Use:

def max_indices(arr, k):
    '''
    Returns the indices of the k first largest elements of arr
    (in descending order in values)
    '''
    assert k <= arr.size, 'k should be smaller or equal to the array size'
    arr_ = arr.astype(float)  # make a copy of arr
    max_idxs = []
    for _ in range(k):
        max_element = np.max(arr_)
        if np.isinf(max_element):
            break
        else:
            idx = np.where(arr_ == max_element)
        max_idxs.append(idx)
        arr_[idx] = -np.inf
    return max_idxs

它也适用于2D数组。例如,

In [0]: A = np.array([[ 0.51845014,  0.72528114],
                     [ 0.88421561,  0.18798661],
                     [ 0.89832036,  0.19448609],
                     [ 0.89832036,  0.19448609]])
In [1]: max_indices(A, 8)
Out[1]:
    [(array([2, 3], dtype=int64), array([0, 0], dtype=int64)),
     (array([1], dtype=int64), array([0], dtype=int64)),
     (array([0], dtype=int64), array([1], dtype=int64)),
     (array([0], dtype=int64), array([0], dtype=int64)),
     (array([2, 3], dtype=int64), array([1, 1], dtype=int64)),
     (array([1], dtype=int64), array([1], dtype=int64))]

In [2]: A[max_indices(A, 8)[0]][0]
Out[2]: array([ 0.89832036])

Use:

from operator import itemgetter
from heapq import nlargest
result = nlargest(N, enumerate(your_list), itemgetter(1))

现在，结果列表将包含N个元组(index, value)，其中value是最大的。

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

使用argpartition的向量化2D实现:

k = 3
probas = np.array([
    [.6, .1, .15, .15],
    [.1, .6, .15, .15],
    [.3, .1, .6, 0],
])

k_indices = np.argpartition(-probas, k-1, axis=-1)[:, :k]

# adjust indices to apply in flat array
adjuster = np.arange(probas.shape[0]) * probas.shape[1]
adjuster = np.broadcast_to(adjuster[:, None], k_indices.shape)
k_indices_flat = k_indices + adjuster

k_values = probas.flatten()[k_indices_flat]

# k_indices:
# array([[0, 2, 3],
#        [1, 2, 3],
#        [2, 0, 1]])
# k_values:
# array([[0.6 , 0.15, 0.15],
#        [0.6 , 0.15, 0.15],
#       [0.6 , 0.3 , 0.1 ]])

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。