util.py 文件源码

def get_normalized_data():
    print "Reading in and transforming data..."
    df = pd.read_csv('../large_files/train.csv')
    data = df.as_matrix().astype(np.float32)
    np.random.shuffle(data)
    X = data[:, 1:]
    mu = X.mean(axis=0)
    std = X.std(axis=0)
    np.place(std, std == 0, 1)
    X = (X - mu) / std # normalize the data
    Y = data[:, 0]
    return X, Y