Struct EnhancedTfidfVectorizer 

pub struct EnhancedTfidfVectorizer { /* private fields */ }

Enhanced TF-IDF vectorizer with IDF smoothing options

Implementations

impl EnhancedTfidfVectorizer

pub fn new() -> Self

Create a new enhanced TF-IDF vectorizer

pub fn set_use_idf(self, useidf: bool) -> Self

Set whether to use IDF weighting

pub fn set_smooth_idf(self, smoothidf: bool) -> Self

Set whether to smooth IDF weights

pub fn set_sublinear_tf(self, sublineartf: bool) -> Self

Set whether to use sublinear TF scaling

pub fn set_norm(self, norm: Option<String>) -> Result<Self>

Set the normalization method (None, “l1”, or “l2”)

pub fn set_ngram_range(self, range: (usize, usize)) -> Result<Self>

Set n-gram range

pub fn set_max_features(self, maxfeatures: Option<usize>) -> Self

Set maximum features

pub fn vocabulary(&self) -> &Vocabulary

Get the vocabulary

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

Fit the vectorizer on a corpus

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

Transform text into a TF-IDF vector

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

Transform multiple texts into a TF-IDF matrix

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

Fit and transform in one step

Trait Implementations

impl Default for EnhancedTfidfVectorizer

fn default() -> Self

Returns the “default value” for a type.