Struct Morris 

pub struct Morris { /* private fields */ }

A Morris screening: the factors, the grid’s number of levels and the number of paths. It serializes as its fields, and reads back through Morris::new’s checks.

Implementations

impl Morris

pub fn new( factors: Vec<Factor>, levels: usize, paths: usize, ) -> Result<Self, AnalysisError>

A screening of factors on a grid of levels levels, with paths paths.

Errors

• AnalysisError::TooFew with no factors, fewer than 2 levels, or fewer than 2 paths (a standard deviation needs two).
• AnalysisError::DuplicateFactor for two factors with one name.
• AnalysisError::Unsupported for an odd number of levels: Morris’s step Δ is a whole number of levels only for an even one.
• AnalysisError::Count for more than MAX_LEVELS levels, or a design of more than MAX_DESIGN_POINTS points or MAX_DESIGN_VALUES coordinates.

pub fn factors(&self) -> &[Factor]

The factors.

pub fn levels(&self) -> usize

The grid’s number of levels, p.

pub fn paths(&self) -> usize

The number of paths, r.

pub fn step(&self) -> f64

The step Δ = p / (2 (p − 1)), as a fraction of each factor’s range.

pub fn design(&self, seed: u64) -> MorrisDesign

The paths of a screening seeded with seed. Path j draws from its own stream, SeededRng::for_stream(seed, &[j]): its start’s levels, then a direction for each factor, then the order (a Fisher–Yates shuffle), so it is the same however many paths are drawn.

pub fn screen( &self, seed: u64, model: impl FnMut(&[f64]) -> f64, ) -> Result<Screening, AnalysisError>

Draws the design seeded with seed, runs model at each of its points in order, and analyses the outputs (MorrisDesign::analyze).

Errors

As MorrisDesign::analyze.

pub fn population( &self, model: impl FnMut(&[f64]) -> f64, ) -> Result<Vec<ElementaryEffects>, AnalysisError>

Each factor’s elementary effects over the whole grid: Fᵢ’s mean, mean absolute value and standard deviation, exactly, from model run once at each of the grid’s p^k points. These are what Morris::screen estimates.

Errors

• AnalysisError::Count for a grid of more than MAX_POPULATION_POINTS points, its count p^k saturating at usize::MAX.
• AnalysisError::Output for an output that isn’t finite, at its grid point’s index (factor 0’s level the fastest-changing digit).

Trait Implementations

impl Clone for Morris

fn clone(&self) -> Morris

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Morris

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for Morris

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for Morris

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for Morris

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for Morris