def test_apply_grid_to_image(self): data, grid = reduce.apply_grid(self.dataset, scale=6) self.assertEquals(data.shape, (1435, 5)) sums = np.sum(data, 0) self.assertGreater(sums[2], sums[3]) self.assertGreater(sums[4], sums[0])
def __init__(self, dataset=None, algorithm=None, output_dir='.', grid_scale=None, features=None, feature_threshold=0.0, global_mask=None, roi_mask=None, distance_mask=None, min_voxels_per_study=None, min_studies_per_voxel=None, distance_metric=None, **kwargs): """ Initialize Clusterer. Args: dataset: The dataset to use for clustering. Either a Dataset instance or a numpy array with voxels in rows and features in columns. algorithm: Optional algorithm to use for clustering. If None, an algorithm must be passed to the cluster() method later. output_directory: Directory to use for writing all outputs. grid_scale: Optional integer. If provided, a 3D grid will be applied to the image data, with values in all voxels in each grid cell being averaged prior to clustering analysis. This is an effective means of dimension reduction in cases where the data are otherwise too large for clustering. features: Optional features to use for selecting a subset of the studies in the Dataset instance. If dataset is a numpy matrix, will be ignored. feature_threshold: float; the threshold to use for feature selection. Will be ignored if features is None. global_mask: An image defining the space to use for all analyses. Only necessary if dataset is a numpy array. roi_mask: An image that determines which voxels to cluster. All non-zero voxels will be included in the clustering analysis. When roi_mask is None, all voxels in the global_mask (i.e., the whole brain) will be clustered. roi_mask can be an image filename, a nibabel image, or an already-masked array with the same dimensions as the global_mask. distance_mask: An image defining the voxels to base the distance matrix computation on. All non-zero voxels will be used to compute the distance matrix. For example, if the roi_mask contains voxels in only the insula, and distance_mask contains voxels in only the cerebellum, then voxels in the insula will be clustered based on the similarity of their coactvation with all and only cerebellum voxels. min_voxels_per_study: An optional integer. If provided, all voxels with fewer than this number of studies will be removed from analysis. min_studies_per_voxel: An optional integer. If provided, all studies with fewer than this number of active voxels will be removed from analysis. distance_metric: Optional string providing the distance metric to use for computation of a distance matrix. When None, no distance matrix is computed and we assume that clustering will be done on the raw data. **kwargs: Additional keyword arguments to pass to the clustering algorithm. """ self.output_dir = output_dir if algorithm is not None: self._set_clustering_algorithm(algorithm, **kwargs) if isinstance(dataset, Dataset): self.dataset = dataset if global_mask is None: global_mask = dataset.masker if features is not None: data = self.dataset.get_ids_by_features(features, threshold=feature_threshold, get_image_data=True) else: data = self.dataset.get_image_data() # if min_studies_per_voxel is not None: # logger.info("Thresholding voxels based on number of studies.") # sum_vox = data.sum(1) # # Save the indices for later reconstruction # active_vox = np.where(sum_vox > min_studies_per_voxel)[0] # n_active_vox = active_vox.shape[0] # if min_voxels_per_study is not None: # logger.info("Thresholding studies based on number of voxels.") # sum_studies = data.sum(0) # active_studies = np.where(sum_studies > min_voxels_per_study)[0] # n_active_studies = active_studies.shape[0] # if min_studies_per_voxel is not None: # logger.info("Selecting voxels with more than %d studies." % min_studies_per_voxel) # data = data[active_vox, :] # if min_voxels_per_study is not None: # logger.info("Selecting studies with more than %d voxels." % min_voxels_per_study) # data = data[:, active_studies] self.data = data else: self.data = dataset if global_mask is None: raise ValueError("If dataset is a numpy array, a valid global_mask (filename, " + "Mask instance, or nibabel image) must be passed.") if not isinstance(global_mask, Masker): global_mask = Masker(global_mask) self.masker = global_mask if distance_mask is not None: self.masker.add(distance_mask) if grid_scale is not None: self.target_data, _ = nsr.apply_grid(self.data, masker=self.masker, scale=grid_scale, threshold=None) else: vox = self.masker.get_current_mask(in_global_mask=True) self.target_data = self.data[vox,:] self.masker.reset() if roi_mask is not None: self.masker.add(roi_mask) if grid_scale is not None: self.data, self.grid = nsr.apply_grid(self.data, masker=self.masker, scale=grid_scale, threshold=None) else: vox = self.masker.get_current_mask(in_global_mask=True) self.data = self.data[vox,:] if distance_metric is not None: self.create_distance_matrix(distance_metric=distance_metric)
def __init__(self, dataset=None, algorithm=None, output_dir='.', grid_scale=None, features=None, feature_threshold=0.0, global_mask=None, roi_mask=None, distance_mask=None, min_voxels_per_study=None, min_studies_per_voxel=None, distance_metric=None, **kwargs): """ Initialize Clusterer. Args: dataset: The dataset to use for clustering. Either a Dataset instance or a numpy array with voxels in rows and features in columns. algorithm: Optional algorithm to use for clustering. If None, an algorithm must be passed to the cluster() method later. output_directory: Directory to use for writing all outputs. grid_scale: Optional integer. If provided, a 3D grid will be applied to the image data, with values in all voxels in each grid cell being averaged prior to clustering analysis. This is an effective means of dimension reduction in cases where the data are otherwise too large for clustering. features: Optional features to use for selecting a subset of the studies in the Dataset instance. If dataset is a numpy matrix, will be ignored. feature_threshold: float; the threshold to use for feature selection. Will be ignored if features is None. global_mask: An image defining the space to use for all analyses. Only necessary if dataset is a numpy array. roi_mask: An image that determines which voxels to cluster. All non-zero voxels will be included in the clustering analysis. When roi_mask is None, all voxels in the global_mask (i.e., the whole brain) will be clustered. roi_mask can be an image filename, a nibabel image, or an already-masked array with the same dimensions as the global_mask. distance_mask: An image defining the voxels to base the distance matrix computation on. All non-zero voxels will be used to compute the distance matrix. For example, if the roi_mask contains voxels in only the insula, and distance_mask contains voxels in only the cerebellum, then voxels in the insula will be clustered based on the similarity of their coactvation with all and only cerebellum voxels. min_voxels_per_study: An optional integer. If provided, all voxels with fewer than this number of studies will be removed from analysis. min_studies_per_voxel: An optional integer. If provided, all studies with fewer than this number of active voxels will be removed from analysis. distance_metric: Optional string providing the distance metric to use for computation of a distance matrix. When None, no distance matrix is computed and we assume that clustering will be done on the raw data. **kwargs: Additional keyword arguments to pass to the clustering algorithm. """ self.output_dir = output_dir if algorithm is not None: self._set_clustering_algorithm(algorithm, **kwargs) if isinstance(dataset, Dataset): self.dataset = dataset if global_mask is None: global_mask = dataset.masker if features is not None: data = self.dataset.get_ids_by_features( features, threshold=feature_threshold, get_image_data=True) else: data = self.dataset.get_image_data() # if min_studies_per_voxel is not None: # logger.info("Thresholding voxels based on number of studies.") # sum_vox = data.sum(1) # # Save the indices for later reconstruction # active_vox = np.where(sum_vox > min_studies_per_voxel)[0] # n_active_vox = active_vox.shape[0] # if min_voxels_per_study is not None: # logger.info("Thresholding studies based on number of voxels.") # sum_studies = data.sum(0) # active_studies = np.where(sum_studies > min_voxels_per_study)[0] # n_active_studies = active_studies.shape[0] # if min_studies_per_voxel is not None: # logger.info("Selecting voxels with more than %d studies." % min_studies_per_voxel) # data = data[active_vox, :] # if min_voxels_per_study is not None: # logger.info("Selecting studies with more than %d voxels." % min_voxels_per_study) # data = data[:, active_studies] self.data = data else: self.data = dataset if global_mask is None: raise ValueError( "If dataset is a numpy array, a valid global_mask (filename, " + "Mask instance, or nibabel image) must be passed.") if not isinstance(global_mask, Masker): global_mask = Masker(global_mask) self.masker = global_mask if distance_mask is not None: self.masker.add(distance_mask) if grid_scale is not None: self.target_data, _ = nsr.apply_grid(self.data, masker=self.masker, scale=grid_scale, threshold=None) else: vox = self.masker.get_current_mask(in_global_mask=True) self.target_data = self.data[vox, :] self.masker.reset() if roi_mask is not None: self.masker.add(roi_mask) if grid_scale is not None: self.data, self.grid = nsr.apply_grid(self.data, masker=self.masker, scale=grid_scale, threshold=None) else: vox = self.masker.get_current_mask(in_global_mask=True) self.data = self.data[vox, :] if distance_metric is not None: self.create_distance_matrix(distance_metric=distance_metric)