Struct Logistic 

pub struct Logistic {
    pub scaler: Scaler,
    pub intercept: f64,
    pub weights: Vec<f64>,
}

Logistic regression p = σ(b₀ + w·z) on standardized inputs z.

Fields

scaler: Scaler

intercept: f64

weights: Vec<f64>

Implementations

impl Logistic

pub fn fit(x: &[Vec<f64>], y: &[f64], w: &[f64], lambda: f64) -> Self

Fit by Newton’s method (IRLS) with ridge penalty lambda per row. Samples can be weighted (e.g. to stop one symbol dominating).

pub fn logit(&self, r: &[f64]) -> f64

pub fn predict(&self, r: &[f64]) -> f64

pub fn lean(&self, r: &[f64]) -> f64

The part of the logit that comes from the features, not the base rate. Positive means “the measurements lean up”.

Trait Implementations

impl Clone for Logistic

fn clone(&self) -> Logistic

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Logistic

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Logistic

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for Logistic

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.