smartcore 0.2.0

The most advanced machine learning library in rust.
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65

//! # Collection of Distance Functions
//!
//! Many algorithms in machine learning require a measure of distance between data points. Distance metric (or metric) is a function that defines a distance between a pair of point elements of a set.
//! Formally, the distance can be any metric measure that is defined as \\( d(x, y) \geq 0\\) and follows three conditions:
//! 1. \\( d(x, y) = 0 \\) if and only \\( x = y \\), positive definiteness
//! 1. \\( d(x, y) = d(y, x) \\), symmetry
//! 1. \\( d(x, y) \leq d(x, z) + d(z, y) \\), subadditivity or triangle inequality
//!
//! for all \\(x, y, z \in Z \\)
//!
//! A good distance metric helps to improve the performance of classification, clustering and information retrieval algorithms significantly.
//!
//! <script src="https://polyfill.io/v3/polyfill.min.js?features=es6"></script>
//! <script id="MathJax-script" async src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>

/// Euclidean Distance is the straight-line distance between two points in Euclidean spacere that presents the shortest distance between these points.
pub mod euclidian;
/// Hamming Distance between two strings is the number of positions at which the corresponding symbols are different.
pub mod hamming;
/// The Mahalanobis distance is the distance between two points in multivariate space.
pub mod mahalanobis;
/// Also known as rectilinear distance, city block distance, taxicab metric.
pub mod manhattan;
/// A generalization of both the Euclidean distance and the Manhattan distance.
pub mod minkowski;

use crate::linalg::Matrix;
use crate::math::num::RealNumber;

/// Distance metric, a function that calculates distance between two points
pub trait Distance<T, F: RealNumber>: Clone {
    /// Calculates distance between _a_ and _b_
    fn distance(&self, a: &T, b: &T) -> F;
}

/// Multitude of distance metric functions
pub struct Distances {}

impl Distances {
    /// Euclidian distance, see [`Euclidian`](euclidian/index.html)
    pub fn euclidian() -> euclidian::Euclidian {
        euclidian::Euclidian {}
    }

    /// Minkowski distance, see [`Minkowski`](minkowski/index.html)
    /// * `p` - function order. Should be >= 1
    pub fn minkowski(p: u16) -> minkowski::Minkowski {
        minkowski::Minkowski { p }
    }

    /// Manhattan distance, see [`Manhattan`](manhattan/index.html)
    pub fn manhattan() -> manhattan::Manhattan {
        manhattan::Manhattan {}
    }

    /// Hamming distance, see [`Hamming`](hamming/index.html)
    pub fn hamming() -> hamming::Hamming {
        hamming::Hamming {}
    }

    /// Mahalanobis distance, see [`Mahalanobis`](mahalanobis/index.html)
    pub fn mahalanobis<T: RealNumber, M: Matrix<T>>(data: &M) -> mahalanobis::Mahalanobis<T, M> {
        mahalanobis::Mahalanobis::new(data)
    }
}