docs: readme

m-muecke · m-muecke · commit dd33d4f4a740 · 2024-12-28T20:22:45.000+01:00
diff --git a/README.Rmd b/README.Rmd
@@ -27,8 +27,10 @@ Extending mlr3 to time series forecasting.
 [![Mattermost](https://img.shields.io/badge/chat-mattermost-orange.svg)](https://lmmisld-lmu-stats-slds.srv.mwn.de/mlr_invite/)
 <!-- badges: end -->
 
+```{=gfm}
 > [!IMPORTANT]
 > This package is in an early stage of development and should be considered experimental.
+```
 
 ## Installation
 
diff --git a/README.md b/README.md
@@ -15,8 +15,8 @@ status](https://www.r-pkg.org/badges/version/mlr3forecast)](https://CRAN.R-proje
 [![Mattermost](https://img.shields.io/badge/chat-mattermost-orange.svg)](https://lmmisld-lmu-stats-slds.srv.mwn.de/mlr_invite/)
 <!-- badges: end -->
 
-> \[!IMPORTANT\] This package is in an early stage of development and
-> should be considered experimental.
+> [!IMPORTANT]
+> This package is in an early stage of development and should be considered experimental.
 
 ## Installation
 
@@ -44,32 +44,32 @@ prediction = ff$predict_newdata(newdata, task)
 prediction
 #> <PredictionRegr> for 3 observations:
 #>  row_ids truth response
-#>        1    NA 444.1509
-#>        2    NA 473.6015
-#>        3    NA 483.2165
+#>        1    NA 444.7671
+#>        2    NA 473.9790
+#>        3    NA 480.9669
 prediction = ff$predict(task, 142:144)
 prediction
 #> <PredictionRegr> for 3 observations:
 #>  row_ids truth response
-#>        1   461 456.5106
-#>        2   390 408.6549
-#>        3   432 395.3594
+#>        1   461 462.5280
+#>        2   390 410.8195
+#>        3   432 388.3864
 prediction$score(measure)
 #> regr.rmse 
-#>  23.87951
+#>  27.91612
 
 ff = Forecaster$new(lrn("regr.ranger"), 1:3)
 resampling = rsmp("forecast_holdout", ratio = 0.8)
 rr = resample(task, ff, resampling)
 rr$aggregate(measure)
 #> regr.rmse 
-#>  97.71474
+#>  115.1751
 
 resampling = rsmp("forecast_cv")
 rr = resample(task, ff, resampling)
 rr$aggregate(measure)
 #> regr.rmse 
-#>  51.24863
+#>  51.15563
 ```
 
 ### Multivariate
@@ -88,39 +88,39 @@ prediction = ff$predict(new_task, 142:144)
 ff$predict(new_task, 142:144)
 #> <PredictionRegr> for 3 observations:
 #>  row_ids truth response
-#>        1   461 448.8459
-#>        2   390 410.8536
-#>        3   432 406.0194
+#>        1   461 450.8882
+#>        2   390 405.8591
+#>        3   432 405.1108
 prediction$score(measure)
 #> regr.rmse 
-#>  20.47428
+#>  18.94544
 
 row_ids = new_task$nrow - 0:2
 ff$predict_newdata(new_task$data(rows = row_ids), new_task)
 #> <PredictionRegr> for 3 observations:
 #>  row_ids truth response
-#>        1   432 408.5416
-#>        2   390 389.6410
-#>        3   461 394.0066
+#>        1   432 407.3052
+#>        2   390 386.6901
+#>        3   461 390.5332
 newdata = new_task$data(rows = row_ids, cols = new_task$feature_names)
 ff$predict_newdata(newdata, new_task)
 #> <PredictionRegr> for 3 observations:
 #>  row_ids truth response
-#>        1    NA 408.5416
-#>        2    NA 389.6410
-#>        3    NA 394.0066
+#>        1    NA 407.3052
+#>        2    NA 386.6901
+#>        3    NA 390.5332
 
 resampling = rsmp("forecast_holdout", ratio = 0.8)
 rr = resample(new_task, ff, resampling)
 rr$aggregate(measure)
 #> regr.rmse 
-#>  83.38583
+#>  80.58328
 
 resampling = rsmp("forecast_cv")
 rr = resample(new_task, ff, resampling)
 rr$aggregate(measure)
 #> regr.rmse 
-#>  43.98399
+#>  44.15569
 ```
 
 ### mlr3pipelines integration
@@ -130,5 +130,5 @@ glrn = as_learner(pop %>>% ff)$train(task)
 prediction = glrn$predict(task, 142:144)
 prediction$score(measure)
 #> regr.rmse 
-#>  19.01081
+#>  19.22717
 ```
