-
not sure why, but I'm having a problem with java. On
devtools::install_github("openml/r")
I get
- installing _source_ package ‘OpenML’ ...
*\* R
*\* inst
*\* tests
*\* byte-compile and prepar…
-
R has a well deserved reputation as being a memory hog when training models. In part this is because the defaults tend toward keeping everything that might be used in the theory that this is easier f…
nkurz updated
9 years ago
-
It seems that downloadOpenMLDataAsMlrTask() can only be used once per R Session, because some files in the temporary data folder can't be overwritten.
Here's what I've done:
task1 = downloadOpenMLDat…
ghost updated
10 years ago
-
Some clarification on how we are reimplementing code uploads/checks:
There will be 2 API calls:
'implementation.upload' (exists)
This call has as a required argument POST description: an XML file co…
-
We are currently converting some of our large scale files from libsvm sparse format to spare ARFF.
The hope is that OpenML can support this on the server side natively.
Can I get some feedback on th…
-
I wanted to create a mlr task from a data set that I just uploaded to OpenML. Unfortunately, there seems to be a problem with some characters in the data set's description!?
Do I have to change the d…
ghost updated
10 years ago
-
Make the existence of a predict method for clustering optional (e.g. as a property). It is not necessarily available and model evaluation by performance measures in many applications is desired on tra…
g-rho updated
10 years ago
-
Dear mlr-team,
just now I have seen a special error that doesn't seem to be tested. When I split data in train and test predict newdata (test-set) on a model then normally the rownames of the pred$da…
-
```
load_all(".")
task = makeClusterTask(data = iris[,1:4])
lrn = makeLearner("cluster.Cobweb")
m = train(lrn, task)
pred = predict(m, task = task)
p = performance(pred, task = task, measures = db)
p…
-
Hi Thomas,
thanks again for your package! Really great :-) Just a tiny remark, there is a typo in the Usage section of your page. In the code below mulitple should be read multiple. Otherwise the exa…