News for hackers. Stuff that matters.
Re:How to Visualize Decision Trees by niyyou on Tuesday September 28, 2021 @01:54PM (#28685520)
And his visualization of constrained optimization is astonishing https://explained.ai/regularization/index.html (I struggled for a long time to get the right intuition of a Lagrangian)
Re:How to Visualize Decision Trees by parrt on Tuesday September 28, 2021 @02:23PM (#28685853)
Thanks! Took me a year to discover the key nut there. L1 vs L2 regularization is not well described I found so I went nuts trying to nail it down.
Re:How to Visualize Decision Trees by bravura on Tuesday September 28, 2021 @05:35PM (#28687823)
If you're interested, in my thesis I induced l1-regularized decision trees through a boosting style approach. Adding an l1 term and maximizing the gradient led to sparse tree.
Re:How to Visualize Decision Trees by jononor on Tuesday September 28, 2021 @09:44AM (#28682688)
Very nice work. Glad to see both classification and regression treated very well, with careful attention to design to make something that is easy to understand.

Now the question is - can we build on this (or do something analogous) for tree ensembles? Random Forests, Gradient Boosted Trees etc. Quite common to use that to gain predictive accuracy, though interpretability/explainability tends to suffer considerably.

Re:How to Visualize Decision Trees by parrt on Tuesday September 28, 2021 @12:52PM (#28684876)
Thanks! It took forever to bash my way to victory on that trees. The lib also supports the shallow trees in boosting machines.
Re:How to Visualize Decision Trees by julbook on Tuesday September 28, 2021 @10:15AM (#28683027)
Great explanation; I understand different visual tree orientations. I agree with the lesson learned section; it's not about programming alone but also about determining the ecosystem's capabilities.
Re:How to Visualize Decision Trees by Torwald on Tuesday September 28, 2021 @11:21AM (#28683851)
In the "Default scikit Iris visualization" example you could colorize the arrows for true|false since colors are available.

Alternatively you could use two distinct types of arrowheads.

Re:How to Visualize Decision Trees by parrt on Tuesday September 28, 2021 @12:53PM (#28684879)
That's a good idea. thanks!
Re:How to Visualize Decision Trees by parrt on Tuesday September 28, 2021 @12:54PM (#28684895)
Also note we recently added 1D and 2D classifier decision boundary plots. See https://github.com/parrt/dtreeviz/blob/master/notebooks/clas...
Re:How to Visualize Decision Trees by mistrial9 on Tuesday September 28, 2021 @10:20AM (#28683081)
kudos for the clean HTML document
Re:How to Visualize Decision Trees by parrt on Tuesday September 28, 2021 @12:53PM (#28684886)
Thanks. It's morphed over time as we add functionality so it's less clean than before.
Re:How to Visualize Decision Trees by graphviz on Tuesday September 28, 2021 @10:20PM (#28689604)
nice