What isBoosting?

How to use this library

[dependencies]minibosts = {version ="0.4.0" }

[dependencies]minibosts = {version ="0.4.0",features = ["gurobi"] }

Caution

Since I am no longer a student, I cannot check whether the compilation succeeded with the"gurobi" flag.

WhyMiniBoosts?

MiniBoosts for reasearch

Examples

miniboosts = {version ="0.4.0" }

miniboosts = {version ="0.4.0",features = ["gurobi"] }

use miniboosts::prelude::*;fnmain(){// Set file namelet file ="/path/to/input/data.csv";// Read the CSV file// The column named `class` corresponds to the labels (targets).let sample =SampleReader::new().file(file).has_header(true).target_feature("class").read().unwrap();// Set tolerance parameter as `0.01`.let tol:f64 =0.01;// Initialize Boosterletmut booster =AdaBoost::init(&sample).tolerance(tol);// Set the tolerance parameter.// Construct `DecisionTree` Weak Learner from `DecisionTreeBuilder`.let weak_learner =DecisionTreeBuilder::new(&sample).max_depth(3)// Specify the max depth (default is 2).criterion(Criterion::Twoing)// Choose the split rule..build();// Build `DecisionTree`.// Run the boosting algorithm// Each booster returns a combined hypothesis.let f = booster.run(&weak_learner);// Get the batch prediction for all examples in `data`.let predictions = f.predict_all(&sample);// You can predict the `i`th instance.let i =0_usize;let prediction = f.predict(&sample, i);// You can convert the hypothesis `f` to `String`.let s = serde_json::to_string(&f);}

let n_sample = sample.shape().0;// Get the number of training exampleslet nu = n_sampleasf64*0.2;// Set the upper-bound of the number of outliers.let lpboost =LPBoost::init(&sample).tolerance(tol).nu(nu);// Set a capping parameter.

Research feature

use miniboosts::prelude::*;use miniboosts::{Logger,LoggerBuilder,SoftMarginObjective,};// Define a loss functionfnzero_one_loss<H>(sample:&Sample,f:&H) ->f64whereH:Classifier{let n_sample = sample.shape().0asf64;let target = sample.target();    f.predict_all(sample).into_iter().zip(target.into_iter()).map(|(fx,&y)|if fx != yasi64{1.0}else{0.0}).sum::<f64>()        / n_sample}fnmain(){// Read the training datalet path ="/path/to/train/data.csv";let train =SampleReader::new().file(path).has_header(true).target_feature("class").read().unwrap();// Set some parameters used later.let n_sample = train.shape().0asf64;let nu =0.01* n_sample;// Read the test datalet path ="/path/to/test/data.csv";let test =SampleReader::new().file(path).has_header(true).target_feature("class").read().unwrap();let booster =LPBoost::init(&train).tolerance(0.01).nu(nu);let weak_learner =DecisionTreeBuilder::new(&train).max_depth(2).criterion(Criterion::Entropy).build();// Set the objective function.// One can use your own function by implementing ObjectiveFunction trait.let objective =SoftMarginObjective::new(nu);letmut logger =LoggerBuilder::new().booster(booster).weak_learner(tree).train_sample(&train).test_sample(&test).objective_function(objective).loss_function(zero_one_loss).time_limit_as_secs(120)// Terminate after 120 seconds.print_every(10)// Print log every 10 rounds..build();// Each line of `lpboost.csv` contains the following four information:// Objective value, Train loss, Test loss, Time per iteration// The returned value `f` is the combined hypothesis.let f = logger.run("logfile.csv").expect("Failed to logging");}

Others

Future work