Struct MinHashIndex 

pub struct MinHashIndex { /* private fields */ }

A collection of MinHash signatures for batch similarity queries.

Implementations

impl MinHashIndex

pub fn new(threshold: f64) -> Self

Create a new index with the given similarity threshold.

pub fn insert(&mut self, label: String, signature: MinHashSignature)

Add a signature to the index.

pub fn len(&self) -> usize

Get the number of entries.

pub fn is_empty(&self) -> bool

Check if the index is empty.

pub fn query_similar(&self, query: &MinHashSignature) -> Vec<(&str, f64)>

Find all entries similar to a query signature.

pub fn find_duplicates(&self) -> Vec<(&str, &str, f64)>

Find all duplicate pairs above the threshold.

pub fn threshold(&self) -> f64

Get the threshold.

Trait Implementations

impl Clone for MinHashIndex

fn clone(&self) -> MinHashIndex

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for MinHashIndex

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.