As a new Dataiku DSS user getting familiar with building partitioned visual models, I would like it to be clearer that there is a set of summary graphics for each of the partitions. This would make using the partition feature easier and build confidence in users. Making this feature feel less like an "easter egg" and more like a productive feature.
As a creator of partitioned visual models trying to use best practices of k-fold cross-validation testing, it would be helpful to see the (ยฑ 0.###) on the summary screens as we do with non-partitioned models. This would allow for a quicker comparison of models.
DSS Screen showing Partitioned visual model summery report. There is a text cloud superimposed over the image that says "No indication here that you can click on anything."
What I was trying to produce was the following as shown in the training materials.
Dataiku DSS model summary Screen showing a partition model Error and Actual values plot. There is a cartoon speach bubble added that says "I ended up clicking about here to get the Error and Actual values graph to show up." With it's pointer pointing to a space between the name of the partition in this case Florida and the word "Trained" this location has been called out with a bit of transparent purple.
For the second comment about k-fold cross validation here is what I'm currently seeing.
Model Summary screen from partitioned models, on the left side of the screen there is an indication of where cross validation results are shown on non-prartitioned models. There is an overlaid speech bubble with the comment " It would be nice if Partitioned Models included the k-Fold cross validation results." This bubble points to a place where these values would be helpful.
For this testing, I'm using DSS V 8.0.4.
cc: @AshleyW