给定一个一维下标数组:

a = array([1, 0, 3])

我想把它编码成一个2D数组:

b = array([[0,1,0,0], [1,0,0,0], [0,0,0,1]])

当前回答

以下是我认为有用的方法:

def one_hot(a, num_classes):
  return np.squeeze(np.eye(num_classes)[a.reshape(-1)])

这里num_classes表示您拥有的类的数量。如果你有一个形状为(10000,)的向量,这个函数将它转换为(10000,C)注意,a是零索引,即one_hot(np。数组([0,1]),2)将给出[[1,0],[0,1]]。

我相信这正是你想要的。

PS:源代码是Sequence models - deeplearning.ai

其他回答

def one_hot(n, class_num, col_wise=True):
  a = np.eye(class_num)[n.reshape(-1)]
  return a.T if col_wise else a

# Column for different hot
print(one_hot(np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 9, 9, 9, 9, 8, 7]), 10))
# Row for different hot
print(one_hot(np.array([0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 9, 9, 9, 9, 8, 7]), 10, col_wise=False))

我添加了一个简单的补全函数,只使用numpy操作符:

   def probs_to_onehot(output_probabilities):
        argmax_indices_array = np.argmax(output_probabilities, axis=1)
        onehot_output_array = np.eye(np.unique(argmax_indices_array).shape[0])[argmax_indices_array.reshape(-1)]
        return onehot_output_array

它以一个概率矩阵作为输入:例如:

[[0.03038822 0.65810204 0.16549407 0.3797123] . [0.02771272 0.2760752 0.3280924 0.33458805]

它会返回

[[0 0 0 0]... [0 0 0 1]

下面是我根据上面的答案和我自己的用例写的一个示例函数:

def label_vector_to_one_hot_vector(vector, one_hot_size=10):
    """
    Use to convert a column vector to a 'one-hot' matrix

    Example:
        vector: [[2], [0], [1]]
        one_hot_size: 3
        returns:
            [[ 0.,  0.,  1.],
             [ 1.,  0.,  0.],
             [ 0.,  1.,  0.]]

    Parameters:
        vector (np.array): of size (n, 1) to be converted
        one_hot_size (int) optional: size of 'one-hot' row vector

    Returns:
        np.array size (vector.size, one_hot_size): converted to a 'one-hot' matrix
    """
    squeezed_vector = np.squeeze(vector, axis=-1)

    one_hot = np.zeros((squeezed_vector.size, one_hot_size))

    one_hot[np.arange(squeezed_vector.size), squeezed_vector] = 1

    return one_hot

label_vector_to_one_hot_vector(vector=[[2], [0], [1]], one_hot_size=3)

为了详细说明K3—rnc的优秀答案,这里有一个更通用的版本:

def onehottify(x, n=None, dtype=float):
    """1-hot encode x with the max value n (computed from data if n is None)."""
    x = np.asarray(x)
    n = np.max(x) + 1 if n is None else n
    return np.eye(n, dtype=dtype)[x]

此外,这里是这个方法的快速和粗略的基准测试,以及YXD目前接受的答案(略有更改,以便他们提供相同的API,除了后者只适用于1D ndarray):

def onehottify_only_1d(x, n=None, dtype=float):
    x = np.asarray(x)
    n = np.max(x) + 1 if n is None else n
    b = np.zeros((len(x), n), dtype=dtype)
    b[np.arange(len(x)), x] = 1
    return b

后一种方法快35% (MacBook Pro 13 2015),但前一种更通用:

>>> import numpy as np
>>> np.random.seed(42)
>>> a = np.random.randint(0, 9, size=(10_000,))
>>> a
array([6, 3, 7, ..., 5, 8, 6])
>>> %timeit onehottify(a, 10)
188 µs ± 5.03 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)
>>> %timeit onehottify_only_1d(a, 10)
139 µs ± 2.78 µs per loop (mean ± std. dev. of 7 runs, 10000 loops each)

你也可以使用numpy的eye函数:

numpy。眼(类数)[包含标签的向量]