Struct TfidfVectorizer 

pub struct TfidfVectorizer { /* private fields */ }

TF-IDF text vectorizer.

Combines count vectorization with IDF weighting and optional normalization. Produces a sparse CSR matrix.

Example

use scry_learn::text::TfidfVectorizer;

let docs = ["the cat sat", "the dog sat", "the cat played"];
let mut tfidf = TfidfVectorizer::new();
let matrix = tfidf.fit_transform(&docs);

Implementations

impl TfidfVectorizer

pub fn new() -> Self

Create a new TfidfVectorizer with default settings.

pub fn min_df(self, n: usize) -> Self

Set minimum document frequency.

pub fn max_df(self, frac: f64) -> Self

Set maximum document frequency fraction.

pub fn ngram_range(self, min_n: usize, max_n: usize) -> Self

Set n-gram range.

pub fn max_features(self, n: usize) -> Self

Limit vocabulary size.

pub fn norm(self, norm: TfidfNorm) -> Self

Set normalization method. Default: L2.

pub fn sublinear_tf(self, enable: bool) -> Self

Enable sublinear TF scaling: tf = 1 + log(tf).

pub fn smooth_idf(self, enable: bool) -> Self

Enable smooth IDF: adds 1 to document frequencies. Default: true (matches sklearn).

pub fn fit<S: AsRef<str>>(&mut self, documents: &[S])

Learn vocabulary and IDF weights from documents.

pub fn transform<S: AsRef<str>>(&self, documents: &[S]) -> CsrMatrix

Transform documents into a TF-IDF weighted sparse matrix.

pub fn fit_transform<S: AsRef<str>>(&mut self, documents: &[S]) -> CsrMatrix

Fit and transform in one step.

pub fn idf(&self) -> &[f64]

Return the learned IDF weights.

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

Return the underlying vocabulary.

pub fn get_feature_names(&self) -> Vec<String>

Return feature names sorted by column index.

pub fn n_features(&self) -> usize

Number of features.

Trait Implementations

impl Clone for TfidfVectorizer

fn clone(&self) -> TfidfVectorizer

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TfidfVectorizer

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

Formats the value using the given formatter.

impl Default for TfidfVectorizer

fn default() -> Self

Returns the “default value” for a type.