Struct MahalanobisDistance 

pub struct MahalanobisDistance<F> {
    pub inv_cov: Array2<F>,
}

Mahalanobis distance metric using precomputed inverse covariance matrix

Fields

inv_cov: Array2<F>

Inverse covariance matrix

Implementations

impl<F> MahalanobisDistance<F>

where F: Float + FromPrimitive + Debug + Send + Sync + ScalarOperand,

pub fn fromdata(data: ArrayView2<'_, F>) -> Result<Self>

Create a new Mahalanobis distance metric

Arguments

• data - Training data to compute the covariance matrix from

Returns

• Result containing the Mahalanobis distance metric or an error

pub fn from_inv_cov(_invcov: Array2<F>) -> Self

Create a Mahalanobis distance metric from a precomputed inverse covariance matrix

Trait Implementations

impl<F: Clone> Clone for MahalanobisDistance<F>

fn clone(&self) -> MahalanobisDistance<F>

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<F: Debug> Debug for MahalanobisDistance<F>

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

Formats the value using the given formatter.

impl<F> DistanceMetric<F> for MahalanobisDistance<F>

where F: Float + FromPrimitive + Debug + Send + Sync + 'static,

fn distance(&self, x: ArrayView1<'_, F>, y: ArrayView1<'_, F>) -> F

Compute distance between two vectors

fn name(&self) -> &'static str

Get the name of this distance metric

fn pairwise_distances(&self, data: ArrayView2<'_, F>) -> Array1<F>

Compute pairwise distances between all points in data

fn distances_to_centroids( &self, data: ArrayView2<'_, F>, centroids: ArrayView2<'_, F>, ) -> Array2<F>

Compute distances from each point to a set of centroids