Struct SparseTfidfVectorizer 

pub struct SparseTfidfVectorizer { /* private fields */ }

Sparse TF-IDF vectorizer

Implementations

impl SparseTfidfVectorizer

pub fn new() -> Self

Create a new sparse TF-IDF vectorizer

pub fn with_settings(useidf: bool, norm: Option<String>) -> Self

Create with custom settings

pub fn with_tokenizer(tokenizer: Box<dyn Tokenizer + Send + Sync>) -> 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 TF-IDF vector

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

Transform a batch of texts into a sparse TF-IDF 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

pub fn idf_values(&self) -> Option<&Array1<f64>>

Get the IDF values

Trait Implementations

impl Clone for SparseTfidfVectorizer

fn clone(&self) -> SparseTfidfVectorizer

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Default for SparseTfidfVectorizer

fn default() -> Self

Returns the “default value” for a type.