对于多维数组，可以使用axis关键字，以便沿着预期的轴应用分区。

# For a 2D array
indices = np.argpartition(arr, -N, axis=1)[:, -N:]

对于抓取物品:

x = arr.shape[0]
arr[np.repeat(np.arange(x), N), indices.ravel()].reshape(x, N)

但请注意，这不会返回一个排序的结果。在这种情况下，你可以沿着预期的轴使用np.argsort():

indices = np.argsort(arr, axis=1)[:, -N:]

# Result
x = arr.shape[0]
arr[np.repeat(np.arange(x), N), indices.ravel()].reshape(x, N)

这里有一个例子:

In [42]: a = np.random.randint(0, 20, (10, 10))

In [44]: a
Out[44]:
array([[ 7, 11, 12,  0,  2,  3,  4, 10,  6, 10],
       [16, 16,  4,  3, 18,  5, 10,  4, 14,  9],
       [ 2,  9, 15, 12, 18,  3, 13, 11,  5, 10],
       [14,  0,  9, 11,  1,  4,  9, 19, 18, 12],
       [ 0, 10,  5, 15,  9, 18,  5,  2, 16, 19],
       [14, 19,  3, 11, 13, 11, 13, 11,  1, 14],
       [ 7, 15, 18,  6,  5, 13,  1,  7,  9, 19],
       [11, 17, 11, 16, 14,  3, 16,  1, 12, 19],
       [ 2,  4, 14,  8,  6,  9, 14,  9,  1,  5],
       [ 1, 10, 15,  0,  1,  9, 18,  2,  2, 12]])

In [45]: np.argpartition(a, np.argmin(a, axis=0))[:, 1:] # 1 is because the first item is the minimum one.
Out[45]:
array([[4, 5, 6, 8, 0, 7, 9, 1, 2],
       [2, 7, 5, 9, 6, 8, 1, 0, 4],
       [5, 8, 1, 9, 7, 3, 6, 2, 4],
       [4, 5, 2, 6, 3, 9, 0, 8, 7],
       [7, 2, 6, 4, 1, 3, 8, 5, 9],
       [2, 3, 5, 7, 6, 4, 0, 9, 1],
       [4, 3, 0, 7, 8, 5, 1, 2, 9],
       [5, 2, 0, 8, 4, 6, 3, 1, 9],
       [0, 1, 9, 4, 3, 7, 5, 2, 6],
       [0, 4, 7, 8, 5, 1, 9, 2, 6]])

In [46]: np.argpartition(a, np.argmin(a, axis=0))[:, -3:]
Out[46]:
array([[9, 1, 2],
       [1, 0, 4],
       [6, 2, 4],
       [0, 8, 7],
       [8, 5, 9],
       [0, 9, 1],
       [1, 2, 9],
       [3, 1, 9],
       [5, 2, 6],
       [9, 2, 6]])

In [89]: a[np.repeat(np.arange(x), 3), ind.ravel()].reshape(x, 3)
Out[89]:
array([[10, 11, 12],
       [16, 16, 18],
       [13, 15, 18],
       [14, 18, 19],
       [16, 18, 19],
       [14, 14, 19],
       [15, 18, 19],
       [16, 17, 19],
       [ 9, 14, 14],
       [12, 15, 18]])

我发现最直观的方法是使用np.unique。

其思想是，唯一方法返回输入值的索引。然后根据最大唯一值和索引，重新创建原始值的位置。

multi_max = [1,1,2,2,4,0,0,4]
uniques, idx = np.unique(multi_max, return_inverse=True)
print np.squeeze(np.argwhere(idx == np.argmax(uniques)))
>> [4 7]

比较了编码的便捷性和速度

速度对我的需求很重要，所以我测试了这个问题的三个答案。

根据我的具体情况，对这三个答案中的代码进行了修改。

然后我比较了每种方法的速度。

编码智慧:

NPE的回答是最优雅的，也足够快地满足我的需求。 Fred foo的回答需要最多的重构来满足我的需求，但却是最快的。我选择了这个答案，因为尽管它需要更多的工作，但它并不太糟糕，并且具有显著的速度优势。 Off99555的回答是最优雅的，但也是最慢的。

测试和比较的完整代码

import numpy as np
import time
import random
import sys
from operator import itemgetter
from heapq import nlargest

''' Fake Data Setup '''
a1 = list(range(1000000))
random.shuffle(a1)
a1 = np.array(a1)

''' ################################################ '''
''' NPE's Answer Modified A Bit For My Case '''
t0 = time.time()
indices = np.flip(np.argsort(a1))[:5]
results = []
for index in indices:
    results.append((index, a1[index]))
t1 = time.time()
print("NPE's Answer:")
print(results)
print(t1 - t0)
print()

''' Fred Foos Answer Modified A Bit For My Case'''
t0 = time.time()
indices = np.argpartition(a1, -6)[-5:]
results = []
for index in indices:
    results.append((a1[index], index))
results.sort(reverse=True)
results = [(b, a) for a, b in results]
t1 = time.time()
print("Fred Foo's Answer:")
print(results)
print(t1 - t0)
print()

''' off99555's Answer - No Modification Needed For My Needs '''
t0 = time.time()
result = nlargest(5, enumerate(a1), itemgetter(1))
t1 = time.time()
print("off99555's Answer:")
print(result)
print(t1 - t0)

输出速度报告

肺水肿的回答是:

[(631934, 999999), (788104, 999998), (413003, 999997), (536514, 999996), (81029, 999995)]
0.1349949836730957

Fred Foo的回答:

[(631934, 999999), (788104, 999998), (413003, 999997), (536514, 999996), (81029, 999995)]
0.011161565780639648

off99555的回答是:

[(631934, 999999), (788104, 999998), (413003, 999997), (536514, 999996), (81029, 999995)]
0.439760684967041

较新的NumPy版本(1.8及以上)有一个名为argpartition的函数。要得到四个最大元素的索引，请执行以下操作

>>> a = np.array([9, 4, 4, 3, 3, 9, 0, 4, 6, 0])
>>> a
array([9, 4, 4, 3, 3, 9, 0, 4, 6, 0])

>>> ind = np.argpartition(a, -4)[-4:]
>>> ind
array([1, 5, 8, 0])

>>> top4 = a[ind]
>>> top4
array([4, 9, 6, 9])

与argsort不同，这个函数在最坏的情况下以线性时间运行，但返回的索引没有排序，这可以从求值a[ind]的结果中看出。如果你也需要，那就把它们分类:

>>> ind[np.argsort(a[ind])]
array([1, 8, 5, 0])

以这种方式获得排在前k位的元素需要O(n + k log k)时间。

您可以简单地使用字典来查找numpy数组中的前k个值和下标。 例如，如果你想找到前2个最大值和索引

import numpy as np
nums = np.array([0.2, 0.3, 0.25, 0.15, 0.1])


def TopK(x, k):
    a = dict([(i, j) for i, j in enumerate(x)])
    sorted_a = dict(sorted(a.items(), key = lambda kv:kv[1], reverse=True))
    indices = list(sorted_a.keys())[:k]
    values = list(sorted_a.values())[:k]
    return (indices, values)

print(f"Indices: {TopK(nums, k = 2)[0]}")
print(f"Values: {TopK(nums, k = 2)[1]}")


Indices: [1, 2]
Values: [0.3, 0.25]

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)