/** @import { ParametersNaiveKNN } from "./index.js" */
/**
 * Naive KNN implementation using a distance matrix.
 *
 * This implementation pre-computes the entire distance matrix and performs
 * an exhaustive search. Best suited for small datasets or when a distance
 * matrix is already available.
 *
 * @template {number[] | Float64Array} T
 * @category KNN
 * @class
 * @extends KNN<T, ParametersNaiveKNN>
 */
export class NaiveKNN<T extends number[] | Float64Array> extends KNN<T, ParametersNaiveKNN> {
  /**
   * Generates a KNN list with given `elements`.
   *
   * @param {T[]} elements - Elements which should be added to the KNN list
   * @param {ParametersNaiveKNN} parameters
   */
  constructor(elements: T[], parameters?: ParametersNaiveKNN);
  _D: Matrix;
  /** @type {Heap<{ value: number; index: number }>[]} */
  KNN: Heap<{
    value: number;
    index: number;
  }>[];
  /**
   * @param {number} i
   * @param {number} k
   */
  search_by_index(
    i: number,
    k?: number,
  ): {
    element: T;
    index: number;
    distance: number;
  }[];
  /**
   * @param {T} t - Query element.
   * @param {number} [k=5] - Number of nearest neighbors to return. Default is `5`
   * @returns {{ element: T; index: number; distance: number }[]} - List consists of the `k` nearest neighbors.
   */
  search(
    t: T,
    k?: number,
  ): {
    element: T;
    index: number;
    distance: number;
  }[];
}
import type { ParametersNaiveKNN } from "./index.js";
import { KNN } from "./KNN.js";
import { Matrix } from "../matrix/index.js";
import { Heap } from "../datastructure/index.js";
//# sourceMappingURL=NaiveKNN.d.ts.map