Struct TokenPrediction 

pub struct TokenPrediction {
    pub token_id: u32,
    pub predicted_label: String,
    pub predicted_class: usize,
    pub confidence: f32,
    pub all_scores: Vec<f32>,
}

Prediction for a single token in token classification

Fields

token_id: u32

Token ID from vocabulary

predicted_label: String

Predicted label (e.g., “B-PERSON”, “I-EMAIL”, “O”)

predicted_class: usize

Index of predicted class

confidence: f32

Confidence score for predicted class (0.0-1.0)

all_scores: Vec<f32>

Probability distribution over all classes (after softmax)

Implementations

impl TokenPrediction

pub fn new( token_id: u32, predicted_label: String, predicted_class: usize, confidence: f32, all_scores: Vec<f32>, ) -> Self

Create a new token prediction

pub fn validate(&self) -> Result<(), String>

Validate invariants

Trait Implementations

impl Clone for TokenPrediction

fn clone(&self) -> TokenPrediction

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TokenPrediction

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

Formats the value using the given formatter.

impl PartialEq for TokenPrediction

fn eq(&self, other: &TokenPrediction) -> 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 StructuralPartialEq for TokenPrediction