Struct Classifier 

pub struct Classifier { /* private fields */ }

A random forest classifier.

Training

The Trainer implements CommonTrainerBuilder and EnsembleTrainerBuilder. Default training parameters:

max_depth: usize::MAX,
max_features: NumFeatures::SQRT,
seed: 42,
min_samples_leaf: 1,
min_samples_split: 2,
sample_weights: empty (1.0 for each sample)
num_trees: 100,
num_threads: 1,

Example

use rafor::rf;
let dataset = [0.7, 0.0, 0.8, 1.0, 0.7, 0.0];
let targets = [1, 5, 1];
let predictor = rf::Classifier::trainer().train(&dataset, &targets);
let predictions = predictor.predict(&dataset, 1);
assert_eq!(&predictions, &[1, 5, 1]);

Implementations

impl Classifier

pub fn predict(&self, dataset: &[f32], num_threads: usize) -> Vec<i64>

Predicts classes for a set of samples using num_threads threads. Dataset is a vector of floats with length multiple of num_features().

pub fn predict_one(&self, sample: &[f32]) -> i64

Predicts class for a single sample given by a slice of length num_features().

pub fn proba(&self, dataset: &[f32], num_threads: usize) -> Vec<f32>

Predicts classes probabilities for each sample using num_threads threads. The length of result vector is number_of_samples * num_classes().

pub fn num_features(&self) -> usize

Returns a number of features for a trained tree.

pub fn trainer() -> Trainer

Provides trainer for training a random forest classifier.

Trait Implementations

impl ClassDecode for Classifier

fn get_decode_table(&self) -> &[i64]

Returns a decode table of length num_classes().

fn num_classes(&self) -> usize

Returns a number of classes stored int table.

fn decode(&self, class_enc: usize) -> i64

Decodes a usize value into i64 according to decode table.

impl Clone for Classifier

fn clone(&self) -> Classifier

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Classifier

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

Formats the value using the given formatter.

impl Default for Classifier

fn default() -> Classifier

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for Classifier

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for Classifier

fn eq(&self, other: &Classifier) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for Classifier

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for Classifier