Struct Dataset 

pub struct Dataset<F>
where
    F: Float,
{
    pub y: Array1<F>,
    pub x: Array2<F>,
    pub linear_offset: Option<Array1<F>>,
    pub weights: Option<Array1<F>>,
    pub freqs: Option<Array1<F>>,
}

Fields

y: Array1<F>

the observation of response data by event

x: Array2<F>

the design matrix with events in rows and instances in columns

linear_offset: Option<Array1<F>>

The offset in the linear predictor for each data point. This can be used to fix the effect of control variables.

weights: Option<Array1<F>>

The variance weight of each observation (a.k.a. analytic weights)

freqs: Option<Array1<F>>

The frequency of each observation (traditionally positive integers)

Implementations

impl<F> Dataset<F>

where F: Float,

pub fn linear_predictor(&self, regressors: &Array1<F>) -> Array1<F>

Returns the linear predictors, i.e. the design matrix multiplied by the regression parameters. Each entry in the resulting array is the linear predictor for a given observation. If linear offsets for each observation are provided, these are added to the linear predictors

pub fn n_obs(&self) -> F

Total number of observations as given by the sum of the frequencies of observations

pub fn n_eff(&self) -> F

Returns the effective sample size corrected for the design effect. This exposes the sum of the squares of the variance weights.

Trait Implementations

impl<F> Clone for Dataset<F>

where F: Float + Clone,

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

Returns a duplicate of the value.

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

Performs copy-assignment from source.