def test_miyawaki2008(): dataset = datasets.fetch_miyawaki2008(data_dir=tmpdir, verbose=0) assert_equal(len(dataset.func), 32) assert_equal(len(dataset.label), 32) assert_true(isinstance(dataset.mask, _basestring)) assert_equal(len(dataset.mask_roi), 38) assert_equal(len(url_request.urls), 1)
:ref:`sphx_glr_auto_examples_02_decoding_plot_miyawaki_encoding.py` for a encoding approach for the same dataset. """ # Some basic imports import time import sys ############################################################################ # First we load the Miyawaki dataset # ----------------------------------- from nilearn import datasets sys.stderr.write("Fetching dataset...") t0 = time.time() miyawaki_dataset = datasets.fetch_miyawaki2008() # print basic information on the dataset print('First functional nifti image (4D) is located at: %s' % miyawaki_dataset.func[0]) # 4D data X_random_filenames = miyawaki_dataset.func[12:] X_figure_filenames = miyawaki_dataset.func[:12] y_random_filenames = miyawaki_dataset.label[12:] y_figure_filenames = miyawaki_dataset.label[:12] y_shape = (10, 10) sys.stderr.write(" Done (%.2fs).\n" % (time.time() - t0)) ############################################################################ # Then we prepare and mask the data
It reconstructs 10x10 binary images from functional MRI data. Random images are used as training set and structured images are used for reconstruction. """ ### Imports ################################################################### from matplotlib import pyplot as plt import time import sys ### Load Kamitani dataset ##################################################### from nilearn import datasets sys.stderr.write("Fetching dataset...") t0 = time.time() miyawaki_dataset = datasets.fetch_miyawaki2008() X_random_filenames = miyawaki_dataset.func[12:] X_figure_filenames = miyawaki_dataset.func[:12] y_random_filenames = miyawaki_dataset.label[12:] y_figure_filenames = miyawaki_dataset.label[:12] y_shape = (10, 10) sys.stderr.write(" Done (%.2fs).\n" % (time.time() - t0)) ### Preprocess and mask ####################################################### import numpy as np from nilearn.input_data import MultiNiftiMasker sys.stderr.write("Preprocessing data...") t0 = time.time()
from the binary pixel-values of the presented images. Then we extract the receptive fields for a set of voxels to see which pixel location a voxel is most sensitive to. See also :doc:`plot_miyawaki_reconstruction` for a decoding approach for the same dataset. """ ############################################################################## # Loading the data # ---------------- # Now we can load the data set: from nilearn.datasets import fetch_miyawaki2008 dataset = fetch_miyawaki2008() ############################################################################## # We only use the training data of this study, # where random binary images were shown. # training data starts after the first 12 files fmri_random_runs_filenames = dataset.func[12:] stimuli_random_runs_filenames = dataset.label[12:] ############################################################################## # We can use :func:`nilearn.input_data.MultiNiftiMasker` to load the fMRI # data, clean and mask it. import numpy as np from nilearn.input_data import MultiNiftiMasker
from core.util.utilities import compute_r2 from sklearn.decomposition import PCA import core.gp.gp_sMTGPR as sMTGPR import core.gp.gp_kronprod as gp_kronprod from core.util.normod import extreme_value_prob, normative_prob_map, extreme_value_prob_fit from sklearn.metrics import roc_auc_score import time ############################################################################### method = 'STGPR' # Select the method among MT_Kronprod, sMT_GPR, STGPR save_path = 'path for saving the results' runs = 10 # Select the number of runs ############################ Loading Data ##################################### miyawaki_dataset = fetch_miyawaki2008() Y_random_filenames = miyawaki_dataset.func[12:] Y_figure_filenames = miyawaki_dataset.func[:12] X_random_filenames = miyawaki_dataset.label[12:] X_figure_filenames = miyawaki_dataset.label[:12] X_shape = (10, 10) masker = MultiNiftiMasker(mask_img=miyawaki_dataset.mask, detrend=True, standardize=False) masker.fit() fmri_random = masker.transform(Y_random_filenames) fmri_figure = masker.transform(Y_figure_filenames) pattern_random = [] for x in X_random_filenames: