get_forecast_counts: Count number of available forecasts

In epiforecasts/scoringutils: Utilities for Scoring and Assessing Predictions

Count number of available forecasts

Description

Given a data set with forecasts, this function counts the number of available forecasts. The level of grouping can be specified using the by argument (e.g. to count the number of forecasts per model, or the number of forecasts per model and location). This is useful to determine whether there are any missing forecasts.

Usage

get_forecast_counts(
  forecast,
  by = get_forecast_unit(forecast),
  collapse = c("quantile_level", "sample_id")
)

Arguments

forecast	A forecast object (a validated data.table with predicted and observed values).
by	character vector or NULL (the default) that denotes the categories over which the number of forecasts should be counted. By default this will be the unit of a single forecast (i.e. all available columns (apart from a few "protected" columns such as 'predicted' and 'observed') plus "quantile_level" or "sample_id" where present).
collapse	character vector (default: ⁠c("quantile_level", "sample_id"⁠) with names of categories for which the number of rows should be collapsed to one when counting. For example, a single forecast is usually represented by a set of several quantiles or samples and collapsing these to one makes sure that a single forecast only gets counted once. Setting collapse = c() would mean that all quantiles / samples would be counted as individual forecasts.

Value

A data.table with columns as specified in by and an additional column "count" with the number of forecasts.

Examples

library(magrittr) # pipe operator
example_quantile %>%
  as_forecast_quantile() %>%
  get_forecast_counts(by = c("model", "target_type"))

epiforecasts/scoringutils documentation built on Dec. 11, 2024, 11:12 a.m.