Struct rv::dist::Dirichlet

pub struct Dirichlet { /* fields omitted */ }

Dirichlet distribution over points on the k-simplex.

Implementations

impl Dirichlet

pub fn new(alphas: Vec<f64>) -> Result<Self, DirichletError>

Creates a Dirichlet with a given alphas vector

pub fn new_unchecked(alphas: Vec<f64>) -> Self

Creates a new Dirichlet without checking whether the parameters are valid.

pub fn symmetric(alpha: f64, k: usize) -> Result<Self, DirichletError>

Creates a Dirichlet where all alphas are identical.

Notes

SymmetricDirichlet if faster and more compact, and is the preferred way to represent a Dirichlet symmetric weights.

Examples

let dir = Dirichlet::symmetric(1.0, 4).unwrap();
assert_eq!(*dir.alphas(), vec![1.0, 1.0, 1.0, 1.0]);

// Equivalent to SymmetricDirichlet
let symdir = SymmetricDirichlet::new(1.0, 4).unwrap();
let x: Vec<f64> = vec![0.1, 0.4, 0.3, 0.2];
assert::close(dir.ln_f(&x), symdir.ln_f(&x), 1E-12);

pub fn jeffreys(k: usize) -> Result<Self, DirichletError>

Creates a Dirichlet with all alphas = 0.5 (Jeffreys prior)

Notes

SymmetricDirichlet if faster and more compact, and is the preferred way to represent a Dirichlet symmetric weights.

Examples

let dir = Dirichlet::jeffreys(3).unwrap();
assert_eq!(*dir.alphas(), vec![0.5, 0.5, 0.5]);

// Equivalent to SymmetricDirichlet::jeffreys
let symdir = SymmetricDirichlet::jeffreys(3).unwrap();
let x: Vec<f64> = vec![0.1, 0.4, 0.5];
assert::close(dir.ln_f(&x), symdir.ln_f(&x), 1E-12);

pub fn k(&self) -> usize

The length of alphas / the number of categories

pub fn alphas(&self) -> &Vec<f64>

Get a reference to the weights vector, alphas

Trait Implementations

impl Clone for Dirichlet

fn clone(&self) -> Dirichlet

Returns a copy of the value.

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

Performs copy-assignment from source.

impl<X: CategoricalDatum> ConjugatePrior<X, Categorical> for Dirichlet

type Posterior = Self

Type of the posterior distribution

type LnMCache = (f64, f64)

Type of the ln_m cache

type LnPpCache = (Vec<f64>, f64)

Type of the ln_pp cache

fn posterior(&self, x: &CategoricalData<'_, X>) -> Self::Posterior

Computes the posterior distribution from the data

fn ln_m_cache(&self) -> Self::LnMCache

Compute the cache for the log marginal likelihood.

fn ln_m_with_cache(
    &self,
    cache: &Self::LnMCache,
    x: &CategoricalData<'_, X>
) -> f64

Log marginal likelihood with supplied cache.

fn ln_pp_cache(&self, x: &CategoricalData<'_, X>) -> Self::LnPpCache

Compute the cache for the Log posterior predictive of y given x.

fn ln_pp_with_cache(&self, cache: &Self::LnPpCache, y: &X) -> f64

Log posterior predictive of y given x with supplied ln(norm)

fn ln_m(&self, x: &DataOrSuffStat<'_, X, Fx>) -> f64

The log marginal likelihood

fn ln_pp(&self, y: &X, x: &DataOrSuffStat<'_, X, Fx>) -> f64

Log posterior predictive of y given x

fn m(&self, x: &DataOrSuffStat<'_, X, Fx>) -> f64

Marginal likelihood of x

fn pp(&self, y: &X, x: &DataOrSuffStat<'_, X, Fx>) -> f64

Posterior Predictive distribution

impl ContinuousDistr<Vec<f64, Global>> for Dirichlet

fn pdf(&self, x: &X) -> f64

The value of the Probability Density Function (PDF) at x

fn ln_pdf(&self, x: &X) -> f64

The value of the log Probability Density Function (PDF) at x

impl Debug for Dirichlet

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

Formats the value using the given formatter.

impl Display for Dirichlet

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

Formats the value using the given formatter.

impl From<&'_ SymmetricDirichlet> for Dirichlet

fn from(symdir: &SymmetricDirichlet) -> Self

Performs the conversion.

impl From<SymmetricDirichlet> for Dirichlet

fn from(symdir: SymmetricDirichlet) -> Self

Performs the conversion.

impl PartialEq<Dirichlet> for Dirichlet

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

This method tests for self and other values to be equal, and is used by ==.

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

This method tests for !=.

impl Rv<Categorical> for Dirichlet

fn ln_f(&self, x: &Categorical) -> f64

Probability function

fn draw<R: Rng>(&self, rng: &mut R) -> Categorical

Single draw from the Rv

fn f(&self, x: &X) -> f64

Probability function

fn sample<R: Rng>(&self, n: usize, rng: &mut R) -> Vec<X>

Multiple draws of the Rv

fn sample_stream<'r, R: Rng>(
    &'r self,
    rng: &'r mut R
) -> Box<dyn Iterator<Item = X> + 'r>

Create a never-ending iterator of samples

impl Rv<Vec<f64, Global>> for Dirichlet

fn draw<R: Rng>(&self, rng: &mut R) -> Vec<f64>

Single draw from the Rv

fn ln_f(&self, x: &Vec<f64>) -> f64

Probability function

fn f(&self, x: &X) -> f64

Probability function

fn sample<R: Rng>(&self, n: usize, rng: &mut R) -> Vec<X>

Multiple draws of the Rv

fn sample_stream<'r, R: Rng>(
    &'r self,
    rng: &'r mut R
) -> Box<dyn Iterator<Item = X> + 'r>

Create a never-ending iterator of samples

impl StructuralPartialEq for Dirichlet

impl Support<Vec<f64, Global>> for Dirichlet

fn supports(&self, x: &Vec<f64>) -> bool

Returns true if x is in the support of the Rv