Struct DecisionTreeClassifier 

pub struct DecisionTreeClassifier<XT: Number, YT: WholeNumber> { /* private fields */ }

Implementation of a decision tree classifier.

This struct represents a decision tree classifier, which is a supervised machine learning algorithm used for classification tasks. It can be used to build a decision tree from a dataset and make predictions on new data.

Type Parameters

• XT: The type of the features in the dataset.
• YT: The type of the labels in the dataset.

Examples

use rusty_ai::trees::classifier::DecisionTreeClassifier;
use rusty_ai::data::dataset::Dataset;
use nalgebra::{DMatrix, DVector};

// Create a new decision tree classifier
let mut tree = DecisionTreeClassifier::<f64, u8>::new();

// Set the minimum number of samples required to split an internal node
tree.set_min_samples_split(5).unwrap();

// Set the maximum depth of the tree
tree.set_max_depth(Some(10)).unwrap();



let x = DMatrix::from_row_slice(3, 2, &[1.0, 2.0, 3.0, 4.0, 5.0, 6.0]);
let y = DVector::from_vec(vec![0, 1, 0]);
let dataset = Dataset::new(x, y);
tree.fit(&dataset).unwrap();

// Make predictions on new data points
let x_test = DMatrix::from_row_slice(2, 2, &[1.0, 2.0, 3.0, 4.0]);
let predictions = tree.predict(&x_test);
assert!(predictions.is_ok());

Implementations

impl<XT: Number, YT: WholeNumber> DecisionTreeClassifier<XT, YT>

pub fn new() -> Self

pub fn with_params( criterion: Option<String>, min_samples_split: Option<u16>, max_depth: Option<u16>, ) -> Result<Self, Box<dyn Error>>

Creates a new instance of the decision tree classifier with custom parameters.

Arguments

• criterion - The criterion used for splitting nodes. Default is “gini”.
• min_samples_split - The minimum number of samples required to split an internal node. Default is 2.
• max_depth - The maximum depth of the tree. Default is None (unlimited depth).

Returns

A new instance of the decision tree classifier with the specified parameters.

Errors

This method will return an error if the classifier is unknown, the minimum number of samples to split is less than 2, or if the maximum depth is less than 1.

pub fn set_min_samples_split( &mut self, min_samples_split: u16, ) -> Result<(), Box<dyn Error>>

Sets the minimum number of samples required to split an internal node.

Arguments

• min_samples_split - The minimum number of samples required to split an internal node.

Errors

This method will return an error if the minimum number of samples to split is less than 2.

pub fn set_max_depth( &mut self, max_depth: Option<u16>, ) -> Result<(), Box<dyn Error>>

Sets the maximum depth of the tree.

Arguments

• max_depth - The maximum depth of the tree.

Errors

This method will return an error if the maximum depth is less than 1.

pub fn set_criterion(&mut self, criterion: String) -> Result<(), Box<dyn Error>>

Sets the criterion used for splitting nodes.

Arguments

• criterion - The criterion used for splitting nodes.

Errors

This method will return an error if the criterion is not supported.

pub fn max_depth(&self) -> Option<u16>

Returns the maximum depth of the tree.

pub fn min_samples_split(&self) -> u16

Returns the minimum number of samples required to split an internal node.

pub fn criterion(&self) -> &str

Returns the criterion used for splitting nodes.

pub fn fit( &mut self, dataset: &Dataset<XT, YT>, ) -> Result<String, Box<dyn Error>>

Builds the decision tree from a dataset.

Arguments

• dataset - The dataset containing features and labels.

Returns

A string indicating that the tree was built successfully.

Errors

This method will return an error if the tree couldn’t be built.

pub fn predict( &self, features: &DMatrix<XT>, ) -> Result<DVector<YT>, Box<dyn Error>>

Predicts the labels for new data.

Arguments

• features - The matrix of features for the new data.

Returns

A vector containing the predicted labels for the new data.

Errors

This method will return an error if the tree wasn’t built yet.

Trait Implementations

impl<XT: Number, YT: WholeNumber> ClassificationMetrics<YT> for DecisionTreeClassifier<XT, YT>

fn confusion_matrix( &self, y_true: &DVector<T>, y_pred: &DVector<T>, ) -> Result<DMatrix<usize>, Box<dyn Error>>

Computes the confusion matrix based on the true labels and predicted labels.

fn accuracy( &self, y_true: &DVector<T>, y_pred: &DVector<T>, ) -> Result<f64, Box<dyn Error>>

Computes the accuracy based on the true labels and predicted labels.

fn precision( &self, y_true: &DVector<T>, y_pred: &DVector<T>, ) -> Result<f64, Box<dyn Error>>

Computes the precision based on the true labels and predicted labels.

fn recall( &self, y_true: &DVector<T>, y_pred: &DVector<T>, ) -> Result<f64, Box<dyn Error>>

Computes the recall based on the true labels and predicted labels.

fn f1_score( &self, y_true: &DVector<T>, y_pred: &DVector<T>, ) -> Result<f64, Box<dyn Error>>

Computes the F1 score based on the true labels and predicted labels.

impl<XT: Clone + Number, YT: Clone + WholeNumber> Clone for DecisionTreeClassifier<XT, YT>

fn clone(&self) -> DecisionTreeClassifier<XT, YT>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<XT: Debug + Number, YT: Debug + WholeNumber> Debug for DecisionTreeClassifier<XT, YT>

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

Formats the value using the given formatter.

impl<XT: Number, YT: WholeNumber> Default for DecisionTreeClassifier<XT, YT>

fn default() -> Self

Returns the “default value” for a type.