class kddNShot: def __init__(self, path, batch_size): self.data_generator = Data(path, batch_size) self.norm_adj = self.data_generator.get_adj_mat() def next(self): return self.data_generator.sample() def get_test(self): return self.data_generator.sample('test')
data_generator = Data(path=args.data_path + args.dataset, batch_size=args.batch_size) USR_NUM, ITEM_NUM = data_generator.n_users, data_generator.n_items N_TRAIN, N_TEST = data_generator.n_train, data_generator.n_test BATCH_SIZE = args.batch_size config = dict() config['n_users'] = data_generator.n_users config['n_items'] = data_generator.n_items print(data_generator.train_items[1]) """ ********************************************************* Generate the Laplacian matrix, where each entry defines the decay factor (e.g., p_ui) between two connected nodes. """ plain_adj, norm_adj, mean_adj, pre_adj = data_generator.get_adj_mat() print("plain_adj") print(plain_adj) print("norm_adj") print(norm_adj) print("mean_adj") print(mean_adj) print("pre_adj") print(pre_adj) if args.adj_type == 'plain': config['norm_adj'] = plain_adj print('use the plain adjacency matrix') elif args.adj_type == 'norm': config['norm_adj'] = norm_adj print('use the normalized adjacency matrix') elif args.adj_type == 'gcmc':