run_popular_expid.py

# =========================================================================
# Copyright (C) 2022. Huawei Technologies Co., Ltd. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# =========================================================================


import sys
import fuxictr_version
import logging


from fuxictr import datasets
from datetime import datetime
from fuxictr.utils import load_config, set_logger, print_to_json, print_to_list
from fuxictr.features import FeatureMap
from fuxictr.pytorch.dataloaders import RankDataLoader
from fuxictr.pytorch.torch_utils import seed_everything
from fuxictr.preprocess import FeatureProcessor, build_dataset
import src
import gc
import argparse
import os
from pathlib import Path

dataset = "demo"  # small, large

if __name__ == '__main__':
    ''' Usage: python run_popular_expid.py --config {config_dir} --expid {experiment_id} --gpu {gpu_device_id}
    '''
    parser = argparse.ArgumentParser()
    parser.add_argument('--config', type=str, default=f'./config/PopularRanker_config',
                        help='The config directory.')
    parser.add_argument('--expid', type=str, default=f'Popular_ebnerd_large_x1',
                        help='The experiment id to run.')
    parser.add_argument('--gpu', type=int, default=-1, help='The gpu index, -1 for cpu')
    args = vars(parser.parse_args())

    experiment_id = args['expid']
    params = load_config(args['config'], experiment_id)
    params['gpu'] = args['gpu']
    set_logger(params)
    logging.info("Params: " + print_to_json(params))
    seed_everything(seed=params['seed'])

    data_dir = os.path.join(params['data_root'], params['dataset_id'])
    feature_map_json = os.path.join(data_dir, "feature_map.json")
    if params["data_format"] == "csv":
        # Build feature_map and transform data
        feature_encoder = FeatureProcessor(**params)

        params["train_data"], params["valid_data"], params["test_data"] = \
            build_dataset(feature_encoder, **params)
    feature_map = FeatureMap(params['dataset_id'], data_dir)
    feature_map.load(feature_map_json, params)
    logging.info("Feature specs: " + print_to_json(feature_map.features))

    model_class = getattr(src, params['model'])
    model = model_class(feature_map, **params)

    train_gen, valid_gen = RankDataLoader(feature_map, stage='train', **params).make_iterator()

    logging.info('****** Validation evaluation ******')
    valid_result = model.evaluate(valid_gen)
    del train_gen, valid_gen
    gc.collect()

    test_result = {}
    result_filename = Path(args['config']).name.replace(".yaml", "") + '.csv'
    with open(result_filename, 'a+') as fw:
        fw.write(' {},[command] python {},[exp_id] {},[dataset_id] {},[train] {},[val] {},[test] {}\n' \
                 .format(datetime.now().strftime('%Y%m%d-%H%M%S'),
                         ' '.join(sys.argv), experiment_id, params['dataset_id'],
                         "N.A.", print_to_list(valid_result), print_to_list(test_result)))