minhash-lsh

This crate reimplements the MinHash and MinHash LSH approaches from the Python package datasketch in Rust. It's only a partial reimplementation, use it at your own risk.

lib.rs:

minhash-lsh

This crate reimplements the MinHash and MinHash LSH approaches from the Python package datasketch in Rust. It's only a partial reimplementation, use it at your own risk.

Example MinHash

 use datasketch_minhash_lsh::MinHash;

 let mut m1 = <MinHash>::new(4, Some(1));
 let mut m2 = <MinHash>::new(4, Some(1));
 assert_eq!(m1.jaccard(&m2).unwrap(), 1.0);

 m2.update(&12);
 assert_eq!(m1.jaccard(&m2).unwrap(), 0.0);

 m1.update(&13);
 assert!(m1.jaccard(&m2).unwrap() < 1.0);

 m1.update(&12);
 let distance = m1.jaccard(&m2).unwrap();
 assert!(distance < 1.0 && distance > 0.0);

Example MinHashLsh

 use datasketch_minhash_lsh::{MinHashLsh, MinHash};

 let mut lsh = <MinHashLsh<&str>>::new(16, None, Some(0.5)).unwrap();
 let mut m1 = <MinHash>::new(16, Some(0));
 m1.update(&"a");

 let mut m2 = <MinHash>::new(16, Some(0));
 m2.update(&"b");

 lsh.insert("a", &m1).unwrap();
 lsh.insert("b", &m2).unwrap();

 let result = lsh.query(&m1).unwrap();
 assert!(result.contains(&"a"));

 let result = lsh.query(&m2).unwrap();
 assert!(result.contains(&"b"));
 assert!(result.len() <= 2);