Implementation:Scikit learn Scikit learn NearestNeighbors

Knowledge Sources	Scikit_learn Scikit-learn Docs
Domains	Machine Learning, Nearest Neighbors
Last Updated	2026-02-08 15:00 GMT

Overview

Concrete tool for performing unsupervised nearest neighbor searches, provided by scikit-learn.

Description

The NearestNeighbors class is an unsupervised learner that implements neighbor searches. It provides both k-nearest neighbor queries (kneighbors) and radius-based neighbor queries (radius_neighbors). It supports multiple algorithms (ball_tree, kd_tree, brute force), various distance metrics, and can handle both dense and sparse input data.

Usage

Use this class when you need to find nearest neighbors in an unsupervised setting, such as for building neighborhood graphs, performing local density estimation, or as a building block for other neighbor-based algorithms.

Code Reference

Source Location

• Repository: scikit-learn
• File: sklearn/neighbors/_unsupervised.py

Signature

class NearestNeighbors(KNeighborsMixin, RadiusNeighborsMixin, NeighborsBase):
    def __init__(
        self,
        *,
        n_neighbors=5,
        radius=1.0,
        algorithm="auto",
        leaf_size=30,
        metric="minkowski",
        p=2,
        metric_params=None,
        n_jobs=None,
    ):

Import

from sklearn.neighbors import NearestNeighbors

I/O Contract

Inputs

Name	Type	Required	Description
n_neighbors	int	No	Number of neighbors for kneighbors queries (default 5)
radius	float	No	Range for radius_neighbors queries (default 1.0)
algorithm	str	No	Algorithm: 'auto', 'ball_tree', 'kd_tree', or 'brute' (default 'auto')
leaf_size	int	No	Leaf size for BallTree or KDTree (default 30)
metric	str or callable	No	Distance metric (default 'minkowski')
p	float	No	Power parameter for Minkowski metric (default 2, i.e. Euclidean)
n_jobs	int or None	No	Number of parallel jobs for neighbor search (default None)

Outputs

Name	Type	Description
distances	ndarray of shape (n_queries, n_neighbors)	Distances to the nearest neighbors
indices	ndarray of shape (n_queries, n_neighbors)	Indices of the nearest neighbors in the training data

Usage Examples

Basic Usage

from sklearn.neighbors import NearestNeighbors
import numpy as np

X = np.array([[1, 2], [3, 4], [5, 6], [7, 8]])
nn = NearestNeighbors(n_neighbors=2)
nn.fit(X)
distances, indices = nn.kneighbors([[2, 3]])
print(indices)    # [[0 1]]
print(distances)  # nearest neighbor distances

Related Pages

• Principle:Scikit_learn_Scikit_learn_Nearest_Neighbors