def new_SpaceNet(self):
if self.task == "classification":
decoder = SpaceNetClassifier(memory="nilearn_cache",
penalty=self.penalty,
screening_percentile=15.,
memory_level=1)
else:
decoder = SpaceNetRegressor(memory="nilearn_cache",
penalty=self.penalty,
screening_percentile=15.,
memory_level=1)
return decoder
from nilearn.image import index_img
niimgs = nibabel.load(data_files.func[0])
X_train = index_img(niimgs, condition_mask_train)
X_test = index_img(niimgs, condition_mask_test)
y_train = target[condition_mask_train]
y_test = target[condition_mask_test]
### Loop over Graph-Net and TV-L1 penalties ##################################
from nilearn.decoding import SpaceNetClassifier
import matplotlib.pyplot as plt
from nilearn.image import mean_img
from nilearn.plotting import plot_stat_map
background_img = mean_img(data_files.func[0])
for penalty in ['graph-net', 'tv-l1']:
### Fit model on train data and predict on test data ######################
decoder = SpaceNetClassifier(memory="cache", penalty=penalty)
decoder.fit(X_train, y_train)
y_pred = decoder.predict(X_test)
accuracy = (y_pred == y_test).mean() * 100.
### Visualization #########################################################
print("Results")
print("=" * 80)
coef_img = decoder.coef_img_
plot_stat_map(coef_img,
background_img,
title="%s: accuracy %g%%" % (penalty, accuracy),
cut_coords=(-34, -16),
display_mode="yz")
coef_img.to_filename('haxby_%s_weights.nii' % penalty)
print("- %s %s" % (penalty, '-' * 60))
y_test = conditions[condition_mask_test]
X_test.shape
# Compute the mean epi to be used for the background of the plotting
from nilearn.image import mean_img
background_img = mean_img(dataset)
## SET & RUN CLASSIFIER - SPACENET WITH GRAPHNET
from nilearn.decoding import SpaceNetClassifier
# Fit model on train data and predict on test data
decoder = SpaceNetClassifier(
memory_level=1,
n_jobs=4,
memory=
'/projects/niblab/bids_projects/Experiments/ChocoData/derivatives/code/decoding',
mask=imag_mask,
standardize=True,
penalty='graph-net')
decoder.fit(X_train, y_train)
y_pred = decoder.predict(X_test)
accuracy = (y_pred == y_test).mean() * 100.
print("Graph-net classification accuracy : %g%%" % accuracy)
## VISUALIZE AND SAVE RESULTS
from nilearn.plotting import plot_stat_map, show
coef_img = decoder.coef_img_
display = plot_stat_map(coef_img,
background_img,
# Split data into train and test samples, using the chunks
condition_mask_train = (condition_mask) & (behavioral['sess'] == 0)
condition_mask_test = (condition_mask) & (behavioral['sess'] == 1)
# Apply this sample mask to X (fMRI data) and y (behavioral labels)
# Because the data is in one single large 4D image, we need to use
# index_img to do the split easily
X_train = index_img(dataset, condition_mask_train)
X_test = index_img(dataset, condition_mask_test)
y_train = y[condition_mask_train]
y_test = y[condition_mask_test]
X_test.shape
# Compute the mean epi to be used for the background of the plotting
from nilearn.image import mean_img
background_img = mean_img(dataset)
## SET & RUN CLASSIFIER - SPACENET WITH GRAPHNET
from nilearn.decoding import SpaceNetClassifier
# Fit model on train data and predict on test data
decoder = SpaceNetClassifier(
memory_level=2,
n_jobs=16,
memory=
'/projects/niblab/bids_projects/Experiments/ChocoData/derivatives\/code/decoding',
mask=imag_mask,
standardize=True,
penalty='graph-net')
decoder.fit(X_train, y_train)
X_train = index_img(func_filenames, condition_mask_train)
X_test = index_img(func_filenames, condition_mask_test)
y_train = target[condition_mask_train]
y_test = target[condition_mask_test]
# Compute the mean epi to be used for the background of the plotting
from nilearn.image import mean_img
background_img = mean_img(func_filenames)
##############################################################################
# Fit SpaceNet with a Graph-Net penalty
from nilearn.decoding import SpaceNetClassifier
# Fit model on train data and predict on test data
decoder = SpaceNetClassifier(memory="nilearn_cache", penalty="graph-net")
decoder.fit(X_train, y_train)
y_pred = decoder.predict(X_test)
accuracy = (y_pred == y_test).mean() * 100.0
print("Graph-net classification accuracy : %g%%" % accuracy)
# Visualization
from nilearn.plotting import plot_stat_map, show
coef_img = decoder.coef_img_
plot_stat_map(
coef_img, background_img, title="graph-net: accuracy %g%%" % accuracy, cut_coords=(-34, -16), display_mode="yz"
)
# Save the coefficients to a nifti file
coef_img.to_filename("haxby_graph-net_weights.nii")
X_train = index_img(func_filenames, condition_mask_train)
X_test = index_img(func_filenames, condition_mask_test)
y_train = target[condition_mask_train]
y_test = target[condition_mask_test]
# Compute the mean epi to be used for the background of the plotting
from nilearn.image import mean_img
background_img = mean_img(func_filenames)
##############################################################################
# Fit SpaceNet with a Graph-Net penalty
from nilearn.decoding import SpaceNetClassifier
# Fit model on train data and predict on test data
decoder = SpaceNetClassifier(memory="nilearn_cache", penalty='graph-net')
decoder.fit(X_train, y_train)
y_pred = decoder.predict(X_test)
accuracy = (y_pred == y_test).mean() * 100.
print("Graph-net classification accuracy : %g%%" % accuracy)
# Visualization
from nilearn.plotting import plot_stat_map, show
coef_img = decoder.coef_img_
plot_stat_map(coef_img,
background_img,
title="graph-net: accuracy %g%%" % accuracy,
cut_coords=(-34, -16),
display_mode="yz")
X_test = index_img(func_filenames, condition_mask_test)
y_train = target[condition_mask_train]
y_test = target[condition_mask_test]
# Compute the mean epi to be used for the background of the plotting
from nilearn.image import mean_img
background_img = mean_img(func_filenames)
background_img.to_filename("bg.nii.gz")
##############################################################################
# Fit SpaceNet with a Graph-Net penalty
from nilearn.decoding import SpaceNetClassifier
# Fit model on train data and predict on test data
decoder = SpaceNetClassifier(memory="nilearn_cache",
penalty='graph-net',
memory_level=2,
screening_percentile=20.)
decoder.fit(X_train, y_train)
y_pred = decoder.predict(X_test)
accuracy = (y_pred == y_test).mean() * 100.
print("Graph-net classification accuracy : %g%%" % accuracy)
# Visualization
from nilearn.plotting import plot_stat_map, show
coef_img = decoder.coef_img_
plot_stat_map(coef_img,
background_img,
title="graph-net: accuracy %g%%" % accuracy,
cut_coords=(-34, -16),
display_mode="yz")