data_fetch.py 文件源码

def fetch_load_letters(data_dir=None):
    path = os.path.join(get_data_home(data_dir), 'letter-recognition.data')

    if not os.path.exists(path):
        from urllib import request
        url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/letter-recognition/letter-recognition.data'
        print('Downloading letter-recognition dataset from {}...'.format(url))
        request.urlretrieve(url=url, filename=path)
    else:
        print('Found letter-recognition in {}!'.format(path))

    X, y = [], []
    with open(path) as f:
        reader = csv.reader(f)
        for row in reader:
            y.append(row[0])
            X.append(row[1:])
    labels, label_idx = np.unique(y, return_inverse=True)
    return np.asarray(X, dtype=float), label_idx