Struct EnhancedCountVectorizer 

pub struct EnhancedCountVectorizer { /* private fields */ }

Enhanced count vectorizer with n-gram support

Implementations

impl EnhancedCountVectorizer

pub fn new() -> Self

Create a new enhanced count vectorizer

pub fn set_binary(self, binary: bool) -> Self

Set whether to produce binary vectors

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

Set the n-gram range (min_n, max_n)

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

Set the maximum number of features

pub fn set_min_df(self, mindf: f64) -> Result<Self>

Set the minimum document frequency

pub fn set_max_df(self, maxdf: f64) -> Result<Self>

Set the maximum document frequency

pub fn set_lowercase(self, lowercase: bool) -> Self

Set whether to lowercase text

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 count vector

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

Transform multiple texts into a count matrix

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

Fit and transform in one step

Trait Implementations

impl Default for EnhancedCountVectorizer

fn default() -> Self

Returns the “default value” for a type.