Struct NaiveBayesClassifier 

pub struct NaiveBayesClassifier { /* private fields */ }

Multinomial Naive Bayes text classifier with Laplace smoothing.

Uses a bag-of-words representation; each token in a document contributes to the likelihood estimate.

Implementations

impl NaiveBayesClassifier

pub fn new() -> Self

Create an unfitted classifier.

pub fn fit(&mut self, corpus: &[(String, String)], alpha: f64) -> Result<()>

Train on (text, label) pairs.

alpha is the Laplace smoothing factor (typical: 1.0).

pub fn predict(&self, text: &str) -> Result<Option<String>>

Predict the most likely class label for text.

pub fn predict_proba(&self, text: &str) -> Result<Vec<(String, f64)>>

Predict posterior probabilities (softmax of log-scores) per class.

pub fn predict_batch(&self, texts: &[String]) -> Result<Vec<Option<String>>>

Batch predict over multiple texts.

pub fn accuracy(&self, test_set: &[(String, String)]) -> Result<f64>

Compute accuracy on a labelled test set.

pub fn class_names(&self) -> &[String]

Return ordered class names.

Trait Implementations

impl Clone for NaiveBayesClassifier

fn clone(&self) -> NaiveBayesClassifier

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for NaiveBayesClassifier

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

Formats the value using the given formatter.

impl Default for NaiveBayesClassifier

fn default() -> NaiveBayesClassifier

Returns the “default value” for a type.