sklearn k最近邻居问题

Issue with sklearn k nearest neighbors

我想知道是否有一种方法可以强制 sklearn NearestNeighbors 算法,以在存在重复点时考虑输入数组中点的顺序。

举例说明:

>>> from sklearn.neighbors import NearestNeighbors
>>> import numpy as np

X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1], [3, 2]])
nbrs = NearestNeighbors(n_neighbors=2, algorithm='ball_tree').fit(X)
distances, indices = nbrs.kneighbors(X)
indices                                           
>>>> array([[0, 1],
     [1, 0],
     [2, 1],
     [3, 4],
     [4, 3],
     [5, 4]])

因为查询集与训练集相匹配,所以每个点的最近邻就是点本身,距离为零。但是,如果我允许 X 中有重复点,则可以理解,该算法不会区分重复点:

X = np.array([[-1, -1], [-2, -1], [-3, -2], [1, 1], [2, 1],[3, 2],[-1,-1],[-1,-1]])
nbrs = NearestNeighbors(n_neighbors=2, algorithm='auto').fit(X)
distances, indices = nbrs.kneighbors(X)
indices 
>>>> array([[6, 0],
   [1, 0],
   [2, 1],
   [3, 4],
   [4, 3],
   [5, 4],
   [6, 0],
   [6, 0]])

理想情况下,我希望最后的输出类似于:

    >>>> array([[0, 6],
   [1, 0],
   [2, 1],
   [3, 4],
   [4, 3],
   [5, 4],
   [6, 0],
   [7, 6]])

我认为你不能那样做,因为从 ref 我们得到:

Warning: Regarding the Nearest Neighbors algorithms, if two neighbors, neighbor k+1 and k, have identical distances but different labels, the results will depend on the ordering of the training data.