Struct TfidfVectorizer 

pub struct TfidfVectorizer { /* private fields */ }

TF-IDF vectorizer for converting text to TF-IDF features

Implementations

impl TfidfVectorizer

pub fn new() -> Self

Create a new TF-IDF vectorizer

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

Set whether to use IDF weighting

pub fn with_norm(self, norm: bool) -> Self

Set whether to apply L2 normalization

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

Set whether to smooth IDF weights

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

Set whether to use sublinear term frequency

pub fn configure_count_vectorizer<F>(self, f: F) -> Self

where F: FnOnce(CountVectorizer) -> CountVectorizer,

Configure the underlying count vectorizer

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

Fit the vectorizer on documents

pub fn transform(&self, documents: &[String]) -> Result<Array2<f64>>

Transform documents to TF-IDF vectors

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

Fit and transform in one step

pub fn get_feature_names(&self) -> &[String]

Get feature names

Trait Implementations

impl Default for TfidfVectorizer

fn default() -> Self

Returns the “default value” for a type.