edb300280cd7854bb58e023d01ac24160bf6d98d,neurosynth/analysis/cluster.py,Clusterer,__init__,#Clusterer#Any#Any#Any#Any#Any#Any#Any#Any#Any#Any#Any#Any#,22

Before Change

        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

After Change

        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 = sum_vox > min_studies_per_voxel
            // n_active_vox = active_vox.shape[0]
            av = self.masker.unmask(active_vox, output="vector")
            self.masker.add(av)

            // 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

        if distance_mask is not None:
            self.masker.add(distance_mask)

Instances