Function sgbt 

pub fn sgbt(n_steps: usize, lr: f64) -> SGBTLearner

Create an SGBT learner with squared loss from minimal parameters.

For full control, use SGBTConfig::builder() directly.

use irithyll::{sgbt, StreamingLearner};

let mut model = sgbt(50, 0.01);
model.train(&[1.0, 2.0], 3.0);
let pred = model.predict(&[1.0, 2.0]);