def test_data(tmpdir):
sim = Simulator()
r = 10
sigma = 1
y = [0, 1]
n_reps = 3
output_dir = str(tmpdir)
sim.create_data(y, sigma, reps=n_reps, output_dir=output_dir)
shape_3d = (91, 109, 91)
shape_2d = (6, 238955)
y = pd.read_csv(os.path.join(str(tmpdir.join('y.csv'))),
header=None,
index_col=None).T
flist = glob.glob(str(tmpdir.join('centered*.nii.gz')))
# Test load list
dat = Brain_Data(data=flist, Y=y)
# Test load file
assert Brain_Data(flist[0])
# Test to_nifti
d = dat.to_nifti()
assert d.shape[0:3] == shape_3d
# Test load nibabel
assert Brain_Data(d)
# Test shape
assert dat.shape() == shape_2d
# Test Mean
assert dat.mean().shape()[0] == shape_2d[1]
# Test Std
assert dat.std().shape()[0] == shape_2d[1]
# Test add
new = dat + dat
assert new.shape() == shape_2d
# Test subtract
new = dat - dat
assert new.shape() == shape_2d
# Test multiply
new = dat * dat
assert new.shape() == shape_2d
# Test Iterator
x = [x for x in dat]
assert len(x) == len(dat)
assert len(x[0].data.shape) == 1
# # Test T-test
out = dat.ttest()
assert out['t'].shape()[0] == shape_2d[1]
# # # Test T-test - permutation method
# out = dat.ttest(threshold_dict={'permutation':'tfce','n_permutations':50,'n_jobs':1})
# assert out['t'].shape()[0]==shape_2d[1]
# Test Regress
dat.X = pd.DataFrame(
{
'Intercept': np.ones(len(dat.Y)),
'X1': np.array(dat.Y).flatten()
},
index=None)
out = dat.regress()
assert out['beta'].shape() == (2, shape_2d[1])
# Test indexing
assert out['t'][1].shape()[0] == shape_2d[1]
# Test threshold
i = 1
tt = threshold(out['t'][i], out['p'][i], .05)
assert isinstance(tt, Brain_Data)
# Test write
dat.write(os.path.join(str(tmpdir.join('test_write.nii'))))
assert Brain_Data(os.path.join(str(tmpdir.join('test_write.nii'))))
# Test append
assert dat.append(dat).shape()[0] == shape_2d[0] * 2
# Test distance
distance = dat.distance(method='euclidean')
assert distance.shape == (shape_2d[0], shape_2d[0])
# Test predict
stats = dat.predict(algorithm='svm',
cv_dict={
'type': 'kfolds',
'n_folds': 2,
'n': len(dat.Y)
},
plot=False,
**{'kernel': "linear"})
# Support Vector Regression, with 5 fold cross-validation with Platt Scaling
# This will output probabilities of each class
stats = dat.predict(algorithm='svm',
cv_dict=None,
plot=False,
**{
'kernel': 'linear',
'probability': True
})
assert isinstance(stats['weight_map'], Brain_Data)
# Logistic classificiation, with 5 fold stratified cross-validation.
stats = dat.predict(algorithm='logistic',
cv_dict={
'type': 'kfolds',
'n_folds': 5,
'n': len(dat.Y)
},
plot=False)
assert isinstance(stats['weight_map'], Brain_Data)
# Ridge classificiation, with 5 fold between-subject cross-validation, where data for each subject is held out together.
stats = dat.predict(algorithm='ridgeClassifier', cv_dict=None, plot=False)
assert isinstance(stats['weight_map'], Brain_Data)
# Test Similarity
r = dat.similarity(stats['weight_map'])
assert len(r) == shape_2d[0]
r2 = dat.similarity(stats['weight_map'].to_nifti())
assert len(r2) == shape_2d[0]
# Test apply_mask - might move part of this to test mask suite
s1 = create_sphere([41, 64, 55], radius=10)
assert isinstance(s1, nb.Nifti1Image)
s2 = Brain_Data(s1)
masked_dat = dat.apply_mask(s1)
assert masked_dat.shape()[1] == np.sum(s2.data != 0)
# Test extract_roi
mask = create_sphere([41, 64, 55], radius=10)
assert len(dat.extract_roi(mask)) == shape_2d[0]
# Test r_to_z
z = dat.r_to_z()
assert z.shape() == dat.shape()
# Test copy
d_copy = dat.copy()
assert d_copy.shape() == dat.shape()
# Test detrend
detrend = dat.detrend()
assert detrend.shape() == dat.shape()
def test_brain_data(tmpdir):
# Add 3mm to list to test that resolution as well
for resolution in ['2mm']:
MNI_Template["resolution"] = resolution
sim = Simulator()
r = 10
sigma = 1
y = [0, 1]
n_reps = 3
output_dir = str(tmpdir)
dat = sim.create_data(y, sigma, reps=n_reps, output_dir=output_dir)
if MNI_Template["resolution"] == '2mm':
shape_3d = (91, 109, 91)
shape_2d = (6, 238955)
elif MNI_Template["resolution"] == '3mm':
shape_3d = (60, 72, 60)
shape_2d = (6, 71020)
y = pd.read_csv(os.path.join(str(tmpdir.join('y.csv'))),header=None, index_col=None)
holdout = pd.read_csv(os.path.join(str(tmpdir.join('rep_id.csv'))),header=None,index_col=None)
# Test load list of 4D images
file_list = [str(tmpdir.join('data.nii.gz')), str(tmpdir.join('data.nii.gz'))]
dat = Brain_Data(file_list)
dat = Brain_Data([nb.load(x) for x in file_list])
# Test load list
dat = Brain_Data(data=str(tmpdir.join('data.nii.gz')), Y=y)
# Test concatenate
out = Brain_Data([x for x in dat])
assert isinstance(out, Brain_Data)
assert len(out)==len(dat)
# Test to_nifti
d = dat.to_nifti()
assert d.shape[0:3] == shape_3d
# Test load nibabel
assert Brain_Data(d)
# Test shape
assert dat.shape() == shape_2d
# Test Mean
assert dat.mean().shape()[0] == shape_2d[1]
# Test Std
assert dat.std().shape()[0] == shape_2d[1]
# Test add
new = dat + dat
assert new.shape() == shape_2d
# Test subtract
new = dat - dat
assert new.shape() == shape_2d
# Test multiply
new = dat * dat
assert new.shape() == shape_2d
# Test Indexing
index = [0, 3, 1]
assert len(dat[index]) == len(index)
index = range(4)
assert len(dat[index]) == len(index)
index = dat.Y == 1
assert len(dat[index.values.flatten()]) == index.values.sum()
assert len(dat[index]) == index.values.sum()
assert len(dat[:3]) == 3
# Test Iterator
x = [x for x in dat]
assert len(x) == len(dat)
assert len(x[0].data.shape) == 1
# # Test T-test
out = dat.ttest()
assert out['t'].shape()[0] == shape_2d[1]
# # # Test T-test - permutation method
# out = dat.ttest(threshold_dict={'permutation':'tfce','n_permutations':50,'n_jobs':1})
# assert out['t'].shape()[0]==shape_2d[1]
# Test Regress
dat.X = pd.DataFrame({'Intercept':np.ones(len(dat.Y)),
'X1':np.array(dat.Y).flatten()}, index=None)
# Standard OLS
out = dat.regress()
assert type(out['beta'].data) == np.ndarray
assert type(out['t'].data) == np.ndarray
assert type(out['p'].data) == np.ndarray
assert type(out['residual'].data) == np.ndarray
assert type(out['df'].data) == np.ndarray
assert out['beta'].shape() == (2, shape_2d[1])
assert out['t'][1].shape()[0] == shape_2d[1]
# Robust OLS
out = dat.regress(mode='robust')
assert type(out['beta'].data) == np.ndarray
assert type(out['t'].data) == np.ndarray
assert type(out['p'].data) == np.ndarray
assert type(out['residual'].data) == np.ndarray
assert type(out['df'].data) == np.ndarray
assert out['beta'].shape() == (2, shape_2d[1])
assert out['t'][1].shape()[0] == shape_2d[1]
# Test threshold
i=1
tt = threshold(out['t'][i], out['p'][i], .05)
assert isinstance(tt, Brain_Data)
# Test write
dat.write(os.path.join(str(tmpdir.join('test_write.nii'))))
assert Brain_Data(os.path.join(str(tmpdir.join('test_write.nii'))))
# Test append
assert dat.append(dat).shape()[0] == shape_2d[0]*2
# Test distance
distance = dat.distance(method='euclidean')
assert isinstance(distance, Adjacency)
assert distance.square_shape()[0] == shape_2d[0]
# Test predict
stats = dat.predict(algorithm='svm',
cv_dict={'type': 'kfolds', 'n_folds': 2},
plot=False, **{'kernel':"linear"})
# Support Vector Regression, with 5 fold cross-validation with Platt Scaling
# This will output probabilities of each class
stats = dat.predict(algorithm='svm',
cv_dict=None, plot=False,
**{'kernel':'linear', 'probability':True})
assert isinstance(stats['weight_map'], Brain_Data)
# Logistic classificiation, with 2 fold cross-validation.
stats = dat.predict(algorithm='logistic',
cv_dict={'type': 'kfolds', 'n_folds': 2},
plot=False)
assert isinstance(stats['weight_map'], Brain_Data)
# Ridge classificiation,
stats = dat.predict(algorithm='ridgeClassifier', cv_dict=None, plot=False)
assert isinstance(stats['weight_map'], Brain_Data)
# Ridge
stats = dat.predict(algorithm='ridge',
cv_dict={'type': 'kfolds', 'n_folds': 2,
'subject_id':holdout}, plot=False, **{'alpha':.1})
# Lasso
stats = dat.predict(algorithm='lasso',
cv_dict={'type': 'kfolds', 'n_folds': 2,
'stratified':dat.Y}, plot=False, **{'alpha':.1})
# PCR
stats = dat.predict(algorithm='pcr', cv_dict=None, plot=False)
# Test Similarity
r = dat.similarity(stats['weight_map'])
assert len(r) == shape_2d[0]
r2 = dat.similarity(stats['weight_map'].to_nifti())
assert len(r2) == shape_2d[0]
r = dat.similarity(stats['weight_map'], method='dot_product')
assert len(r) == shape_2d[0]
r = dat.similarity(stats['weight_map'], method='cosine')
assert len(r) == shape_2d[0]
r = dat.similarity(dat, method='correlation')
assert r.shape == (dat.shape()[0],dat.shape()[0])
r = dat.similarity(dat, method='dot_product')
assert r.shape == (dat.shape()[0],dat.shape()[0])
r = dat.similarity(dat, method='cosine')
assert r.shape == (dat.shape()[0],dat.shape()[0])
# Test apply_mask - might move part of this to test mask suite
s1 = create_sphere([12, 10, -8], radius=10)
assert isinstance(s1, nb.Nifti1Image)
masked_dat = dat.apply_mask(s1)
assert masked_dat.shape()[1] == np.sum(s1.get_data() != 0)
# Test extract_roi
mask = create_sphere([12, 10, -8], radius=10)
assert len(dat.extract_roi(mask)) == shape_2d[0]
# Test r_to_z
z = dat.r_to_z()
assert z.shape() == dat.shape()
# Test copy
d_copy = dat.copy()
assert d_copy.shape() == dat.shape()
# Test detrend
detrend = dat.detrend()
assert detrend.shape() == dat.shape()
# Test standardize
s = dat.standardize()
assert s.shape() == dat.shape()
assert np.isclose(np.sum(s.mean().data), 0, atol=.1)
s = dat.standardize(method='zscore')
assert s.shape() == dat.shape()
assert np.isclose(np.sum(s.mean().data), 0, atol=.1)
# Test Sum
s = dat.sum()
assert s.shape() == dat[1].shape()
# Test Groupby
s1 = create_sphere([12, 10, -8], radius=10)
s2 = create_sphere([22, -2, -22], radius=10)
mask = Brain_Data([s1, s2])
d = dat.groupby(mask)
assert isinstance(d, Groupby)
# Test Aggregate
mn = dat.aggregate(mask, 'mean')
assert isinstance(mn, Brain_Data)
assert len(mn.shape()) == 1
# Test Threshold
s1 = create_sphere([12, 10, -8], radius=10)
s2 = create_sphere([22, -2, -22], radius=10)
mask = Brain_Data(s1)*5
mask = mask + Brain_Data(s2)
m1 = mask.threshold(upper=.5)
m2 = mask.threshold(upper=3)
m3 = mask.threshold(upper='98%')
m4 = Brain_Data(s1)*5 + Brain_Data(s2)*-.5
m4 = mask.threshold(upper=.5,lower=-.3)
assert np.sum(m1.data > 0) > np.sum(m2.data > 0)
assert np.sum(m1.data > 0) == np.sum(m3.data > 0)
assert np.sum(m4.data[(m4.data > -.3) & (m4.data <.5)]) == 0
assert np.sum(m4.data[(m4.data < -.3) | (m4.data >.5)]) > 0
# Test Regions
r = mask.regions(min_region_size=10)
m1 = Brain_Data(s1)
m2 = r.threshold(1, binarize=True)
# assert len(r)==2
assert len(np.unique(r.to_nifti().get_data())) == 2
diff = m2-m1
assert np.sum(diff.data) == 0
# Test Bootstrap
masked = dat.apply_mask(create_sphere(radius=10, coordinates=[0, 0, 0]))
n_samples = 3
b = masked.bootstrap('mean', n_samples=n_samples)
assert isinstance(b['Z'], Brain_Data)
b = masked.bootstrap('std', n_samples=n_samples)
assert isinstance(b['Z'], Brain_Data)
b = masked.bootstrap('predict', n_samples=n_samples, plot=False)
assert isinstance(b['Z'], Brain_Data)
b = masked.bootstrap('predict', n_samples=n_samples,
plot=False, cv_dict={'type':'kfolds','n_folds':3})
assert isinstance(b['Z'], Brain_Data)
b = masked.bootstrap('predict', n_samples=n_samples,
save_weights=True, plot=False)
assert len(b['samples'])==n_samples
# Test decompose
n_components = 3
stats = dat.decompose(algorithm='pca', axis='voxels',
n_components=n_components)
assert n_components == len(stats['components'])
assert stats['weights'].shape == (len(dat), n_components)
stats = dat.decompose(algorithm='ica', axis='voxels',
n_components=n_components)
assert n_components == len(stats['components'])
assert stats['weights'].shape == (len(dat), n_components)
dat.data = dat.data + 2
dat.data[dat.data<0] = 0
stats = dat.decompose(algorithm='nnmf', axis='voxels',
n_components=n_components)
assert n_components == len(stats['components'])
assert stats['weights'].shape == (len(dat), n_components)
stats = dat.decompose(algorithm='fa', axis='voxels',
n_components=n_components)
assert n_components == len(stats['components'])
assert stats['weights'].shape == (len(dat), n_components)
stats = dat.decompose(algorithm='pca', axis='images',
n_components=n_components)
assert n_components == len(stats['components'])
assert stats['weights'].shape == (len(dat), n_components)
stats = dat.decompose(algorithm='ica', axis='images',
n_components=n_components)
assert n_components == len(stats['components'])
assert stats['weights'].shape == (len(dat), n_components)
dat.data = dat.data + 2
dat.data[dat.data<0] = 0
stats = dat.decompose(algorithm='nnmf', axis='images',
n_components=n_components)
assert n_components == len(stats['components'])
assert stats['weights'].shape == (len(dat), n_components)
stats = dat.decompose(algorithm='fa', axis='images',
n_components=n_components)
assert n_components == len(stats['components'])
assert stats['weights'].shape == (len(dat), n_components)
# Test Hyperalignment Method
sim = Simulator()
y = [0, 1]
n_reps = 10
s1 = create_sphere([0, 0, 0], radius=3)
d1 = sim.create_data(y, 1, reps=n_reps, output_dir=None).apply_mask(s1)
d2 = sim.create_data(y, 2, reps=n_reps, output_dir=None).apply_mask(s1)
d3 = sim.create_data(y, 3, reps=n_reps, output_dir=None).apply_mask(s1)
# Test procrustes using align
data = [d1, d2, d3]
out = align(data, method='procrustes')
assert len(data) == len(out['transformed'])
assert len(data) == len(out['transformation_matrix'])
assert data[0].shape() == out['common_model'].shape()
transformed = np.dot(d1.data, out['transformation_matrix'][0])
centered = d1.data - np.mean(d1.data, 0)
transformed = (np.dot(centered/np.linalg.norm(centered), out['transformation_matrix'][0])*out['scale'][0])
np.testing.assert_almost_equal(0, np.sum(out['transformed'][0].data - transformed), decimal=5)
# Test deterministic brain_data
bout = d1.align(out['common_model'], method='deterministic_srm')
assert d1.shape() == bout['transformed'].shape()
assert d1.shape() == bout['common_model'].shape()
assert d1.shape()[1] == bout['transformation_matrix'].shape[0]
btransformed = np.dot(d1.data, bout['transformation_matrix'])
np.testing.assert_almost_equal(0, np.sum(bout['transformed'].data - btransformed))
# Test deterministic brain_data
bout = d1.align(out['common_model'], method='probabilistic_srm')
assert d1.shape() == bout['transformed'].shape()
assert d1.shape() == bout['common_model'].shape()
assert d1.shape()[1] == bout['transformation_matrix'].shape[0]
btransformed = np.dot(d1.data, bout['transformation_matrix'])
np.testing.assert_almost_equal(0, np.sum(bout['transformed'].data-btransformed))
# Test procrustes brain_data
bout = d1.align(out['common_model'], method='procrustes')
assert d1.shape() == bout['transformed'].shape()
assert d1.shape() == bout['common_model'].shape()
assert d1.shape()[1] == bout['transformation_matrix'].shape[0]
centered = d1.data - np.mean(d1.data, 0)
btransformed = (np.dot(centered/np.linalg.norm(centered), bout['transformation_matrix'])*bout['scale'])
np.testing.assert_almost_equal(0, np.sum(bout['transformed'].data-btransformed), decimal=5)
np.testing.assert_almost_equal(0, np.sum(out['transformed'][0].data - bout['transformed'].data))
# Test hyperalignment on Brain_Data over time (axis=1)
sim = Simulator()
y = [0, 1]
n_reps = 10
s1 = create_sphere([0, 0, 0], radius=5)
d1 = sim.create_data(y, 1, reps=n_reps, output_dir=None).apply_mask(s1)
d2 = sim.create_data(y, 2, reps=n_reps, output_dir=None).apply_mask(s1)
d3 = sim.create_data(y, 3, reps=n_reps, output_dir=None).apply_mask(s1)
data = [d1, d2, d3]
out = align(data, method='procrustes', axis=1)
assert len(data) == len(out['transformed'])
assert len(data) == len(out['transformation_matrix'])
assert data[0].shape() == out['common_model'].shape()
centered = data[0].data.T-np.mean(data[0].data.T, 0)
transformed = (np.dot(centered/np.linalg.norm(centered), out['transformation_matrix'][0])*out['scale'][0])
np.testing.assert_almost_equal(0,np.sum(out['transformed'][0].data-transformed.T), decimal=5)
bout = d1.align(out['common_model'], method='deterministic_srm', axis=1)
assert d1.shape() == bout['transformed'].shape()
assert d1.shape() == bout['common_model'].shape()
assert d1.shape()[0] == bout['transformation_matrix'].shape[0]
btransformed = np.dot(d1.data.T, bout['transformation_matrix'])
np.testing.assert_almost_equal(0, np.sum(bout['transformed'].data-btransformed.T))
bout = d1.align(out['common_model'], method='probabilistic_srm', axis=1)
assert d1.shape() == bout['transformed'].shape()
assert d1.shape() == bout['common_model'].shape()
assert d1.shape()[0] == bout['transformation_matrix'].shape[0]
btransformed = np.dot(d1.data.T, bout['transformation_matrix'])
np.testing.assert_almost_equal(0, np.sum(bout['transformed'].data-btransformed.T))
bout = d1.align(out['common_model'], method='procrustes', axis=1)
assert d1.shape() == bout['transformed'].shape()
assert d1.shape() == bout['common_model'].shape()
assert d1.shape()[0] == bout['transformation_matrix'].shape[0]
centered = d1.data.T-np.mean(d1.data.T, 0)
btransformed = (np.dot(centered/np.linalg.norm(centered), bout['transformation_matrix'])*bout['scale'])
np.testing.assert_almost_equal(0, np.sum(bout['transformed'].data-btransformed.T), decimal=5)
np.testing.assert_almost_equal(0, np.sum(out['transformed'][0].data-bout['transformed'].data))
# visualize which regions are more central in this analysis.
from sklearn.metrics import pairwise_distances
from nltools.data import Adjacency
from nltools.mask import roi_to_brain
import pandas as pd
import numpy as np
sub_list = data.X['SubjectID'].unique()
# perform matrix multiplication to compute linear contrast for each subject
lin_contrast = []
for sub in sub_list:
lin_contrast.append(data[data.X['SubjectID'] == sub] * np.array([1, -1, 0]))
# concatenate list of Brain_Data instances into a single instance
lin_contrast = Brain_Data(lin_contrast)
# Compute correlation distance between each ROI
dist = Adjacency(pairwise_distances(lin_contrast.extract_roi(mask), metric='correlation'), matrix_type='distance')
# Threshold functional connectivity and convert to Adjacency Matrix. Plot as heatmap
dist.threshold(upper=.4, binarize=True).plot()
# Convert Adjacency matrix to networkX instance
g = dist.threshold(upper=.4, binarize=True).to_graph()
# Compute degree centrality and convert back into Brain_Data instance.
degree_centrality = roi_to_brain(pd.Series(dict(g.degree())), mask_x)
degree_centrality.plot()
hv.extension('bokeh')
hv.output(size=200)
### Data
This tutorial will be using the **Sherlock** dataset and will require downloading the Average ROI **csv** files.
We have already extracted the data for you to make this easier and have written out the average activity within each ROI into a separate csv file for each participant. If you would like to get practice doing this yourself, here is the code we used. Note that we are working with the hdf5 files as they load much faster than the nifti images, but either one will work for this example.
``` python
for scan in ['Part1', 'Part2']:
file_list = glob.glob(os.path.join(data_dir, 'fmriprep', '*', 'func', f'*crop*{scan}*hdf5'))
for f in file_list:
sub = os.path.basename(f).split('_')[0]
print(sub)
data = Brain_Data(f)
roi = data.extract_roi(mask)
pd.DataFrame(roi.T).to_csv(os.path.join(os.path.dirname(f), f"{sub}_{scan}_Average_ROI_n50.csv" ), index=False)
```
You will want to change `datadir` to wherever you have installed the Sherlock datalad repository. We will initialize a datalad dataset instance and get the files we need for this tutorial. If you've already downloaded everything, this cell should execute quickly. See the [Download Data Tutorial](http://naturalistic-data.org/features/notebooks/Download_Data.html) for more information about how to install and use datalad.
datadir = '/Volumes/Engram/Data/Sherlock'
# If dataset hasn't been installed, clone from GIN repository
if not os.path.exists(datadir):
dl.clone(source='https://gin.g-node.org/ljchang/Sherlock', path=datadir)
# Initialize dataset
ds = dl.Dataset(datadir)
# Get Cropped & Denoised CSV Files
def test_brain_data(tmpdir):
sim = Simulator()
r = 10
sigma = 1
y = [0, 1]
n_reps = 3
output_dir = str(tmpdir)
sim.create_data(y, sigma, reps=n_reps, output_dir=output_dir)
shape_3d = (91, 109, 91)
shape_2d = (6, 238955)
y=pd.read_csv(os.path.join(str(tmpdir.join('y.csv'))), header=None,index_col=None).T
holdout=pd.read_csv(os.path.join(str(tmpdir.join('rep_id.csv'))),header=None,index_col=None).T
flist = glob.glob(str(tmpdir.join('centered*.nii.gz')))
# Test load list
dat = Brain_Data(data=flist,Y=y)
# Test load file
assert Brain_Data(flist[0])
# Test to_nifti
d = dat.to_nifti()
assert d.shape[0:3] == shape_3d
# Test load nibabel
assert Brain_Data(d)
# Test shape
assert dat.shape() == shape_2d
# Test Mean
assert dat.mean().shape()[0] == shape_2d[1]
# Test Std
assert dat.std().shape()[0] == shape_2d[1]
# Test add
new = dat + dat
assert new.shape() == shape_2d
# Test subtract
new = dat - dat
assert new.shape() == shape_2d
# Test multiply
new = dat * dat
assert new.shape() == shape_2d
# Test Iterator
x = [x for x in dat]
assert len(x) == len(dat)
assert len(x[0].data.shape) == 1
# # Test T-test
out = dat.ttest()
assert out['t'].shape()[0] == shape_2d[1]
# # # Test T-test - permutation method
# out = dat.ttest(threshold_dict={'permutation':'tfce','n_permutations':50,'n_jobs':1})
# assert out['t'].shape()[0]==shape_2d[1]
# Test Regress
dat.X = pd.DataFrame({'Intercept':np.ones(len(dat.Y)), 'X1':np.array(dat.Y).flatten()},index=None)
out = dat.regress()
assert out['beta'].shape() == (2,shape_2d[1])
# Test indexing
assert out['t'][1].shape()[0] == shape_2d[1]
# Test threshold
i=1
tt = threshold(out['t'][i], out['p'][i], .05)
assert isinstance(tt,Brain_Data)
# Test write
dat.write(os.path.join(str(tmpdir.join('test_write.nii'))))
assert Brain_Data(os.path.join(str(tmpdir.join('test_write.nii'))))
# Test append
assert dat.append(dat).shape()[0]==shape_2d[0]*2
# Test distance
distance = dat.distance(method='euclidean')
assert isinstance(distance,Adjacency)
assert distance.square_shape()[0]==shape_2d[0]
# Test predict
stats = dat.predict(algorithm='svm', cv_dict={'type': 'kfolds','n_folds': 2}, plot=False,**{'kernel':"linear"})
# Support Vector Regression, with 5 fold cross-validation with Platt Scaling
# This will output probabilities of each class
stats = dat.predict(algorithm='svm', cv_dict=None, plot=False,**{'kernel':'linear', 'probability':True})
assert isinstance(stats['weight_map'],Brain_Data)
# Logistic classificiation, with 2 fold cross-validation.
stats = dat.predict(algorithm='logistic', cv_dict={'type': 'kfolds', 'n_folds': 2}, plot=False)
assert isinstance(stats['weight_map'],Brain_Data)
# Ridge classificiation,
stats = dat.predict(algorithm='ridgeClassifier', cv_dict=None,plot=False)
assert isinstance(stats['weight_map'],Brain_Data)
# Ridge
stats = dat.predict(algorithm='ridge', cv_dict={'type': 'kfolds', 'n_folds': 2,'subject_id':holdout}, plot=False,**{'alpha':.1})
# Lasso
stats = dat.predict(algorithm='lasso', cv_dict={'type': 'kfolds', 'n_folds': 2,'stratified':dat.Y}, plot=False,**{'alpha':.1})
# PCR
stats = dat.predict(algorithm='pcr', cv_dict=None, plot=False)
# Test Similarity
r = dat.similarity(stats['weight_map'])
assert len(r) == shape_2d[0]
r2 = dat.similarity(stats['weight_map'].to_nifti())
assert len(r2) == shape_2d[0]
# Test apply_mask - might move part of this to test mask suite
s1 = create_sphere([12, 10, -8], radius=10)
assert isinstance(s1, nb.Nifti1Image)
s2 = Brain_Data(s1)
masked_dat = dat.apply_mask(s1)
assert masked_dat.shape()[1] == np.sum(s2.data != 0)
# Test extract_roi
mask = create_sphere([12, 10, -8], radius=10)
assert len(dat.extract_roi(mask)) == shape_2d[0]
# Test r_to_z
z = dat.r_to_z()
assert z.shape() == dat.shape()
# Test copy
d_copy = dat.copy()
assert d_copy.shape() == dat.shape()
# Test detrend
detrend = dat.detrend()
assert detrend.shape() == dat.shape()
# Test standardize
s = dat.standardize()
assert s.shape() == dat.shape()
assert np.isclose(np.sum(s.mean().data), 0, atol=.1)
s = dat.standardize(method='zscore')
assert s.shape() == dat.shape()
assert np.isclose(np.sum(s.mean().data), 0, atol=.1)
# Test Sum
s = dat.sum()
assert s.shape() == dat[1].shape()
# Test Groupby
s1 = create_sphere([12, 10, -8], radius=10)
s2 = create_sphere([22, -2, -22], radius=10)
mask = Brain_Data([s1, s2])
d = dat.groupby(mask)
assert isinstance(d, Groupby)
# Test Aggregate
mn = dat.aggregate(mask, 'mean')
assert isinstance(mn, Brain_Data)
assert len(mn.shape()) == 1
# Test Threshold
s1 = create_sphere([12, 10, -8], radius=10)
s2 = create_sphere([22, -2, -22], radius=10)
mask = Brain_Data(s1)*5
mask = mask + Brain_Data(s2)
m1 = mask.threshold(thresh=.5)
m2 = mask.threshold(thresh=3)
m3 = mask.threshold(thresh='98%')
assert np.sum(m1.data > 0) > np.sum(m2.data > 0)
assert np.sum(m1.data > 0) == np.sum(m3.data > 0)
# Test Regions
r = mask.regions(min_region_size=10)
m1 = Brain_Data(s1)
m2 = r.threshold(1, binarize=True)
# assert len(r)==2
assert len(np.unique(r.to_nifti().get_data())) == 2 # JC edit: I think this is what you were trying to do
diff = m2-m1
assert np.sum(diff.data) == 0
# Get data and covariates file and create nuisance design matrix
print(preproc_dir, subject_id, episode)
sub_cov, sub_epi = fileGetter(preproc_dir,subject_id,episode)
#Load run data
print("Loading brain data: {}".format(smooth))
dat = Brain_Data(sub_epi)
cov_mat = Design_Matrix(pd.read_csv(sub_cov[0]).fillna(0), sampling_rate=TR)
# Add Intercept
cov_mat['Intercept'] = 1
# Add Linear Trend
cov_mat['LinearTrend'] = range(cov_mat.shape[0])-np.mean(range(cov_mat.shape[0]))
cov_mat['QuadraticTrend'] = cov_mat['LinearTrend']**2
cov_mat['CSF'] = dat.extract_roi(csf.threshold(.85,binarize=True))
assert cov_mat.shape[0] == dat.shape()[0]
spikeless_idx = np.logical_not( startswith(cov_mat.columns.values.astype(str), "spike") | startswith(cov_mat.columns.values.astype(str), "FD") )
#dat.X = cov_mat
dat.X = cov_mat.loc[:,spikeless_idx]
datcln = dat.regress()['residual']
# ## Loop through voxels to produce STPs
# In[14]:
zero_voxels = np.apply_along_axis(lambda x: np.count_nonzero(x) == 0, axis=0, arr=datcln.data)
zero_voxels = np.arange(datcln.data.shape[1])[zero_voxels]
