Peter Reutemann

The unlabeled dataset requires the exact same structure as the training set (ie same attribute and nominal label order) and the class attribute columns to contain only missing values (ie...

From a quick look at the code: 1. MultiSearch isn't a semi-supervised algorithm itself (and therefore won't get the unlabeled dataset for training), so can't be used to optimize a...

If you check the README in the root, this github repo is a *read-only* mirror of the official Weka subversion repository. Please post patches etc to the Weka mailing list...

I'm not familiar with MULAN, so not sure which characters it doesn't like. However, I've added a `-no-rename` command-line option (in the GUI it is the inverse: `renameAttributes`), which allows...

Have you tried a new snapshot with the new functionality?

What unresolved dependencies did you encounter? The master branch gets built every night and a [snapshot](https://adams.cms.waikato.ac.nz/snapshots/meka/) made available.

Great to hear that the build problem disappeared!

Please use the [Weka mailing list](https://list.waikato.ac.nz/postorius/lists/wekalist.list.waikato.ac.nz/) for questions/bug reports. The github repos are only courtesy read-only mirrors of the official subversion repository.

There are numerous ways of dealing with missing values: * `weka.classifiers.functions.Logistic`: uses [ReplaceMissingValues](https://weka.sourceforge.io/doc.dev/weka/filters/unsupervised/attribute/ReplaceMissingValues.html) filter (the easiest approach, though not necessarily the best) * `weka.classifiers.trees.RandomForest`: uses `weka.classifiers.trees.RandomTree` inside `weka.classifiers.meta.Bagging`; `RandomTree` ignores...

* J48 (improved version of C4.5): it's a rather complicated algorithm, as the tree building depends on whether binary trees are used and whether reduced error pruning is applied *...