Function reference • forecast.vocs

Forecast

Functions for forecasting across models, dates, and scenarios.

forecast(): Forecast using branching processes at a target date

forecast_across_dates(): Forecast across multiple dates

forecast_across_scenarios(): Forecast across multiple scenarios and dates

forecast_n_strain(): Forecast for a single model and summarise

plot(<fv_forecast>): Plot method for forecast

summary(<fv_forecast>): Summary method for forecast

unnest_posterior(): Unnest posterior estimates from a forecast data.frame

Model

Functions for fitting the forecasting models.

fv_as_data_list(): Format data for use with stan

fv_inits(): Set up initial conditions for model

fv_model(): Load and compile a strain model

fv_sample(): Fit a brancing process strain model

Preprocess

Functions for preprocessing observations.

filter_by_availability(): Filter data based on availability and forecast date

fv_dow_period(): Calculate the day of the week periodicity

latest_obs(): Filter for latest observations of all types

piecewise_steps(): Calculate piecewise steps

Postprocess

Functions for postprocessing model output.

convert_to_stanfit(): Convert to stanfit object

extract_draws(): Extract posterior draws

extract_forecast_dates(): Extract forecast dates

fv_extract_forecast(): Extract forecasts from a summarised posterior

fv_posterior(): Summarise the posterior

fv_tidy_posterior(): Summarise the posterior tidily

link_dates_with_posterior(): Link dates by time for posterior parameter estimates

link_obs_with_posterior(): Link posterior estimates with observed data

plot(<fv_posterior>): Plot method for fv_tidy_posterior

print(<fv_posterior>): Print method for fv_tidy_posterior

quantiles_to_long(): Convert summarised quantiles from wide to long format

summary(<fv_posterior>): Summary method for fv_tidy_posterior

update_voc_label(): Label the Variant of Concern

Plot

Functions for plotting postprocessed forecast model output.

add_forecast_dates(): Add the forecast dates to a plot

plot(<fv_forecast>): Plot method for forecast

plot(<fv_posterior>): Plot method for fv_tidy_posterior

plot_cases(): Plot the posterior prediction for cases

plot_default(): Default posterior plot

plot_growth(): Plot the posterior prediction for the growth rate

plot_pairs(): Pairs plot of parameters of interest and fitting diagnostics

plot_posterior(): Plot posterior predictions

plot_rt(): Plot the posterior prediction for the reproduction number

plot_theme(): Add the default plot theme

plot_voc_advantage(): Plot the posterior prediction for the transmission advantage for the variant of concern

plot_voc_frac(): Plot the population posterior prediction for the fraction of samples with the variant of concern

save_plots(): Save plots by name

Model validation

Functions for validating model fits and forecasts.

bp_launch_shinystan(): Launch shinystan

fv_score_forecast(): Evaluate forecasts using proper scoring rules

plot_pairs(): Pairs plot of parameters of interest and fitting diagnostics

Generate data

Functions for generating simulated data.

generate_obs(): Generate Simulated Observations

sample_sequences(): Sample Sequence Observation Model

Define and generate scenarios

Functions for defining and generating data scenarios.

define_scenarios(): Define data availability scenarios

generate_obs_scenario(): Define observed data for a scenario

update_obs_availability(): Update observations based on availability

Datasets

Package datasets used in examples and by users to explore the package functionality.

fv_example(): Load a package example

germany_covid19_delta_obs: Test positive COVID-19 cases and sequences in Germany

Check inputs

Functions to check the structure of user inputs.

check_dataframe(): Check a data.frame

check_observations(): Check observations are in the correct format

check_param(): Check a parameter is the correct type and length

check_quantiles(): Check Quantiles Required are Present