Mitokic/10162024/hts drivers fix

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: finnts
 Title: Microsoft Finance Time Series Forecasting Framework
-Version: 0.4.0.9007
+Version: 0.4.0.9008
 Authors@R: 
     c(person(given = "Mike",
            family = "Tokic",
@@ -24,7 +24,7 @@ License: MIT + file LICENSE
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 Imports: 
     cli,
     Cubist,

NEWS.md

@@ -1,12 +1,12 @@
-# finnts 0.4.0.9007 (DEVELOPMENT VERSION)
+# finnts 0.4.0.9008 (DEVELOPMENT VERSION)
 
 ## Improvements
 
 -   Added support for hierarchical forecasting with external regressors
 -   Allow global models for hierarchical forecasts
 -   Multistep horizon forecasts for R1 recipe, listed as `multistep_horizon` within `prep_data()` 
 -   Always save the most accurate model average, regardless if selected as best model. This allows for improved scaling with large data sets.
--   Automatically condense large forecasts (+10k time series) into smaller amount of files to make it easier to read forecast outputs
+-   Automatically condense large forecasts (+3k time series) into smaller amount of files to make it easier to read forecast outputs
 -   Improved weighted MAPE calculation across all time series
 -   Changed default for box_cox argument in `prep_data()` to FALSE
 -   Support for spark version 3.4 in Azure Synapse/Fabric

R/final_models.R

@@ -618,7 +618,7 @@ final_models <- function(run_info,
   par_end(cl)
 
   # condense outputs into less files for larger runs
-  if (length(combo_list) > 10000) {
+  if (length(combo_list) > 3000) {
     cli::cli_progress_step("Condensing Forecasts")
 
     condense_data(

R/hierarchy.R

@@ -112,6 +112,7 @@ prep_hierarchical_data <- function(input_data,
           .noexport = NULL
         ) %do% {
           temp_tbl <- input_data_adj %>%
+            tidyr::drop_na(tidyselect::all_of(regressor_var)) %>%
             dplyr::select(Date, tidyselect::all_of(value_level_iter), tidyselect::all_of(regressor_var)) %>%
             dplyr::distinct()
 
@@ -144,6 +145,7 @@ prep_hierarchical_data <- function(input_data,
 
         # agg by total
         total_tbl <- input_data_adj %>%
+          tidyr::drop_na(tidyselect::all_of(regressor_var)) %>%
           dplyr::select(Date, value_level[[1]], tidyselect::all_of(regressor_var)) %>%
           dplyr::distinct() %>%
           dplyr::group_by(Date) %>%