示例#1
0
文件: run_tgen.py 项目: UFAL-DSG/tgen
def percrank_train(args):
    opts, files = getopt(args, 'c:d:s:j:w:e:r:')
    candgen_model = None
    train_size = 1.0
    parallel = False
    jobs_number = 0
    work_dir = None
    experiment_id = None

    for opt, arg in opts:
        if opt == '-d':
            set_debug_stream(file_stream(arg, mode='w'))
        elif opt == '-s':
            train_size = float(arg)
        elif opt == '-c':
            candgen_model = arg
        elif opt == '-j':
            parallel = True
            jobs_number = int(arg)
        elif opt == '-w':
            work_dir = arg
        elif opt == '-e':
            experiment_id = arg
        elif opt == '-r' and arg:
            rnd.seed(arg)

    if len(files) != 4:
        sys.exit(__doc__)

    fname_rank_config, fname_train_das, fname_train_ttrees, fname_rank_model = files
    log_info('Training perceptron ranker...')

    rank_config = Config(fname_rank_config)
    if candgen_model:
        rank_config['candgen_model'] = candgen_model
    if rank_config.get('nn'):
        from tgen.rank_nn import SimpleNNRanker, EmbNNRanker
        if rank_config['nn'] in ['emb', 'emb_trees', 'emb_prev']:
            ranker_class = EmbNNRanker
        else:
            ranker_class = SimpleNNRanker
    else:
        ranker_class = PerceptronRanker

    log_info('Using %s for ranking' % ranker_class.__name__)

    if not parallel:
        ranker = ranker_class(rank_config)
    else:
        rank_config['jobs_number'] = jobs_number
        if work_dir is None:
            work_dir, _ = os.path.split(fname_rank_config)
        ranker = ParallelRanker(rank_config, work_dir, experiment_id, ranker_class)

    ranker.train(fname_train_das, fname_train_ttrees, data_portion=train_size)

    # avoid the "maximum recursion depth exceeded" error
    sys.setrecursionlimit(100000)
    ranker.save_to_file(fname_rank_model)
示例#2
0
文件: run_tgen.py 项目: fooyou/tgen
def percrank_train(args):
    opts, files = getopt(args, 'c:d:s:j:w:e:')
    candgen_model = None
    train_size = 1.0
    parallel = False
    jobs_number = 0
    work_dir = None
    experiment_id = None

    for opt, arg in opts:
        if opt == '-d':
            set_debug_stream(file_stream(arg, mode='w'))
        elif opt == '-s':
            train_size = float(arg)
        elif opt == '-c':
            candgen_model = arg
        elif opt == '-j':
            parallel = True
            jobs_number = int(arg)
        elif opt == '-w':
            work_dir = arg
        elif opt == '-e':
            experiment_id = arg

    if len(files) != 4:
        sys.exit(__doc__)

    fname_rank_config, fname_train_das, fname_train_ttrees, fname_rank_model = files
    log_info('Training perceptron ranker...')

    rank_config = Config(fname_rank_config)
    if candgen_model:
        rank_config['candgen_model'] = candgen_model
    if rank_config.get('nn'):
        if rank_config['nn'] == 'emb':
            ranker_class = EmbNNRanker
        else:
            ranker_class = SimpleNNRanker
    else:
        ranker_class = PerceptronRanker
    if not parallel:
        ranker = ranker_class(rank_config)
    else:
        rank_config['jobs_number'] = jobs_number
        if work_dir is None:
            work_dir, _ = os.path.split(fname_rank_config)
        ranker = ParallelRanker(rank_config, work_dir, experiment_id, ranker_class)
    ranker.train(fname_train_das, fname_train_ttrees, data_portion=train_size)
    ranker.save_to_file(fname_rank_model)
示例#3
0
def percrank_train(args):
    opts, files = getopt(args, 'c:d:s:j:w:e:r:')
    candgen_model = None
    train_size = 1.0
    parallel = False
    jobs_number = 0
    work_dir = None
    experiment_id = None

    for opt, arg in opts:
        if opt == '-d':
            set_debug_stream(file_stream(arg, mode='w'))
        elif opt == '-s':
            train_size = float(arg)
        elif opt == '-c':
            candgen_model = arg
        elif opt == '-j':
            parallel = True
            jobs_number = int(arg)
        elif opt == '-w':
            work_dir = arg
        elif opt == '-e':
            experiment_id = arg
        elif opt == '-r' and arg:
            rnd.seed(arg)

    if len(files) != 4:
        sys.exit(__doc__)

    fname_rank_config, fname_train_das, fname_train_ttrees, fname_rank_model = files
    log_info('Training perceptron ranker...')

    rank_config = Config(fname_rank_config)
    if candgen_model:
        rank_config['candgen_model'] = candgen_model
    if rank_config.get('nn'):
        from tgen.rank_nn import SimpleNNRanker, EmbNNRanker
        if rank_config['nn'] in ['emb', 'emb_trees', 'emb_prev']:
            ranker_class = EmbNNRanker
        else:
            ranker_class = SimpleNNRanker
    else:
        ranker_class = PerceptronRanker

    log_info('Using %s for ranking' % ranker_class.__name__)

    if not parallel:
        ranker = ranker_class(rank_config)
    else:
        rank_config['jobs_number'] = jobs_number
        if work_dir is None:
            work_dir, _ = os.path.split(fname_rank_config)
        ranker = ParallelRanker(rank_config, work_dir, experiment_id,
                                ranker_class)

    ranker.train(fname_train_das, fname_train_ttrees, data_portion=train_size)

    # avoid the "maximum recursion depth exceeded" error
    sys.setrecursionlimit(100000)
    ranker.save_to_file(fname_rank_model)