Change Details

{T314863} has led to a first working computation of **article-level** relevance scores. This task lists the next steps, and may be broken down into subtasks. NOTE: //QID// = Wikidata identifier ==Engineering== - [] compute the full TF, i.e., //raw TF / count of all topic QIDs per page QID// - [] add constant columns at the very end of the pipeline - [] don't select TF-IDF component columns, just the final score - [] refactor the relevance computation function - [] consider refactoring tests with [chispa](https://github.com/MrPowers/chispa) ==Product== CC @AUgolnikova-WMF @CBogen. - [] decide whether we should keep null page QIDs and/or topic QIDs - [] decide whether we should also implement **section-level** relevance

{T314863} has led to a first working computation of **article-level** relevance scores. This task lists the next steps, and may be broken down into subtasks. NOTE: //QID// = Wikidata identifier ==Engineering== - [] compute the full TF, i.e., //raw TF / count of all topic QIDs per page QID// - [] add constant columns at the very end of the pipeline - [] don't select TF-IDF component columns, just the final score - [] refactor the relevance computation function - [] consider refactoring tests with [chispa](https://github.com/MrPowers/chispa) ==Product== CC @AUgolnikova-WMF @CBogen. - [] decide whether we should keep null page QIDs and/or topic QIDs - [] decide whether we should also implement **section-level** relevance - [] manual checks on data samples

{T314863} has led to a first working computation of **article-level** relevance scores. This task lists the next steps, and may be broken down into subtasks. NOTE: //QID// = Wikidata identifier ==Engineering== - [] compute the full TF, i.e., //raw TF / count of all topic QIDs per page QID// - [] add constant columns at the very end of the pipeline - [] don't select TF-IDF component columns, just the final score - [] refactor the relevance computation function - [] consider refactoring tests with [chispa](https://github.com/MrPowers/chispa) ==Product== CC @AUgolnikova-WMF @CBogen. - [] decide whether we should keep null page QIDs and/or topic QIDs - [] decide whether we should also implement **section-level** relevance - [] manual checks on data samples