igrigorik / decisiontree

ID3-based implementation of the ML Decision Tree algorithm
1.44k stars 130 forks source link

Performance Improvements #32

Closed cheerfulstoic closed 7 years ago

cheerfulstoic commented 7 years ago

I was using the Bagging with a large amount of data and it was really slow. I've made some improvements (though it's still pretty slow ;).

The biggest improvement was pulling out the index = attributes.index(attribute) so that it didn't happen over and over again in each loop.

It also seemed like the fitness variable was being used, but I was only using the discrete. I'm happy to put that back if that's not true for continuous

igrigorik commented 7 years ago

👍