Struct WordLevel 

pub struct WordLevel { /* private fields */ }

WordLevel model.

Example

use std::collections::HashMap;
use morpheme::models::WordLevel;
use morpheme::Model;

let vocab: HashMap<String, u32> = [("<unk>", 0), ("hello", 1)].map(|(t, i)| (t.to_string(), i)).into();
let wl = WordLevel::builder().vocab(vocab).unk_token("<unk>").build()?;
assert_eq!(wl.tokenize("hello")?[0].id, 1);
assert_eq!(wl.tokenize("goodbye")?[0].id, 0);

Implementations

impl WordLevel

pub fn builder() -> WordLevelBuilder

Start building a model.

pub fn unk_token(&self) -> &str

The token emitted for words that are not in the vocabulary.

Trait Implementations

impl Clone for WordLevel

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for WordLevel

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

Formats the value using the given formatter.

impl Default for WordLevel

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for WordLevel

fn deserialize<D: Deserializer<'de>>(deserializer: D) -> Result<Self, D::Error>

Deserialize this value from the given Serde deserializer.

impl Eq for WordLevel

impl From<WordLevel> for ModelWrapper

fn from(m: WordLevel) -> Self

Converts to this type from the input type.

impl Model for WordLevel

fn tokenize(&self, token: &str) -> Result<Vec<Token>>

Tokenize sequence. Token offsets are byte offsets into sequence.

fn token_to_id(&self, token: &str) -> Option<u32>

Id of token, if it is in the vocabulary.

fn id_to_token(&self, id: u32) -> Option<String>

Token for id, if it is in the vocabulary.

fn vocab(&self) -> HashMap<String, u32>

The full vocabulary.

fn vocab_size(&self) -> usize

Vocabulary size.

impl PartialEq for WordLevel

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for WordLevel

fn serialize<S: Serializer>(&self, serializer: S) -> Result<S::Ok, S::Error>

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for WordLevel