def test_bval_predict():
# Now check to see if the values for individual b values is
# around a value we want
actual_vals, predicted_vals = pn.kfold_xval(data_pv, bvals_pv, bvecs_pv, mask_pv,
ad, rd, 20, "multi", mean = "empirical",
solver = "nnls")
npt.assert_equal(np.mean(predicted_vals[1][predicted_vals[1] >1])>800,1)
npt.assert_equal(np.mean(actual_vals[1][actual_vals[1] >1])>800,1)
# Let's see if the RMSE is reasonable.
this_rmse = np.sqrt(np.mean((actual_vals - predicted_vals)**2))
npt.assert_equal(this_rmse<350, 1)
# Predict 10% (n = 10)
ad = {
1000: 1.6386920952169737,
2000: 1.2919249903637751,
3000: 0.99962593218241236
}
rd = {
1000: 0.33450124887561905,
2000: 0.28377379537043729,
3000: 0.24611723207420028
}
actual_single, predicted_single = pn.kfold_xval(data,
bvals,
bvecs,
mask,
ad,
rd,
10,
"multi",
mean="mean_model",
solver="nnls")
aff = np.eye(4)
save_path = "/hsgs/nobackup/klchan13/"
nib.Nifti1Image(predicted_single, aff).to_filename(
os.path.join(save_path, "multi_mm_single_exp_rs%s.nii.gz" % (i)))
t2 = time.time()
print "This program took %4.2f minutes to run." % ((t2 - t1) / 60.)
ad_rd = np.loadtxt(os.path.join(data_path, "ad_rd_%s.txt" % sid))
ad = {1000: ad_rd[0, 0], 2000: ad_rd[0, 1], 3000: ad_rd[0, 2]}
rd = {1000: ad_rd[1, 0], 2000: ad_rd[1, 1], 3000: ad_rd[1, 2]}
if im == "bi_exp_rs":
shorthand_im = "be"
elif im == "single_exp_rs":
shorthand_im = "se"
# Predict 10% (n = 10)
actual, predicted = pn.kfold_xval(data,
bvals,
bvecs,
mask,
ad,
rd,
10,
fODF,
mean_mod_func=im,
mean="mean_model",
solver="nnls")
cod = ozu.coeff_of_determination(actual, predicted)
np.save(
os.path.join(data_path,
"sfm_predict_%s_%s%s.npy" % (fODF, shorthand_im, i)),
predicted)
np.save(
os.path.join(data_path,
"sfm_cod_%s_%s%s.npy" % (fODF, shorthand_im, i)), cod)
if fODF == "multi":
precision = "emd_multi_combine"
else:
precision = "emd"
if im == "bi_exp_rs":
shorthand_im = "be"
elif im == "single_exp_rs":
shorthand_im = "se"
# Predict 10% (n = 10)
emd = pn.kfold_xval(data,
bvals,
bvecs,
mask,
ad,
rd,
10,
fODF,
mean="mean_model",
precision=precision,
solver="nnls",
mean_mod_func=im)
np.save(
os.path.join(data_save_path,
"emd_%s_%s%s.npy" % (fODF, shorthand_im, i)), emd[0].T)
t2 = time.time()
print "This program took %4.2f minutes to run." % ((t2 - t1) / 60.)
high = np.min([(i+1) * 2000, int(np.sum(wm_data))])
# Now set the mask:
mask = np.zeros(wm_data_file.shape)
mask[wm_idx[0][low:high], wm_idx[1][low:high], wm_idx[2][low:high]] = 1
# Load the AD, RD values for this subject.
ad_rd = np.loadtxt(os.path.join(data_path, "ad_rd_%s.txt"%sid))
ad = {1000:ad_rd[0,0], 2000:ad_rd[0,1], 3000:ad_rd[0,2]}
rd = {1000:ad_rd[1,0], 2000:ad_rd[1,1], 3000:ad_rd[1,2]}
if fODF == "multi":
precision = "emd_multi_combine"
else:
precision = "emd"
if im == "bi_exp_rs":
shorthand_im = "be"
elif im == "single_exp_rs":
shorthand_im = "se"
# Predict 10% (n = 10)
emd = pn.kfold_xval(data, bvals, bvecs, mask, ad, rd, 10, fODF,
mean = "mean_model", precision = precision,
solver = "nnls", mean_mod_func = im)
np.save(os.path.join(data_save_path, "emd_%s_%s%s.npy"%(fODF,shorthand_im,i)), emd[0].T)
t2 = time.time()
print "This program took %4.2f minutes to run."%((t2 - t1)/60.)
high = np.min([(i+1) * 2000, int(np.sum(wm_data))])
# Now set the mask:
mask = np.zeros(wm_data_file.shape)
mask[wm_idx[0][low:high], wm_idx[1][low:high], wm_idx[2][low:high]] = 1
# Load the AD, RD values for this subject.
ad_rd = np.loadtxt(os.path.join(data_path, "ad_rd_%s.txt"%sid))
ad = {1000:ad_rd[0,0], 2000:ad_rd[0,1], 3000:ad_rd[0,2]}
rd = {1000:ad_rd[1,0], 2000:ad_rd[1,1], 3000:ad_rd[1,2]}
if im == "bi_exp_rs":
shorthand_im = "be"
elif im == "single_exp_rs":
shorthand_im = "se"
# Predict 10% (n = 10)
actual, predicted = pn.kfold_xval(data, bvals, bvecs,
mask, ad, rd, 10, fODF,
mean_mod_func = im,
mean = "mean_model", solver = "nnls")
cod = ozu.coeff_of_determination(actual, predicted)
np.save(os.path.join(data_path, "sfm_predict_%s_%s%s.npy"%(fODF,
shorthand_im,i)), predicted)
np.save(os.path.join(data_path, "sfm_cod_%s_%s%s.npy"%(fODF,
shorthand_im,i)), cod)
t2 = time.time()
print "This program took %4.2f minutes to run."%((t2 - t1)/60.)
data = data_file.get_data()
wm_data = wm_data_file.get_data()
wm_idx = np.where(wm_data==1)
bvals = np.loadtxt(os.path.join(data_path, "bvals"))
bvecs = np.loadtxt(os.path.join(data_path, "bvecs"))
low = i*2000
# Make sure not to go over the edge of the mask:
high = np.min([(i+1) * 2000, int(np.sum(wm_data))])
# Now set the mask:
mask = np.zeros(wm_data_file.shape)
mask[wm_idx[0][low:high], wm_idx[1][low:high], wm_idx[2][low:high]] = 1
# Predict 10% (n = 10)
ad = {1000:1.6386920952169737, 2000:1.2919249903637751, 3000:0.99962593218241236}
rd = {1000:0.33450124887561905, 2000:0.28377379537043729, 3000:0.24611723207420028}
actual_single, predicted_single = pn.kfold_xval(data, bvals, bvecs,
mask, ad, rd, 10, "multi",
mean = "mean_model", solver = "nnls")
aff = np.eye(4)
save_path = "/hsgs/nobackup/klchan13/"
nib.Nifti1Image(predicted_single, aff).to_filename(os.path.join(save_path,
"multi_mm_single_exp_rs%s.nii.gz"%(i)))
t2 = time.time()
print "This program took %4.2f minutes to run."%((t2 - t1)/60.)
