Struct Vocabulary 

pub struct Vocabulary { /* private fields */ }

Vocabulary with frequency counts and subsampling

Implementations

impl Vocabulary

pub fn new(min_count: u64, sample: f64) -> Self

Create new vocabulary builder

pub fn build_from_file<P: AsRef<Path>>(&mut self, path: P) -> Result<()>

Build vocabulary from corpus file (space-separated word_ids per line)

pub fn contains(&self, word_id: u32) -> bool

Check if word_id is in vocabulary

pub fn get(&self, word_id: u32) -> Option<&WordInfo>

Get word info

pub fn len(&self) -> usize

Get vocabulary size

pub fn is_empty(&self) -> bool

Check if vocabulary is empty

pub fn total_words(&self) -> u64

Get total word count

pub fn max_word_id(&self) -> u32

Get maximum word_id in vocabulary

pub fn iter(&self) -> impl Iterator<Item = &WordInfo>

Iterate over all words

pub fn get_word_id(&self, remapped_id: u32) -> Option<u32>

Get word_id from remapped_id

pub fn get_remapped_id(&self, word_id: u32) -> Option<u32>

Fast lookup: word_id → remapped_id (O(1), for training hot path)

Trait Implementations

impl Debug for Vocabulary

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

Formats the value using the given formatter.