doctorAI.py 文件源码

def parse_arguments(parser):
    parser.add_argument('seq_file', type=str, metavar='<visit_file>', help='The path to the Pickled file containing visit information of patients')
    parser.add_argument('n_input_codes', type=int, metavar='<n_input_codes>', help='The number of unique input medical codes')
    parser.add_argument('label_file', type=str, metavar='<label_file>', help='The path to the Pickled file containing label information of patients')
    parser.add_argument('n_output_codes', type=int, metavar='<n_output_codes>', help='The number of unique label medical codes')
    parser.add_argument('out_file', metavar='out_file', help='The path to the output models. The models will be saved after every epoch')
    parser.add_argument('--time_file', type=str, default='', help='The path to the Pickled file containing durations between visits of patients. If you are not using duration information, do not use this option')
    parser.add_argument('--predict_time', type=int, default=0, choices=[0,1], help='Use this option if you want the GRU to also predict the time duration until the next visit (0 for false, 1 for true) (default value: 0)')
    parser.add_argument('--tradeoff', type=float, default=1.0, help='Tradeoff variable for balancing the two loss functions: code prediction function and duration prediction function (default value: 1.0)')
    parser.add_argument('--use_log_time', type=int, default=1, choices=[0,1], help='Use logarithm of time duration to dampen the impact of the outliers (0 for false, 1 for true) (default value: 1)')
    parser.add_argument('--embed_file', type=str, default='', help='The path to the Pickled file containing the representation vectors of medical codes. If you are not using medical code representations, do not use this option')
    parser.add_argument('--embed_size', type=int, default=200, help='The size of the visit embedding before passing it to the GRU layers. If you are not providing your own medical code vectors, you must specify this value (default value: 200)')
    parser.add_argument('--embed_finetune', type=int, default=1, choices=[0,1], help='If you are using randomly initialized code representations, always use this option. If you are using an external medical code representations, and you want to fine-tune them as you train the GRU, use this option as well. (0 for false, 1 for true) (default value: 1)')
    parser.add_argument('--hidden_dim_size', type=str, default='[200,200]', help='The size of the hidden layers of the GRU. This is a string argument. For example, [500,400] means you are using a two-layer GRU where the lower layer uses a 500-dimensional hidden layer, and the upper layer uses a 400-dimensional hidden layer. (default value: [200,200])')
    parser.add_argument('--batch_size', type=int, default=100, help='The size of a single mini-batch (default value: 100)')
    parser.add_argument('--n_epochs', type=int, default=10, help='The number of training epochs (default value: 10)')
    parser.add_argument('--L2_softmax', type=float, default=0.001, help='L2 regularization for the softmax function (default value: 0.001)')
    parser.add_argument('--L2_time', type=float, default=0.001, help='L2 regularization for the linear regression (default value: 0.001)')
    parser.add_argument('--dropout_rate', type=float, default=0.5, help='Dropout rate between GRU hidden layers, and between the final hidden layer and the softmax layer (default value: 0.5)')
    parser.add_argument('--log_eps', type=float, default=1e-8, help='A small value to prevent log(0) (default value: 1e-8)')
    parser.add_argument('--verbose', action='store_true', help='Print output after every 10 mini-batches (default false)')
    args = parser.parse_args()
    return args