Sklearn实现最近邻算法(KNN)

>>> 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]]...)
>>> distances
array([[0.        , 1.        ],
       [0.        , 1.        ],
       [0.        , 1.41421356],
       [0.        , 1.        ],
       [0.        , 1.        ],
       [0.        , 1.41421356]])Copy
因为查询集匹配训练集，每个点的最近邻点是其自身，距离为0。

还可以有效地生成一个稀疏图来标识相连点之间的连接情况：

>>> nbrs.kneighbors_graph(X).toarray()
array([[ 1.,  1.,  0.,  0.,  0.,  0.],
 [ 1.,  1.,  0.,  0.,  0.,  0.],
 [ 0.,  1.,  1.,  0.,  0.,  0.],
 [ 0.,  0.,  0.,  1.,  1.,  0.],
 [ 0.,  0.,  0.,  1.,  1.,  0.],
 [ 0.,  0.,  0.,  0.,  1.,  1.]])