-
We have at least few interesting things that we could support. This will be exposed after the release
- scaling
- transductive
- one class
- regression
-
1. We do not define environment, compare **DONE**
```
> svm
function (x, ...)
UseMethod("svm")
> SVM
function(x, ...)
UseMethod("SVM")
```
2. Shouldn't I be ab…
-
Fix only warnings. Data warnings is fixed (packing script bug)
Reproducing:
`./src/packThis.sh `
`R CMD check `
```
* using log directory ‘/Users/stanislawj/Documents/gmum.r.Rcheck’
* using R vers…
-
Dear all,
At the line number 161-162 of the file Vertex.scala, it is the implementation of the quantity cv as described in the section 2.2 [1].
``` scala
val ent = GetNeighborhoodEntropy(neighborCl…
-
http://svmlight.joachims.org/ - here is a list of awesome features. Should we include in the API any of those?
-
The `TSNE` class has no `fit` method. This issue is basically asking whether this is ok.
I thought having a `fit` was an API requirement.
Other manifold methods store the result of `fit_transform` in …
-
We should add `predict` and `fit_predict` to other clustering algorithms than `KMeans`: they are useful to retrieve cluster labels independently of the underlying attribute names...