parser.add_argument("--cutoff", type=int, default=10, help="Length of displayed rankings.") parser.add_argument("--ranker_pair", type=int, default=0, help="Ranker pair to put in comparison.") args = parser.parse_args() click_model = args.click_model binarize_labels = 'binarized' in click_model eta = args.eta cutoff = args.cutoff data = dataset.get_dataset_from_json_info( args.dataset, args.dataset_info_path, ) fold_id = (args.fold_id-1)%data.num_folds() data = data.get_data_folds()[fold_id] start = time.time() data.read_data() print('Time past for reading data: %d seconds' % (time.time() - start)) pretrain_models = prtr.read_many_models(args.model_file, data) n_models = pretrain_models.shape[0] # chosen_models = np.random.choice(n_models, size=2, replace=False) chosen_models = np.array([(args.ranker_pair-1)*2, (args.ranker_pair-1)*2+1])
help="Name of dataset to sample from.") parser.add_argument("--dataset_info_path", type=str, default="local_dataset_info.txt", help="Path to dataset info file.") parser.add_argument("--cutoff", type=int, help="Maximum number of items that can be displayed.", default=5) args = parser.parse_args() click_model_name = args.click_model cutoff = args.cutoff data = dataset.get_dataset_from_json_info( args.dataset, args.dataset_info_path, shared_resource = False, ) fold_id = (args.fold_id-1)%data.num_folds() data = data.get_data_folds()[fold_id] start = time.time() data.read_data() print('Time past for reading data: %d seconds' % (time.time() - start)) max_ranking_size = np.min((cutoff, data.max_query_size())) click_model = clk.get_click_model(click_model_name) alpha, beta = click_model(np.arange(max_ranking_size))