Merge pull request #548 from epiforecasts/test-metrics-point

Issue 551: Remove scoringutils metrics as using Metrics versions

NAMESPACE

@@ -13,7 +13,6 @@ S3method(validate_forecast,forecast_binary)
 S3method(validate_forecast,forecast_point)
 S3method(validate_forecast,forecast_quantile)
 S3method(validate_forecast,forecast_sample)
-export(abs_error)
 export(add_coverage)
 export(add_pairwise_comparison)
 export(ae_median_quantile)
@@ -69,7 +68,6 @@ export(score)
 export(se_mean_sample)
 export(select_rules)
 export(set_forecast_unit)
-export(squared_error)
 export(summarise_scores)
 export(summarize_scores)
 export(theme_scoringutils)

NEWS.md

@@ -36,8 +36,9 @@ The update introduces breaking changes. If you want to keep using the older vers
   - `plot_avail_forecasts()` was renamed `plot_forecast_counts()` in line with the change in the function name. The `x` argument no longer has a default value, as the value will depend on the data provided by the user.
 - The deprecated `..density..` was replaced with `after_stat(density)` in ggplot calls.
 - Files ending in ".Rda" were renamed to ".rds" where appropriate when used together with `saveRDS()` or `readRDS()`.
-- `score()` now calls `na.omit()` on the data, instead of only removing rows with missing values in the columns `observed` and `predicted`. This is because `NA` values in other columns can also mess up e.g. grouping of forecasts according to the unit of a single forecast. 
+- `score()` now calls `na.omit()` on the data, instead of only removing rows with missing values in the columns `observed` and `predicted`. This is because `NA` values in other columns can also mess up e.g. grouping of forecasts according to the unit of a single forecast.
 - added documentation for the return value of `summarise_scores()`.
+- Removed abs_error and squared_error from the package in favour of `Metrics::ae` and `Metrics::se`. 
 - Added unit tests for `interval_coverage_quantile()` and `interval_coverage_dev_quantile()` in order to make sure that the functions provide the correct warnings when insufficient quantiles are provided.
 
 # scoringutils 1.2.2

R/metrics-quantile.R

@@ -499,7 +499,7 @@ bias_quantile_single_vector <- function(observed, predicted, quantile, na.rm) {
 #' `quantile`.
 #' @inheritParams wis
 #' @return numeric vector of length N with the absolute error of the median
-#' @seealso [ae_median_sample()], [abs_error()]
+#' @seealso [ae_median_sample()]
 #' @importFrom stats median
 #' @examples
 #' observed <- rnorm(30, mean = 1:30)

R/metrics-sample.R

@@ -92,7 +92,7 @@ bias_sample <- function(observed, predicted) {
 #' the number of data points and N (number of columns) the number of Monte
 #' Carlo samples. Alternatively, `predicted` can just be a vector of size n.
 #' @return vector with the scoring values
-#' @seealso [ae_median_quantile()], [abs_error()]
+#' @seealso [ae_median_quantile()]
 #' @importFrom stats median
 #' @examples
 #' observed <- rnorm(30, mean = 1:30)
@@ -127,7 +127,6 @@ ae_median_sample <- function(observed, predicted) {
 #' the number of data points and N (number of columns) the number of Monte
 #' Carlo samples. Alternatively, `predicted` can just be a vector of size n.
 #' @return vector with the scoring values
-#' @seealso [squared_error()]
 #' @examples
 #' observed <- rnorm(30, mean = 1:30)
 #' predicted_values <- matrix(rnorm(30, mean = 1:30))