res = ptest.calibrate(nperms=100,
clusters=[cluster_def])
# Simulated Zmax values for FWER correction
simu_zmax = ptest.zscore(voxel_res['perm_maxT_values'])
