A Microsoft's LightGBM Rust binding
This tool is based on the work of @vaaaaanquish, that unfortunatelly, can't be used in actual linux distributions or recent rust version.
As a Data Scientist who uses LightGBM, I wissh to deploy, and possible train in rust, but as a Machine Learning engineer I wish to load model and data from cloud object storage, what is not possible from the Cpp distribution.
cargo add lightgbm2There are some examples in examples folder, like this one, adapted from @vaaaaanquish:
extern crate serde_json;
use lightgbm::{Dataset, Booster};
use serde_json::json;
let data = vec![vec![1.0, 0.1, 0.2, 0.1],
vec![0.7, 0.4, 0.5, 0.1],
vec![0.9, 0.8, 0.5, 0.1],
vec![0.2, 0.2, 0.8, 0.7],
vec![0.1, 0.7, 1.0, 0.9]];
let label = vec![0.0, 0.0, 0.0, 1.0, 1.0];
let dataset = Dataset::from_mat(data, label).unwrap();
let params = json!{
{
"num_iterations": 3,
"objective": "binary",
"metric": "auc"
}
};
let bst = Booster::train(dataset, ¶ms).unwrap();Contributions are welcome, just make a pull request. No rules other then keep current tests passing, add new tests for new changes and follow good coding practices, the best you can.