当top_k<<axis_length时，它优于argsort。

import numpy as np

def get_sorted_top_k(array, top_k=1, axis=-1, reverse=False):
    if reverse:
        axis_length = array.shape[axis]
        partition_index = np.take(np.argpartition(array, kth=-top_k, axis=axis),
                                  range(axis_length - top_k, axis_length), axis)
    else:
        partition_index = np.take(np.argpartition(array, kth=top_k, axis=axis), range(0, top_k), axis)
    top_scores = np.take_along_axis(array, partition_index, axis)
    # resort partition
    sorted_index = np.argsort(top_scores, axis=axis)
    if reverse:
        sorted_index = np.flip(sorted_index, axis=axis)
    top_sorted_scores = np.take_along_axis(top_scores, sorted_index, axis)
    top_sorted_indexes = np.take_along_axis(partition_index, sorted_index, axis)
    return top_sorted_scores, top_sorted_indexes

if __name__ == "__main__":
    import time
    from sklearn.metrics.pairwise import cosine_similarity

    x = np.random.rand(10, 128)
    y = np.random.rand(1000000, 128)
    z = cosine_similarity(x, y)
    start_time = time.time()
    sorted_index_1 = get_sorted_top_k(z, top_k=3, axis=1, reverse=True)[1]
    print(time.time() - start_time)

我能想到的最简单的是:

>>> import numpy as np
>>> arr = np.array([1, 3, 2, 4, 5])
>>> arr.argsort()[-3:][::-1]
array([4, 3, 1])

这涉及到一个完整的数组。我想知道numpy是否提供了一种内置的方法来进行部分排序;到目前为止我还没有找到。

如果这个解决方案太慢(特别是对于小n)，那么可能值得考虑用Cython编写一些东西。

这段代码适用于numpy 2D矩阵数组:

mat = np.array([[1, 3], [2, 5]]) # numpy matrix
 
n = 2  # n
n_largest_mat = np.sort(mat, axis=None)[-n:] # n_largest 
tf_n_largest = np.zeros((2,2), dtype=bool) # all false matrix
for x in n_largest_mat: 
  tf_n_largest = (tf_n_largest) | (mat == x) # true-false  

n_largest_elems = mat[tf_n_largest] # true-false indexing 

这将产生一个true-false的n_maximum矩阵索引，也可以从矩阵数组中提取n_maximum元素

如果你碰巧在使用一个多维数组，那么你需要平展和解开索引:

def largest_indices(ary, n):
    """Returns the n largest indices from a numpy array."""
    flat = ary.flatten()
    indices = np.argpartition(flat, -n)[-n:]
    indices = indices[np.argsort(-flat[indices])]
    return np.unravel_index(indices, ary.shape)

例如:

>>> xs = np.sin(np.arange(9)).reshape((3, 3))
>>> xs
array([[ 0.        ,  0.84147098,  0.90929743],
       [ 0.14112001, -0.7568025 , -0.95892427],
       [-0.2794155 ,  0.6569866 ,  0.98935825]])
>>> largest_indices(xs, 3)
(array([2, 0, 0]), array([2, 2, 1]))
>>> xs[largest_indices(xs, 3)]
array([ 0.98935825,  0.90929743,  0.84147098])

当top_k<<axis_length时，它优于argsort。

import numpy as np

def get_sorted_top_k(array, top_k=1, axis=-1, reverse=False):
    if reverse:
        axis_length = array.shape[axis]
        partition_index = np.take(np.argpartition(array, kth=-top_k, axis=axis),
                                  range(axis_length - top_k, axis_length), axis)
    else:
        partition_index = np.take(np.argpartition(array, kth=top_k, axis=axis), range(0, top_k), axis)
    top_scores = np.take_along_axis(array, partition_index, axis)
    # resort partition
    sorted_index = np.argsort(top_scores, axis=axis)
    if reverse:
        sorted_index = np.flip(sorted_index, axis=axis)
    top_sorted_scores = np.take_along_axis(top_scores, sorted_index, axis)
    top_sorted_indexes = np.take_along_axis(partition_index, sorted_index, axis)
    return top_sorted_scores, top_sorted_indexes

if __name__ == "__main__":
    import time
    from sklearn.metrics.pairwise import cosine_similarity

    x = np.random.rand(10, 128)
    y = np.random.rand(1000000, 128)
    z = cosine_similarity(x, y)
    start_time = time.time()
    sorted_index_1 = get_sorted_top_k(z, top_k=3, axis=1, reverse=True)[1]
    print(time.time() - start_time)

我认为最省时的方法是手动遍历数组并保持k-size的min-heap，正如其他人所提到的那样。

我还想出了一个蛮力方法:

top_k_index_list = [ ]
for i in range(k):
    top_k_index_list.append(np.argmax(my_array))
    my_array[top_k_index_list[-1]] = -float('inf')

在使用argmax获取其索引后，将最大的元素设置为一个较大的负值。然后argmax的下一次调用将返回第二大的元素。 您可以记录这些元素的原始值，并在需要时恢复它们。