data_fetch.py 文件源码

def fetch_load_isolet(data_dir=None):
    train = 'isolet1+2+3+4.data.Z'
    test = 'isolet5.data.Z'
    path_train = os.path.join(get_data_home(data_dir), train)
    path_test  = os.path.join(get_data_home(data_dir), test)

    if not os.path.exists(path_train[:-2]) or not os.path.exists(path_test[:-2]):
        from urllib import request
        url = 'https://archive.ics.uci.edu/ml/machine-learning-databases/isolet/'
        if not os.path.exists(path_train[:-2]):
            if not os.path.exists(path_train):
                print('Downloading Isolated Letter Speech Recognition data set from {}...'.format(
                    url))
                request.urlretrieve(url=url+train, filename=path_train)
            # os.system('gzip -d ' + path_train)
            decompress_z(path_train)
        if not os.path.exists(path_test[:-2]):
            if not os.path.exists(path_test):
                print('Downloading Isolated Letter Speech Recognition data set from {}...'.format(
                    url))
                request.urlretrieve(url=url+test, filename=path_test)
            # os.system('gzip -d ' + path_test)
            decompress_z(path_test)
    else:
        print('Found Isolated Letter Speech Recognition data set!')

    xtr, ytr = [], []
    with open(path_train[:-2]) as f:
        reader = csv.reader(f)
        for row in reader:
            xtr.append(row[:-1])
            ytr.append(int(float(row[-1])))
    labels, ytr = np.unique(ytr, return_inverse=True)
    xte, yte = [], []
    with open(path_test[:-2]) as f:
        reader = csv.reader(f)
        for row in reader:
            xte.append(row[:-1])
            yte.append(int(float(row[-1])))
    labels, yte = np.unique(yte, return_inverse=True)

    return np.asarray(xtr, dtype=float), np.asarray(xte, dtype=float), ytr, yte