Struct Scaler 

pub struct Scaler {
    pub center: Array1<f64>,
    pub scale: Array1<f64>,
}

Fitting a scaler produces these per-column statistics. Reuse them to replay the same transform on new data.

Fit a scaler on the training rows only. Then apply it unchanged to the test rows. Fitting it on everything leaks information about the test set into training. That is why standardize and min_max_scale return this struct. Keep it. Pass it to apply_scaler for every later batch.

The two field names describe the general shape of the transform, (value - center) / scale:

• standardize sets center to the column mean and scale to its standard deviation.
• min_max_scale sets center to the column minimum and scale to its range.

Fields

center: Array1<f64>

Per-column value that apply_scaler subtracts before scaling (mean, or minimum).

scale: Array1<f64>

Per-column divisor (standard deviation, or range). Never 0: a constant column gets a scale of 1, so it maps to all-zeros instead of NaN.

Trait Implementations

impl Clone for Scaler

fn clone(&self) -> Scaler

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Scaler

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

Formats the value using the given formatter.

impl PartialEq for Scaler

fn eq(&self, other: &Scaler) -> bool

Equality operator ==.

fn ne(&self, other: &Rhs) -> bool

Inequality operator !=.

impl StructuralPartialEq for Scaler