X = X[perm]
# 2. CONSTRUCT TRAINING & TEST DATA
rng = check_random_state(42)
X_train, X_test, y_train, y_test = train_test_split(
X, y, train_size=.8, random_state=rng)
###########################################################################
# Fit the SpaceNet and predict with it
decoder = SpaceNetRegressor(memory="nilearn_cache", penalty=fitpenalty,
screening_percentile=screenp, memory_level=2, n_jobs=4)
logging.info('Classifier set up. Starting model fit.')
decoder.fit(X_train, y_train) # fit
logging.info('Model fit complete. Saving outputs...')
y_pred = decoder.predict(X_test).ravel() # predict
mse = np.mean(np.abs(y_test - y_pred))
logging.info('Mean square error (MSE) of the prediction: %.2f' % mse)
# 4. OUTPUTS
# Save csv metadata
inputdata.to_csv(logdir+inputcsv)
# Save decoder object
decoder_dir = './outputs/%s-%sx%s/decoder_sma/' % (timestamp,taskcode,predictor) # directory
if not os.path.exists(decoder_dir):
os.makedirs(decoder_dir) # create if missing
dec_filename = '%s%s_decoder_SpaceNet_%sscreen%d.jbl' % (
decoder_dir, timestamp, decoder.penalty, screenp)
joblib.dump(decoder, dec_filename)
# Save coefficients to nifti file
# -------------------------------------
from nilearn.decoding import SpaceNetRegressor
# To save time (because these are anat images with many voxels), we include
# only the 5-percent voxels most correlated with the age variable to fit.
# Also, we set memory_level=2 so that more of the intermediate computations
# are cached. Also, you may pass and n_jobs=<some_high_value> to the
# SpaceNetRegressor class, to take advantage of a multi-core system.
#
# Also, here we use a graph-net penalty but more beautiful results can be
# obtained using the TV-l1 penalty, at the expense of longer runtimes.
decoder = SpaceNetRegressor(memory="nilearn_cache", penalty="graph-net",
screening_percentile=5., memory_level=2)
decoder.fit(gm_imgs_train, age_train) # fit
coef_img = decoder.coef_img_
y_pred = decoder.predict(gm_imgs_test).ravel() # predict
mse = np.mean(np.abs(age_test - y_pred))
print('Mean square error (MSE) on the predicted age: %.2f' % mse)
###########################################################################
# Visualize the resulting maps
from nilearn.plotting import plot_stat_map, show
# weights map
background_img = gm_imgs[0]
plot_stat_map(coef_img, background_img, title="graph-net weights",
display_mode="z", cut_coords=1)
###########################################################################
# Visualize the quality of predictions
