Struct LabelBinarizer 

pub struct LabelBinarizer { /* private fields */ }

An unfitted one-vs-rest label binarizer.

Calling Fit::fit on an Array1<usize> discovers the sorted set of unique class labels and returns a FittedLabelBinarizer.

neg_label / pos_label are the integer values written into the output indicator matrix for absent / present classes, mirroring sklearn’s LabelBinarizer(neg_label=0, pos_label=1) (sklearn/preprocessing/_label.py:263). The defaults 0 / 1 reproduce the canonical 0/1 indicator behavior.

Implementations

impl LabelBinarizer

pub fn new() -> Self

Create a new LabelBinarizer with the default neg_label=0, pos_label=1 (the canonical 0/1 indicator encoding).

pub fn with_neg_label(self, neg_label: i64) -> Self

Set the neg_label (value used for absent classes).

Mirrors sklearn’s LabelBinarizer(neg_label=...) (sklearn/preprocessing/_label.py:263). Must be strictly less than pos_label; validated at Fit::fit time (_label.py:283-287).

pub fn with_pos_label(self, pos_label: i64) -> Self

Set the pos_label (value used for the present class).

Mirrors sklearn’s LabelBinarizer(pos_label=...) (sklearn/preprocessing/_label.py:263). Must be strictly greater than neg_label; validated at Fit::fit time (_label.py:283-287).

pub fn neg_label(&self) -> i64

Return the configured neg_label.

pub fn pos_label(&self) -> i64

Return the configured pos_label.

Trait Implementations

impl Clone for LabelBinarizer

fn clone(&self) -> LabelBinarizer

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LabelBinarizer

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

Formats the value using the given formatter.

impl Default for LabelBinarizer

fn default() -> Self

Returns the “default value” for a type.

impl Fit<ArrayBase<OwnedRepr<usize>, Dim<[usize; 1]>>, ()> for LabelBinarizer

fn fit( &self, y: &Array1<usize>, _target: &(), ) -> Result<FittedLabelBinarizer, FerroError>

Fit the binarizer by discovering unique class labels.

Errors

• Returns FerroError::InvalidParameter if neg_label >= pos_label, mirroring sklearn’s neg_label={0} must be strictly less than pos_label={1}. raise (sklearn/preprocessing/_label.py:283-287).
• Returns FerroError::InsufficientSamples if the input is empty.

type Fitted = FittedLabelBinarizer

The fitted model type returned by fit.

type Error = FerroError

The error type returned by fit.