def generate_humavips_dataset( glob_file_pattern="/mnt/protolab_server/media/sounds/datasets/NAR_dataset/*/*.wav" ): dict_with_features = _generate_humavips_dataset( glob_file_pattern=glob_file_pattern) df = pd.DataFrame(dict_with_features) df['features'] = df['features'].apply(lambda x: _flatten_features_dict(x)) return df
def generate_8k_dataset(glob_file_pattern='/mnt/protolab_server_8k/fold*/*.wav', nfft=1024, downsampling_freq=None): dict_with_features = _generate_8k_dataset_dict(glob_file_pattern=glob_file_pattern, nfft=nfft) df = pd.DataFrame(dict_with_features) df['fold'] = df['file_path'].apply(lambda x: int(os.path.basename(x)[4:])) # string = foldXY , so we take string[4: df['features'] = df['features'].apply(lambda x : _flatten_features_dict(x)) df['expected_class'] = df['file_name'].apply(lambda x: _add_class_from_filename_8kdataset(x)) return df
def generate_aldebaran_dataset(files, nfft=1024, window_block=None): dict_with_features = _generate_aldebaran_dataset(files, window_block=window_block) df = pd.DataFrame(dict_with_features) df['features'] = df['features'].apply(lambda x : _flatten_features_dict(x)) return df
def generate_humavips_dataset(glob_file_pattern="/mnt/protolab_server/media/sounds/datasets/NAR_dataset/*/*.wav"): dict_with_features = _generate_humavips_dataset(glob_file_pattern=glob_file_pattern) df = pd.DataFrame(dict_with_features) df['features'] = df['features'].apply(lambda x : _flatten_features_dict(x)) return df
def generate_aldebaran_dataset(files, nfft=1024, window_block=None): dict_with_features = _generate_aldebaran_dataset(files, window_block=window_block) df = pd.DataFrame(dict_with_features) df['features'] = df['features'].apply(lambda x: _flatten_features_dict(x)) return df