//! # Hamming Distance
//!
//! Hamming Distance measures the similarity between two integer-valued vectors of the same length.
//! Given two vectors \\( x \in ℝ^n \\), \\( y \in ℝ^n \\) the hamming distance between \\( x \\) and \\( y \\), \\( d(x, y) \\), is the number of places where \\( x \\) and \\( y \\) differ.
//!
//! Example:
//!
//! ```
//! use smartcore::metrics::distance::Distance;
//! use smartcore::metrics::distance::hamming::Hamming;
//!
//! let a = vec![1, 0, 0, 1, 0, 0, 1];
//! let b = vec![1, 1, 0, 0, 1, 0, 1];
//!
//! let h: f64 = Hamming::new().distance(&a, &b);
//!
//! ```
//!
//!
//!
#[cfg(feature = "serde")]
use serde::{Deserialize, Serialize};
use std::marker::PhantomData;
use super::Distance;
use crate::linalg::basic::arrays::ArrayView1;
use crate::numbers::basenum::Number;
/// While comparing two integer-valued vectors of equal length, Hamming distance is the number of bit positions in which the two bits are different
#[cfg_attr(feature = "serde", derive(Serialize, Deserialize))]
#[derive(Debug, Clone)]
pub struct Hamming {
_t: PhantomData,
}
impl Hamming {
/// instatiate the initial structure
pub fn new() -> Hamming {
Hamming { _t: PhantomData }
}
}
impl Default for Hamming {
fn default() -> Self {
Self::new()
}
}
impl> Distance for Hamming {
fn distance(&self, x: &A, y: &A) -> f64 {
if x.shape() != y.shape() {
panic!("Input vector sizes are different");
}
let dist: usize = x
.iterator(0)
.zip(y.iterator(0))
.map(|(a, b)| match a != b {
true => 1,
false => 0,
})
.sum();
dist as f64 / x.shape() as f64
}
}
#[cfg(test)]
mod tests {
use super::*;
#[cfg_attr(
all(target_arch = "wasm32", not(target_os = "wasi")),
wasm_bindgen_test::wasm_bindgen_test
)]
#[test]
fn hamming_distance() {
let a = vec![1, 0, 0, 1, 0, 0, 1];
let b = vec![1, 1, 0, 0, 1, 0, 1];
let h: f64 = Hamming::new().distance(&a, &b);
assert!((h - 0.42857142).abs() < 1e-8);
}
}