Decision Tree output doesn't show Variable importance plot

[Fran]

Hi.  I can't see within the Decision Tree browse (O, R, I) the Variable importance plot. Can you help me to  fix it?

Thanks

[CharlieS]

In your screenshot, you see the tool is operating as "RPart Decision-Tree Classification". I think this plot is only produced when the model type is "Regression" (Customize > Model Type and Sampling Weights > Regression).  

From the tool documentation:

• If the target field is a member of a category set, a classification tree is constructed.
• If the target field is a continuous variable, a regression tree is constructed.

https://help.alteryx.com/2018.3/rpart.htm

My test found the Variable Important plot in I output > Variable Importance.

[Fran]

Hi Charlie. Thank you for your clear explanation. Unhappily, your suggestion didn't work. I tried the 3 options: Auto, Classification, and Regression, none of the options showed up the Variable importance plot. It might be an Alteryx bug. 

Thanks again

[Fran]

Hi Charlie. Thank you for your clear explanation. Unhappily, your suggestion didn't work. I tried the 3 options: Auto, Classification, and Regression, none of the options showed up the Variable importance plot. It might be a Alteryx bug. 

Thanks again

[CharlieS]

Could you provide a sample of your data to test with?

[JohnE1 · Accepted solution]

I think i found out how to fix the problem - it is a Tool version issue. Do the following:

• Add the Decision Tree Tool to the canvass
• Right click on it
• Select "Choose Tool Version"
• You will see three options - select the second option (i.e. Decision Tree 1.0)

I ran into the same issue and it consumed a lot of time looking for solutions.  I hope that helps

[kittymilburn]

Thank you so much - my output looked completely different and this fixed it. Lifesaver! Thank you so much. 

[TimothyL]

Hi @Fran @kittymilburn ,

Thank for your supports. To empower users interpreting and explaining their predictive model,  we recently published a new set of model explanation macros: LIME & SHAP in this post.

It supports Decision Tree and other predictive tools like Random Forest, SVM, etc. Give a try and see if it could help you!