def permute_isc_within(a, b, x, outfile, mask='', isc_only=False, hdf5=None, thresh=6000, n_pass=.7, n_reps=1000, t=False):
import numpy as np
from pycorr.funcs_correlate import crosscor, intersubcorr
from pycorr.statistics import perm, isc_corrmat_within_diff
from pycorr.subject import Run, Exp
from pycorr.pietools import mkdir_p, parse_section, arr_slice
# TASK ID so script knows where to slice, converts SGE_TASK_ID to 0-indexed
ID = parse_section(x) if x is not None else int(os.environ['SGE_TASK_ID']) - 1
# OUTPUTS
out = {}
# Load and Slice data ---------------------------------------------------------
mask = np.load(mask) if mask else slice(None)
if not hdf5:
# LOAD FILES
if t: #TESTING FLAG
from pycorr.gen_corrmat import fourD
A_files = fourD + 7000
B_files = fourD + 7000
elif a and b:
A_files = [os.path.join(a[0], fname) for fname in os.listdir(a[0])] #TODO change back, hack until rondo jobs are fixed
B_files = [os.path.join(b[0], fname) for fname in os.listdir(b[0])]
else: raise BaseException('need either test or specify inputs')
A = [arr_slice(fname, ID)[...,mask].astype('float') for fname in A_files]
B = [arr_slice(fname, ID)[...,mask].astype('float') for fname in B_files]
# Thresholding
#Hack to get threshold function, which is a class method TODO def move threshold
import h5py
Run = Run(h5py.File('dummy.h5'))
# threshold tcs with low mean
for dat in A+B: dat[Run.threshold(6000, dat)] = np.nan
thresh_pass = [~np.isnan(dat.sum(axis=-1)) for dat in A+B]
out['thresh_fail'] = Exp.cond_thresh(thresh_pass, mustpassprop=.7)
else:
E = Exp(hdf5)
A = [run.load(use_subset=mask, standardized=True, threshold=True, _slice=ID) for run in E.iter_runs(a[0])]
if b: #TODO fix, so hacky.. this script needs structure (want to let arg.b be optional
B = [run.load(standardized=True, threshold=True, _slice=ID) for run in E.iter_runs(b[0])]
else: B = []
E.get_cond(a[0])
out['thresh_fail'] = E.get_cond(a[0])['threshold'][...]
# Combine group indices for correlation matrix (we will shuffle these) --------
indx_A = range(len(A))
indx_B = range(len(A), len(A + B))
print indx_A
print indx_B
# Cross-Correlation matrix (we will permute rows and columns) -----------------
out['isc_corrmat'] = crosscor(A+B, standardized=False)
out['isc_A'] = intersubcorr(out['isc_corrmat'][..., indx_A, :][..., :, indx_A])
# Permutation Test ------------------------------------------------------------
if not isc_only:
out_shape = (n_reps, ) + out['isc_corrmat'].shape[:-2] #n_reps x spatial_dims
swap_dims = range(1,len(out_shape)) + [0] #list with first and last dims swapped
out['null'] = perm(indx_A, indx_B, isc_corrmat_within_diff, C = out['isc_corrmat'],
nreps=n_reps, out=np.zeros(out_shape))
out['null'] = out['null'].transpose(swap_dims) #put corrs on last dim
out['r'] = isc_corrmat_within_diff(indx_A, indx_B, out['isc_corrmat'])[..., np.newaxis] #since 1 corr, add axis for broadcasting
out['p'] = np.mean(np.abs(out['r']) <= np.abs(out['null']), axis=-1)
# Output ----------------------------------------------------------------------
outtmp = os.path.join(outfile, "{fold}/{ID}.npy")
for k, v in out.iteritems():
outfile = outtmp.format(fold=k, ID=x or ID)
mkdir_p(os.path.dirname(outfile))
np.save(outfile, v)
def test_perm_isc_corrmat_within():
A, B = range(3), range(3, 6)
r_null = perm(B, A, isc_corrmat_within_diff, nreps=10000, C=C)
r = isc_corrmat_within_diff(B, A, C)
assert np.mean(np.array(r_null) <= r) == 1 #original grouping yields highest corr
def permute_isc_within(a,
b,
x,
outfile,
mask='',
isc_only=False,
hdf5=None,
thresh=6000,
n_pass=.7,
n_reps=1000,
t=False):
import numpy as np
from pycorr.funcs_correlate import crosscor, intersubcorr
from pycorr.statistics import perm, isc_corrmat_within_diff
from pycorr.subject import Run, Exp
from pycorr.pietools import mkdir_p, parse_section, arr_slice
# TASK ID so script knows where to slice, converts SGE_TASK_ID to 0-indexed
ID = parse_section(x) if x is not None else int(
os.environ['SGE_TASK_ID']) - 1
# OUTPUTS
out = {}
# Load and Slice data ---------------------------------------------------------
mask = np.load(mask) if mask else slice(None)
if not hdf5:
# LOAD FILES
if t: #TESTING FLAG
from pycorr.gen_corrmat import fourD
A_files = fourD + 7000
B_files = fourD + 7000
elif a and b:
A_files = [
os.path.join(a[0], fname) for fname in os.listdir(a[0])
] #TODO change back, hack until rondo jobs are fixed
B_files = [os.path.join(b[0], fname) for fname in os.listdir(b[0])]
else:
raise BaseException('need either test or specify inputs')
A = [
arr_slice(fname, ID)[..., mask].astype('float')
for fname in A_files
]
B = [
arr_slice(fname, ID)[..., mask].astype('float')
for fname in B_files
]
# Thresholding
#Hack to get threshold function, which is a class method TODO def move threshold
import h5py
Run = Run(h5py.File('dummy.h5'))
# threshold tcs with low mean
for dat in A + B:
dat[Run.threshold(6000, dat)] = np.nan
thresh_pass = [~np.isnan(dat.sum(axis=-1)) for dat in A + B]
out['thresh_fail'] = Exp.cond_thresh(thresh_pass, mustpassprop=.7)
else:
E = Exp(hdf5)
A = [
run.load(use_subset=mask,
standardized=True,
threshold=True,
_slice=ID) for run in E.iter_runs(a[0])
]
if b: #TODO fix, so hacky.. this script needs structure (want to let arg.b be optional
B = [
run.load(standardized=True, threshold=True, _slice=ID)
for run in E.iter_runs(b[0])
]
else:
B = []
E.get_cond(a[0])
out['thresh_fail'] = E.get_cond(a[0])['threshold'][...]
# Combine group indices for correlation matrix (we will shuffle these) --------
indx_A = range(len(A))
indx_B = range(len(A), len(A + B))
print indx_A
print indx_B
# Cross-Correlation matrix (we will permute rows and columns) -----------------
out['isc_corrmat'] = crosscor(A + B, standardized=False)
out['isc_A'] = intersubcorr(out['isc_corrmat'][..., indx_A, :][..., :,
indx_A])
# Permutation Test ------------------------------------------------------------
if not isc_only:
out_shape = (
n_reps, ) + out['isc_corrmat'].shape[:-2] #n_reps x spatial_dims
swap_dims = range(
1, len(out_shape)) + [0] #list with first and last dims swapped
out['null'] = perm(indx_A,
indx_B,
isc_corrmat_within_diff,
C=out['isc_corrmat'],
nreps=n_reps,
out=np.zeros(out_shape))
out['null'] = out['null'].transpose(swap_dims) #put corrs on last dim
out['r'] = isc_corrmat_within_diff(indx_A, indx_B, out['isc_corrmat'])[
..., np.newaxis] #since 1 corr, add axis for broadcasting
out['p'] = np.mean(np.abs(out['r']) <= np.abs(out['null']), axis=-1)
# Output ----------------------------------------------------------------------
outtmp = os.path.join(outfile, "{fold}/{ID}.npy")
for k, v in out.iteritems():
outfile = outtmp.format(fold=k, ID=x or ID)
mkdir_p(os.path.dirname(outfile))
np.save(outfile, v)
def test_isc_within_correct():
assert np.allclose(isc_corrmat_within_diff(range(3), range(3), C), 0)
def test_perm_test_is_permuting():
np.random.seed(1)
fun = lambda A, B: sum(A) - sum(B)
out = perm([0,0,0,0], [1,1,1,1], fun, nreps=1000)
assert .010 < np.mean(np.array(out) == 4) < .018
C11 = np.ones([3,3]) * .3
C22 = np.ones([3,3]) * .5
C12 = np.ones([3,3]) * 0
C = np.hstack([np.vstack([C11, C12]), np.vstack([C12, C22])])
C[np.diag_indices_from(C)] = 1
D = corr_eig(None, 6, 20, C)[1].T
a = isc_within_diff(D[0:3], D[3:])
b = isc_corrmat_within_diff(range(3), range(3, 6), C)
#TODO wrap in setup func or class
def test_isc_within_both_equiv():
assert np.allclose(a, b)
def test_isc_within_correct():
assert np.allclose(isc_corrmat_within_diff(range(3), range(3), C), 0)
def test_isc_corrmat_within_correct():
assert np.allclose(isc_within_diff(D[0:3], D[0:3]), 0)
# this would hold if you were doing actual isc not subject-total corr
#def test_isc_within_correct_diff():
# assert np.allclose(a, -.2)
#
#def test_isc_corrmat_within_correct_diff():
def test_perm_isc_corrmat_within():
A, B = range(3), range(3, 6)
r_null = perm(B, A, isc_corrmat_within_diff, nreps=10000, C=C)
r = isc_corrmat_within_diff(B, A, C)
assert np.mean(
np.array(r_null) <= r) == 1 #original grouping yields highest corr
def test_isc_within_correct():
assert np.allclose(isc_corrmat_within_diff(range(3), range(3), C), 0)
def test_perm_test_is_permuting():
np.random.seed(1)
fun = lambda A, B: sum(A) - sum(B)
out = perm([0, 0, 0, 0], [1, 1, 1, 1], fun, nreps=1000)
assert .010 < np.mean(np.array(out) == 4) < .018
C11 = np.ones([3, 3]) * .3
C22 = np.ones([3, 3]) * .5
C12 = np.ones([3, 3]) * 0
C = np.hstack([np.vstack([C11, C12]), np.vstack([C12, C22])])
C[np.diag_indices_from(C)] = 1
D = corr_eig(None, 6, 20, C)[1].T
a = isc_within_diff(D[0:3], D[3:])
b = isc_corrmat_within_diff(range(3), range(3, 6), C)
#TODO wrap in setup func or class
def test_isc_within_both_equiv():
assert np.allclose(a, b)
def test_isc_within_correct():
assert np.allclose(isc_corrmat_within_diff(range(3), range(3), C), 0)
def test_isc_corrmat_within_correct():
assert np.allclose(isc_within_diff(D[0:3], D[0:3]), 0)
