Struct OptProphetOptions 

pub struct OptProphetOptions {

    pub growth: Option<GrowthType>,
    pub changepoints: Option<Vec<TimestampSeconds>>,
    pub n_changepoints: Option<u32>,
    pub changepoint_range: Option<PositiveFloat>,
    pub yearly_seasonality: Option<SeasonalityOption>,
    pub weekly_seasonality: Option<SeasonalityOption>,
    pub daily_seasonality: Option<SeasonalityOption>,
    pub seasonality_mode: Option<FeatureMode>,
    pub seasonality_prior_scale: Option<PositiveFloat>,
    pub changepoint_prior_scale: Option<PositiveFloat>,
    pub estimation: Option<EstimationMode>,
    pub interval_width: Option<IntervalWidth>,
    pub uncertainty_samples: Option<u32>,
    pub scaling: Option<Scaling>,
    pub holidays: Option<HashMap<String, Holiday>>,
    pub holidays_prior_scale: Option<PositiveFloat>,
    pub holidays_mode: Option<FeatureMode>,
}

Optional version of Prophet’s options, before applying any defaults.

Fields

growth: Option<GrowthType>

The type of growth (trend) to use.

changepoints: Option<Vec<TimestampSeconds>>

An optional list of changepoints.

If not provided, changepoints will be automatically selected.

n_changepoints: Option<u32>

The number of potential changepoints to include.

Not used if changepoints is provided.

If provided and changepoints is not provided, then n_changepoints potential changepoints will be selected uniformly from the first changepoint_range proportion of the history.

changepoint_range: Option<PositiveFloat>

The proportion of the history to consider for potential changepoints.

Not used if changepoints is provided.

yearly_seasonality: Option<SeasonalityOption>

How to fit yearly seasonality.

weekly_seasonality: Option<SeasonalityOption>

How to fit weekly seasonality.

daily_seasonality: Option<SeasonalityOption>

How to fit daily seasonality.

seasonality_mode: Option<FeatureMode>

How to model seasonality.

seasonality_prior_scale: Option<PositiveFloat>

The prior scale for seasonality.

This modulates the strength of seasonality, with larger values allowing the model to fit larger seasonal fluctuations and smaller values dampening the seasonality.

Can be specified for individual seasonalities using Prophet::add_seasonality.

changepoint_prior_scale: Option<PositiveFloat>

The prior scale for changepoints.

This modulates the flexibility of the automatic changepoint selection. Large values will allow many changepoints, while small values will allow few changepoints.

estimation: Option<EstimationMode>

How to perform parameter estimation.

When EstimationMode::Mle or EstimationMode::Map are used then no MCMC samples are taken.

interval_width: Option<IntervalWidth>

The width of the uncertainty intervals.

Must be between 0.0 and 1.0. Common values are 0.8 (80%), 0.9 (90%) and 0.95 (95%).

uncertainty_samples: Option<u32>

The number of simulated draws used to estimate uncertainty intervals.

Setting this value to 0 will disable uncertainty estimation and speed up the calculation.

scaling: Option<Scaling>

How to scale the data prior to fitting the model.

holidays: Option<HashMap<String, Holiday>>

Holidays to include in the model.

holidays_prior_scale: Option<PositiveFloat>

Prior scale for holidays.

This parameter modulates the strength of the holiday components model, unless overridden in each individual holiday’s input.

holidays_mode: Option<FeatureMode>

How to model holidays.

Trait Implementations

impl Clone for OptProphetOptions

fn clone(&self) -> OptProphetOptions

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for OptProphetOptions

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

Formats the value using the given formatter.

impl Default for OptProphetOptions

fn default() -> OptProphetOptions

Returns the “default value” for a type.

impl From<OptProphetOptions> for ProphetOptions

fn from(value: OptProphetOptions) -> Self

Converts to this type from the input type.