Climbing trees 1: what are decision trees?
1–5 of 5 posts
Re: Climbing trees 1: what are decision trees?
#2I love decision trees. Conceptually simple, computational efficient and giving very good results for a lot of tasks. I especially use them on microcontroller grade system, via emlearn - which converts scikit-learn models to embedded friendly C code.
These articles are a good and pretty comprehensive introduction. I would have loved to have even more examples around the bias/variance trade off for forests, it is a key concept that not all practitioners have integrated.
Re: Climbing trees 1: what are decision trees?
#3I love decision trees. Conceptually simple, computational efficient and giving very good results for a lot of tasks. I especially use them on microcontroller grade system, via emlearn - which converts scikit-learn models to embedded friendly C code. These articles are a good and pretty comprehensive introduction. I would have loved to have even more examples around the bias/variance trade off for forests, it is a key…
Is there a tool to better to visualize them than like this https://mathpn.com/_astro/weather_tree.GMStLECX_ZgpDEk.svg for humans? I have tried graphviz or doing it in tex to ugly outputs
Re: Climbing trees 1: what are decision trees?
#4I love decision trees. Conceptually simple, computational efficient and giving very good results for a lot of tasks. I especially use them on microcontroller grade system, via emlearn - which converts scikit-learn models to embedded friendly C code. These articles are a good and pretty comprehensive introduction. I would have loved to have even more examples around the bias/variance trade off for forests, it is a key…
Is there a tool to better to visualize them than like this https://mathpn.com/_astro/weather_tree.GMStLECX_ZgpDEk.svg for humans? I have tried graphviz or doing it in tex to ugly outputs
https://github.com/parrt/dtreeviz has several interesting visualisation
Re: Climbing trees 1: what are decision trees?
#5I love decision trees. Conceptually simple, computational efficient and giving very good results for a lot of tasks. I especially use them on microcontroller grade system, via emlearn - which converts scikit-learn models to embedded friendly C code. These articles are a good and pretty comprehensive introduction. I would have loved to have even more examples around the bias/variance trade off for forests, it is a key…
Is there a tool to better to visualize them than like this https://mathpn.com/_astro/weather_tree.GMStLECX_ZgpDEk.svg for humans? I have tried graphviz or doing it in tex to ugly outputs
I've been liking Explainable Boosting Machines lately (kind of a cross between a GAM and a tree). They also have decision trees. Haven't tested them in production yet but they're pretty to look at.
[0] https://interpret.ml/docs/ebm.html [1] https://interpret.ml/docs/dt.html