Skip to main content

​
Overview

The KNeighborsClassifier implements the k-nearest neighbors vote for classification. It predicts the class of a sample based on the majority class among its k nearest neighbors in the training set.

​
Constructor

import { KNeighborsClassifier } from '@scikitjs/sklearn';

const classifier = new KNeighborsClassifier({
  nNeighbors: 5
});

​
Parameters

​
nNeighbors
number
default:5
Number of neighbors to use for classification. Must be a positive integer.

​
Methods

​
fit()

Fit the k-nearest neighbors classifier from the training dataset. 
fit(X: Matrix, y: Vector, sampleWeight?: Vector): this
​
X
Matrix
required
Training data matrix where each row is a sample and each column is a feature.
​
y
Vector
required
Target values (class labels) for the training data.
​
sampleWeight
Vector
Sample weights (currently not implemented but reserved for future use).
Returns: this - The fitted classifier instance. Throws:
  • Error if nNeighbors exceeds the training set size
  • Error if input validation fails

​
predict()

Predict the class labels for the provided data. 
predict(X: Matrix): Vector
​
X
Matrix
required
Test samples to predict.
Returns: Vector - Predicted class labels.

​
predictProba()

Return probability estimates for the test data. 
predictProba(X: Matrix): Matrix
​
X
Matrix
required
Test samples to predict.
Returns: Matrix - Probability of each class for each sample. Each row represents a sample, and each column represents a class probability.

​
score()

Return the mean accuracy on the given test data and labels. 
score(X: Matrix, y: Vector): number
​
X
Matrix
required
Test samples.
​
y
Vector
required
True labels for the test samples.
Returns: number - Mean accuracy score.

​
Attributes

​
classes_
Vector
Unique class labels identified during training.

​
Examples

​
Basic Classification

import { KNeighborsClassifier } from '@scikitjs/sklearn';

// Training data: 2D features
const X = [
  [0, 0],
  [1, 1],
  [2, 2],
  [3, 3]
];

// Labels: binary classification
const y = [0, 0, 1, 1];

// Create and train classifier
const knn = new KNeighborsClassifier({ nNeighbors: 3 });
knn.fit(X, y);

// Predict new samples
const predictions = knn.predict([[1.5, 1.5], [2.5, 2.5]]);
console.log(predictions); // [0, 1]

​
Multi-class Classification with Probabilities

import { KNeighborsClassifier } from '@scikitjs/sklearn';

// Iris-like dataset
const X = [
  [5.1, 3.5],
  [4.9, 3.0],
  [7.0, 3.2],
  [6.4, 3.2],
  [6.3, 3.3],
  [5.8, 2.7]
];
const y = [0, 0, 1, 1, 2, 2];

const knn = new KNeighborsClassifier({ nNeighbors: 3 });
knn.fit(X, y);

// Get probability estimates
const probabilities = knn.predictProba([[6.0, 3.0]]);
console.log(probabilities);
// [[0.0, 0.67, 0.33]] - 67% class 1, 33% class 2

​
Model Evaluation

import { KNeighborsClassifier } from '@scikitjs/sklearn';

// Training data
const XTrain = [
  [0, 0], [0.5, 0.5], [1, 1],
  [2, 2], [2.5, 2.5], [3, 3]
];
const yTrain = [0, 0, 0, 1, 1, 1];

// Test data
const XTest = [[0.25, 0.25], [2.75, 2.75]];
const yTest = [0, 1];

const knn = new KNeighborsClassifier({ nNeighbors: 3 });
knn.fit(XTrain, yTrain);

// Calculate accuracy
const accuracy = knn.score(XTest, yTest);
console.log(`Accuracy: ${accuracy}`); // 1.0 (100%)

​
Notes

  • Uses squared Euclidean distance for efficiency (avoids square root computation)
  • Stores the entire training dataset (instance-based learning)
  • Prediction time increases with training set size
  • Works best when features are on similar scales
  • The algorithm uses uniform weighting (all neighbors contribute equally)

Build docs developers (and LLMs) love

Get started for freeTalk to us