extract_features.py

r'''
  ____   ____    _    ____  _____                          _      _
 |  _ \ / ___|  / \  / ___|| ____|     _ __ ___   ___   __| | ___| |___
 | | | | |     / _ \ \___ \|  _| _____| '_ ` _ \ / _ \ / _` |/ _ \ / __|
 | |_| | |___ / ___ \ ___) | |__|_____| | | | | | (_) | (_| |  __/ \__ \\
 |____/ \____/_/   \_\____/|_____|    |_| |_| |_|\___/ \__,_|\___|_|___/

 Feature extraction example

'''

import os
import argparse

from dcase_models.data.datasets import get_available_datasets
from dcase_models.data.features import get_available_features
from dcase_models.util.files import load_json


def main():
    # Parse arguments
    parser = argparse.ArgumentParser(
        description=__doc__,
        formatter_class=argparse.RawDescriptionHelpFormatter
    )
    parser.add_argument(
        '-d', '--dataset', type=str,
        help='dataset name (e.g. UrbanSound8k, ESC50, URBAN_SED, SONYC_UST)',
        default='UrbanSound8k'
    )
    parser.add_argument(
        '-f', '--features', type=str,
        help='features name (e.g. Spectrogram, MelSpectrogram, Openl3)',
        default='MelSpectrogram'
    )
    parser.add_argument(
        '-p', '--path', type=str,
        help='path to the parameters.json file',
        default='../'
    )
    args = parser.parse_args()

    print(__doc__)

    if args.dataset not in get_available_datasets():
        raise AttributeError('Dataset not available')

    if args.features not in get_available_features():
        raise AttributeError('Features not available')

    # Get parameters
    parameters_file = os.path.join(args.path, 'parameters.json')
    params = load_json(parameters_file)
    params_dataset = params['datasets'][args.dataset]
    params_features = params['features']

    # Get and init dataset class
    dataset_class = get_available_datasets()[args.dataset]
    dataset_path = os.path.join(args.path, params_dataset['dataset_path'])
    dataset = dataset_class(dataset_path)

    # Get and init feature class
    features_class = get_available_features()[args.features]
    features = features_class(
        sequence_time=params_features['sequence_time'],
        sequence_hop_time=params_features['sequence_hop_time'],
        audio_win=params_features['audio_win'],
        audio_hop=params_features['audio_hop'],
        sr=params_features['sr'], **params_features[args.features]
    )

    # Extract features
    if features.check_if_extracted(dataset):
        print('%s features were already extracted for %s dataset. ' % (
            args.features, args.dataset))
    else:
        print('Extracting features ...')
        features.extract(dataset)

    print('Done!')


if __name__ == "__main__":
    main()