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

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)

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

Use:

>>> import heapq
>>> import numpy
>>> a = numpy.array([1, 3, 2, 4, 5])
>>> heapq.nlargest(3, range(len(a)), a.take)
[4, 3, 1]

对于常规的Python列表:

>>> a = [1, 3, 2, 4, 5]
>>> heapq.nlargest(3, range(len(a)), a.__getitem__)
[4, 3, 1]

如果使用Python 2，请使用xrange而不是range。

来源:堆队列算法

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