Re: [go-nuts] [ANN] A gradient boosting regressor package

2018-02-06 Thread Sina Siadat
Thanks for the link! On Mon, Feb 5, 2018 at 4:22 PM Aliaksandr Valialkin wrote: > > > On Tuesday, January 30, 2018 at 12:43:38 AM UTC+2, Sina Siadat wrote: >> >> Hi Sebastien, >> >> ​Thanks for your comment and question :) >> >> > I have one "drive-by-comment" and a question:

Re: [go-nuts] [ANN] A gradient boosting regressor package

2018-02-05 Thread Aliaksandr Valialkin
On Tuesday, January 30, 2018 at 12:43:38 AM UTC+2, Sina Siadat wrote: > > Hi Sebastien, > > ​Thanks for your comment and question :) > > > I have one "drive-by-comment" and a question: > > you could have perhaps used gonum for the stats stuff :) > > ​Actually, I did start with gonum :)) but I

Re: [go-nuts] [ANN] A gradient boosting regressor package

2018-01-30 Thread matthewjuran
Thanks for sharing gradboostreg here. Matt On Tuesday, January 30, 2018 at 12:47:33 AM UTC-6, Sina Siadat wrote: > > Hi Matt, > > Thank you for the code review! > > ​ > ​ > > gradboostreg/tree, stat, sample have no tests. > > Yes, thanks for reminder, I should write tests for them!​ > > ​ > ​ >

Re: [go-nuts] [ANN] A gradient boosting regressor package

2018-01-29 Thread Sina Siadat
Hi Matt, Thank you for the code review! ​ ​ > gradboostreg/tree, stat, sample have no tests. Yes, thanks for reminder, I should write tests for them!​ ​ ​ > These sub-packages may be better in package gradboostreg since they seem straightforward and contained to this library. Keeping those

Re: [go-nuts] [ANN] A gradient boosting regressor package

2018-01-29 Thread matthewjuran
Hi Sina, here’s a general code review. gradboostreg/tree, stat, sample have no tests. These sub-packages may be better in package gradboostreg since they seem straightforward and contained to this library. Keeping those things in sub-packages doesn’t seem to add much value over just having

Re: [go-nuts] [ANN] A gradient boosting regressor package

2018-01-29 Thread Sina Siadat
Hi Sebastien, ​Thanks for your comment and question :) > I have one "drive-by-comment" and a question: > you could have perhaps used gonum for the stats stuff :) ​Actually, I did start with gonum :)) but I thought it was a large dependency and I only needed a few funcs from it, so I decided to

Re: [go-nuts] [ANN] A gradient boosting regressor package

2018-01-29 Thread Sebastien Binet
hi Sina, On Mon, Jan 29, 2018 at 10:25 PM, Sina Siadat wrote: > Hi all! > > I just wrote a simple gradient regressor in Go. Gradient boosting is a > statistical learning method. Given a number of samples it returns a > function that fits the those data and can be used to