cmpstr/dist/types/metric/DiceSorensen.d.ts

CmpStr is a lightweight, fast and well performing package for calculating string similarity

/**
 * Dice-Sørensen Coefficient
 * src/metric/DiceSorensen.ts
 *
 * @see https://en.wikipedia.org/wiki/Dice-S%C3%B8rensen_coefficient
 *
 * This module implements the Dice-Sørensen coefficient, a statistic used to gauge
 * the similarity of two samples. It is commonly used in natural language processing
 * and information retrieval to compare the similarity between two sets of data,
 * such as text documents. The coefficient is defined as twice the size of the
 * intersection divided by the sum of the sizes of the two sets.
 *
 * The implementation includes methods to compute bigrams from strings and calculate
 * the coefficient based on these bigrams. It handles edge cases, such as empty
 * strings and identical strings, to ensure accurate results.
 *
 * @module Metric/DiceSorensenCoefficient
 * @author Paul Köhler (komed3)
 * @license MIT
 */
import type { MetricInput, MetricOptions, MetricCompute } from '../utils/Types';
import { Metric } from './Metric';
export interface DiceRaw {
    intersection: number;
    size: number;
}
/**
 * DiceSorensenCoefficient class extends the Metric class to implement the Dice-Sørensen coefficient.
 */
export declare class DiceSorensenCoefficient extends Metric<DiceRaw> {
    /**
     * Constructor for the DiceSorensen class.
     *
     * Initializes the DiceSorensen metric with two input strings or
     * arrays of strings and optional options.
     *
     * @param {MetricInput} a - First input string or array of strings
     * @param {MetricInput} b - Second input string or array of strings
     * @param {MetricOptions} [opt] - Options for the metric computation
     */
    constructor(a: MetricInput, b: MetricInput, opt?: MetricOptions);
    /**
     * Computes the bigrams of a given string.
     *
     * @param {string} str - The input string
     * @return {Set<string>} - A set of bigrams (two-character sequences) from the string
     */
    private _bigrams;
    /**
     * Calculates the Dice-Sørensen coefficient between two strings.
     *
     * @param {string} a - First string
     * @param {string} b - Second string
     * @return {MetricCompute<DiceRaw>} - Object containing the similarity result and raw distance
     */
    protected compute(a: string, b: string): MetricCompute<DiceRaw>;
}