def test_ingest_blocks_uint16_8_threads(self): now = datetime.now().strftime("%Y%m%d-%H%M%S%f") self.args.experiment = 'dev_ingest_larger' + now self.args.channel = 'def_files' + now self.args.x_extent = [0, 8 * 1024] self.args.z_range = [0, 16] self.args.datatype = 'uint16' self.args.extension = 'tif' x_size = 8 * 1024 y_size = 1024 stride_x = 1024 x_buckets = get_supercube_lims(self.args.x_extent, stride_x) ingest_job = IngestJob(self.args) gen_images(ingest_job) self.args.create_resources = True result = per_channel_ingest(self.args, self.args.channel) assert result == 0 boss_res_params = BossResParams(ingest_job) boss_res_params.get_resources(get_only=True) z_slices = list(range(self.args.z_range[0], self.args.z_range[-1])) y_rng = self.args.y_extent im_array = ingest_job.read_img_stack(z_slices) threads = 8 ingest_block_partial = partial( ingest_block, x_buckets=x_buckets, boss_res_params=boss_res_params, ingest_job=ingest_job, y_rng=y_rng, z_rng=self.args.z_range, im_array=im_array) start_time = time.time() with ThreadPool(threads) as pool: pool.map(ingest_block_partial, x_buckets.keys()) time_taken = time.time() - start_time print('{} secs taken with {} threads'.format(time_taken, threads)) data_boss = download_boss_slice( boss_res_params, ingest_job, 0)[0, :, :] data_local = im_array[0, :, :] assert np.array_equal(data_boss, data_local) # cleanup ingest_job = IngestJob(self.args) boss_res_params = BossResParams(ingest_job) boss_res_params.get_resources(get_only=True) boss_res_params.rmt.delete_project(boss_res_params.ch_resource) boss_res_params.rmt.delete_project(boss_res_params.exp_resource) os.remove(ingest_job.get_log_fname()) del_test_images(ingest_job)
def test_local_ingest_cuts(self): cut = create_cutout(self.cutout_text) coll, exp, ch = (cut.collection, cut.experiment, cut.channel) datasource, s3_bucket_name, aws_profile, boss_config_file, base_path, base_filename, extension, z_step, datatype = create_local_ingest_params( ) args = Namespace( datasource=datasource, s3_bucket_name=s3_bucket_name, collection=coll, experiment=exp, channel=ch, datatype=datatype, aws_profile=aws_profile, boss_config_file=boss_config_file, base_path=base_path, base_filename=base_filename, extension=extension, z_range=[0, 16], z_step=z_step, warn_missing_files=True, get_extents=True, res=0, ) ingest_job = IngestJob(args) boss_res_params = BossResParams(ingest_job) boss_res_params.setup_boss_coord_frame(get_only=True) boss_res_params.get_resources(get_only=False) gen_images(ingest_job) # ingest the cut ingest_cuts([cut], ingest_job, boss_res_params) # pull the data from the boss after the new ingest data_boss = boss_res_params.rmt.get_cutout(boss_res_params.ch_resource, 0, cut.x, cut.y, cut.z) # test to make sure it's the same as local file z_slices = range(cut.z[0], cut.z[1]) # loading data locally for comparison im_array = ingest_job.read_img_stack(z_slices) data_local = im_array[:, cut.y[0]:cut.y[1], cut.x[0]:cut.x[1]] assert np.array_equal(data_local, data_boss) del_test_images(ingest_job) os.remove(ingest_job.get_log_fname()) os.remove(cut.log_fname)
def test_read_uint16_img_stack(self): ingest_job = IngestJob(self.args) # generate some images gen_images(ingest_job) # load images into memory using ingest_job z_slices = range(self.args.z_range[0], self.args.z_range[1]) im_array = ingest_job.read_img_stack(z_slices) # check to make sure each image is equal to each z index in the array for z in z_slices: img_fname = self.args.base_path + 'img_{:04d}.tif'.format(z) with Image.open(img_fname) as im: assert np.array_equal(im_array[z, :, :], im) del_test_images(ingest_job) os.remove(ingest_job.get_log_fname())
def per_channel_ingest(args, channel, threads=8): args.channel = channel ingest_job = IngestJob(args) # extract img_size and datatype to check inputs (by actually reading the data) # this can take a while, as we actually load in the first image slice, # so we should store this first slice so we don't have to load it again when we later read the entire chunk in z # we don't do this for render data source because we get the image size and attributes from the render metadata and the # of bits aren't in the metadata or render if ingest_job.datasource != 'render': im_width, im_height, im_datatype = ingest_job.get_img_info( ingest_job.z_range[0]) # we do this before creating boss resources that could be inaccurate try: assert ingest_job.img_size[0] == im_width and ingest_job.img_size[ 1] == im_height and ingest_job.datatype == im_datatype except AssertionError: ingest_job.send_msg('Mismatch between image file and input parameters. Determined image width: {}, height: {}, datatype: {}'.format( im_width, im_height, im_datatype)) raise ValueError('Image attributes do not match arguments') # create or get the boss resources for the data get_only = not ingest_job.create_resources boss_res_params = BossResParams(ingest_job) boss_res_params.get_resources(get_only=get_only) # we just create the resources, don't do anything else if ingest_job.create_resources: ingest_job.send_msg('{} Resources set up. Collection: {}, Experiment: {}, Channel: {}'.format( get_formatted_datetime(), ingest_job.coll_name, ingest_job.exp_name, ingest_job.ch_name)) return 0 else: ingest_job.send_msg('{} Starting ingest for Collection: {}, Experiment: {}, Channel: {}, Z: {z[0]},{z[1]}'.format( get_formatted_datetime(), ingest_job.coll_name, ingest_job.exp_name, ingest_job.ch_name, z=ingest_job.z_range)) # we begin the ingest here: stride_x = 1024 stride_y = 1024 stride_z = 16 x_buckets = get_supercube_lims(ingest_job.x_extent, stride_x) y_buckets = get_supercube_lims(ingest_job.y_extent, stride_y) z_buckets = get_supercube_lims(ingest_job.z_range, stride_z) with ThreadPool(threads) as pool: # load images files in stacks of 16 at a time into numpy array for _, z_slices in z_buckets.items(): # read images into numpy array im_array = ingest_job.read_img_stack(z_slices) z_rng = [z_slices[0] - ingest_job.offsets[2], z_slices[-1] + 1 - ingest_job.offsets[2]] # slice into np array blocks for _, y_slices in y_buckets.items(): y_rng = [y_slices[0], y_slices[-1] + 1] ingest_block_partial = partial( ingest_block, x_buckets=x_buckets, boss_res_params=boss_res_params, ingest_job=ingest_job, y_rng=y_rng, z_rng=z_rng, im_array=im_array) pool.map(ingest_block_partial, x_buckets.keys()) # checking data posted correctly for an entire z slice assert_equal(boss_res_params, ingest_job, ingest_job.z_range) ch_link = ( 'https://ndwebtools.neurodata.io/channel_detail/{}/{}/{}/').format(ingest_job.coll_name, ingest_job.exp_name, ingest_job.ch_name) ingest_job.send_msg('{} Finished z slices {} for Collection: {}, Experiment: {}, Channel: {}\nThere were {} read failures and {} POST failures.\nView properties of channel and start downsample job on ndwebtools: {}'.format( get_formatted_datetime(), ingest_job.z_range, ingest_job.coll_name, ingest_job.exp_name, ingest_job.ch_name, ingest_job.num_READ_failures, ingest_job.num_POST_failures, ch_link), send_slack=True) return 0