Struct TextDataset 

pub struct TextDataset {
    pub texts: Vec<String>,
    pub labels: Vec<String>,
    /* private fields */
}

Text classification dataset

Fields

texts: Vec<String>

The text samples

labels: Vec<String>

The labels for each text

Implementations

impl TextDataset

pub fn new(texts: Vec<String>, labels: Vec<String>) -> Result<Self>

Create a new text dataset

pub fn len(&self) -> usize

Get the number of samples

pub fn is_empty(&self) -> bool

Check if the dataset is empty

pub fn unique_labels(&self) -> Vec<String>

Get the unique labels in the dataset

pub fn build_label_index(&mut self) -> Result<&mut Self>

Build a label index mapping

pub fn get_label_indices(&self) -> Result<Vec<usize>>

Get label indices

pub fn train_test_split( &self, test_size: f64, random_seed: Option<u64>, ) -> Result<(Self, Self)>

Split the dataset into train and test sets

Trait Implementations

impl Clone for TextDataset

fn clone(&self) -> TextDataset

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TextDataset

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

Formats the value using the given formatter.