Closed
Description
The code in #181 of 02_fit_global_model splits the dataframe by species, but there are still synonyms present in the dataframe (e.g., Reynoutria japonica and Fallopia japonica). As a result, the loop later generates multiple models for each synonym, leading to redundancy.
Consider using canonicalName from taxa_info to standardize species names before splitting the dataframe. This would ensure that synonyms are grouped correctly under a single species.
In the loop, the first two words of scientificName are extracted, which is generally fine. However, this can cause issues if the genus has been updated or changed. This needs to be handled carefully to avoid inconsistencies later on
Metadata
Metadata
Assignees
Labels
No labels