checkerboard.py 文件源码

def generate_data(sample_size=200, pd=[[0.4, 0.4], [0.1, 0.1]]):
    pd = np.array(pd)
    pd /= pd.sum()
    offset = 50
    bins = np.r_[np.zeros((1,)), np.cumsum(pd)]
    bin_counts = np.histogram(np.random.rand(sample_size), bins)[0]
    data = np.empty((0, 2))
    targets = []
    for ((i, j), p), count in zip(np.ndenumerate(pd), bin_counts):
        xs = np.random.uniform(low=0.0, high=50.0, size=count) + j * offset
        ys = np.random.uniform(low=0.0, high=50.0, size=count) + -i * offset
        data = np.vstack((data, np.c_[xs, ys]))
        if i == j:
            targets.extend([1] * count)
        else:
            targets.extend([-1] * count)
    return np.c_[data, targets]