Struct CountVectorizer 

pub struct CountVectorizer { /* private fields */ }

Count vectorizer for converting text documents to term frequency vectors

Implementations

impl CountVectorizer

pub fn new() -> Self

Create a new count vectorizer

pub fn with_max_features(self, maxfeatures: usize) -> Self

Set maximum number of features

pub fn with_min_df(self, mindf: f64) -> Self

Set minimum document frequency

pub fn with_max_df(self, maxdf: f64) -> Self

Set maximum document frequency

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

Set whether to convert to lowercase

pub fn with_token_pattern(self, pattern: &str) -> Result<Self>

Set custom token pattern

pub fn with_stop_words(self, stopwords: Vec<String>) -> Self

Set stop words

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

Fit the vectorizer on a collection of documents

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

Transform documents to count 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 CountVectorizer

fn default() -> Self

Returns the “default value” for a type.