#word2vec

word2vec

Rust interface to word2vec

5 unstable releases

0.3.1 Dec 23, 2018
0.3.0 Sep 9, 2017
0.2.1 Mar 19, 2017
0.2.0 Feb 26, 2017
0.1.0 Feb 3, 2016

#40 in Machine learning

Download history 53/week @ 2018-10-17 4/week @ 2018-10-24 29/week @ 2018-11-07 4/week @ 2018-11-14 5/week @ 2018-11-21 9/week @ 2018-11-28 45/week @ 2018-12-05 5/week @ 2018-12-12 5/week @ 2018-12-19 77/week @ 2018-12-26 2/week @ 2019-01-02

80 downloads per month

MIT license

12KB
245 lines

word2vec Build Status

Rust interface to word2vec word vectors.

This crate provides a way to read a trained word vector file from word2vec. It doesn't provide model training and hence requires a already trained model.

Documentation

Documentation is available at https://github.com/DimaKudosh/word2vec/wiki

Example

Add this to your cargo.toml:

[dependencies]
# …
word2vec = "0.3.0"

Example for word similarity and word clusters:

extern crate word2vec;

fn main(){
	let model = word2vec::wordvectors::WordVector::load_from_binary(
		"vectors.bin").expect("Unable to load word vector model");
	println!("{:?}", model.cosine("snow", 10));
	let positive = vec!["woman", "king"];
	let negative = vec!["man"];
	println!("{:?}", model.analogy(positive, negative, 10));
	
	let clusters = word2vec::wordclusters::WordClusters::load_from_file(
		"classes.txt").expect("Unable to load word clusters");
	println!("{:?}", clusters.get_cluster("belarus"));
	println!("{:?}", clusters.get_words_on_cluster(6));
}

Dependencies

~105KB