Struct SparseCountVectorizer 

pub struct SparseCountVectorizer { /* private fields */ }

Sparse count vectorizer using CSR matrix representation

Implementations

impl SparseCountVectorizer

pub fn new(binary: bool) -> Self

Create a new sparse count vectorizer

pub fn with_tokenizer( tokenizer: Box<dyn Tokenizer + Send + Sync>, binary: bool, ) -> Self

Create with a custom tokenizer

pub fn fit(&mut self, texts: &[&str]) -> Result<()>

Fit the vectorizer on a corpus

pub fn transform(&self, text: &str) -> Result<SparseVector>

Transform a single text into a sparse vector

pub fn transform_batch(&self, texts: &[&str]) -> Result<CsrMatrix>

Transform a batch of texts into a sparse matrix

pub fn fit_transform(&mut self, texts: &[&str]) -> Result<CsrMatrix>

Fit and transform in one step

pub fn vocabulary_size(&self) -> usize

Get vocabulary size

pub fn vocabulary(&self) -> &Vocabulary

Get the vocabulary

Trait Implementations

impl Clone for SparseCountVectorizer

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.