Struct CountVectorizer 

pub struct CountVectorizer { /* private fields */ }

Count vectorizer that uses a bag-of-words representation

Implementations

impl CountVectorizer

pub fn new(binary: bool) -> Self

Create a new count vectorizer

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

Create a count vectorizer with a custom tokenizer

pub fn vocabulary(&self) -> &Vocabulary

Get a reference to the vocabulary

pub fn vocabulary_size(&self) -> usize

Get the vocabulary size

pub fn get_feature_count( &self, matrix: &Array2<f64>, document_index: usize, feature_index: usize, ) -> Option<f64>

Get feature count for a specific document and feature index from a matrix

pub fn vocabulary_map(&self) -> HashMap<String, usize>

Get vocabulary as HashMap for compatibility with visualization

Trait Implementations

impl Clone for CountVectorizer

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Default for CountVectorizer

fn default() -> Self

Returns the “default value” for a type.

impl Vectorizer for CountVectorizer

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

Fit the vectorizer on a corpus of texts

fn transform(&self, text: &str) -> Result<Array1<f64>>

Transform a text into a vector

fn transform_batch(&self, texts: &[&str]) -> Result<Array2<f64>>

Transform a batch of texts into a matrix where each row is a document vector

fn fit_transform(&mut self, texts: &[&str]) -> Result<Array2<f64>>

Fit on a corpus and then transform a batch of texts