Uh oh!
There was an error while loading. Please reload this page.
Extend Gam Samples - #3281
Conversation
Codecov Report
@@ Coverage Diff @@## master #3281 +/- ##
==========================================
+ Coverage 72.62% 72.64% +0.01%
==========================================
Files 807 807 Lines 145080 145191 +111 Branches 16213 16223 +10 ==========================================
+ Hits 105368 105477 +109 - Misses 35294 35295 +1 - Partials 4418 4419 +1
|
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
…ification/Gam.cs Co-Authored-By: rogancarr <rogan.carr@hotmail.com>
…ification/Gam.cs Co-Authored-By: rogancarr <rogan.carr@hotmail.com>
| @@ -0,0 +1,150 @@ | |||
| using System; | |||
There was a problem hiding this comment.
Similar comments for Gam without Options apply here (and other sample files) #Resolved
…ification/Gam.cs Co-Authored-By: rogancarr <rogan.carr@hotmail.com>
…ification/Gam.cs Co-Authored-By: rogancarr <rogan.carr@hotmail.com>
wschin
left a comment
There was a problem hiding this comment.
Just leave some clarification comments. Overall LGTM.
| else if (x < 0.25) | ||
| return 1; | ||
| else | ||
| return 0; |
There was a problem hiding this comment.
0 [](start = 23, length = 1)
is this the same as x < 0 value? #Resolved
There was a problem hiding this comment.
| { | ||
| // Generate random, uncoupled features. | ||
| var data = new Data { | ||
| Features = new float[2] { (float)(rng.NextDouble() - 0.5), (float)(rng.NextDouble() - 0.5) } |
There was a problem hiding this comment.
(float)(rng.NextDouble() - 0.5) [](start = 46, length = 31)
i would define this as a lambda below rng definition to make the code cleaner.
var rndFloat => (float)(rng.NextDouble() - 0.5) #Resolved
| // at least the default number of bins, as a small number of bins limits the capacity of | ||
| // the model. | ||
| var trainer = mlContext.BinaryClassification.Trainers.Gam( | ||
| new GamBinaryTrainer.Options { MaximumBinCountPerFeature = 16 }); |
There was a problem hiding this comment.
ptions { MaximumBinCountPerFeature = 16 } [](start = 38, length = 41)
can we use some options that are only available through Options class? #Resolved
* Adding Regression and Binary Classification GAM samples. (cherry picked from commit e37e5b1)
This PR extends the current GAM samples for regression and adds them for Binary Classification.
Fixes#3280