5

Recently I stumbled upon a R package that works similar like caret, but I can't remember what it's name was and I can't find it. It seemed to be less well known, but at least as extensive. Someone able to help?

Edit: I search for this other package to widen my horizon. There is no specific other reason. This question is specific however, since I am not looking for a general recommendation, but I am looking for this specific package I have in mind. I will recognize the package once I read its functions and descriptions. I had searched for a couple of hours myself and did not find it by searching for "package similar to caret". That is why I need help.

Make42
  • 752
  • 2
  • 8
  • 18
  • This question is closed for a reason. – Dawny33 Apr 14 '16 at 11:53
  • @Dawny33: I would love to know what the reason is. That is something I really hate about SE: Downvotes and closes without good reason. This is not about a recommendation. – Make42 Apr 14 '16 at 12:23
  • I understand that it is frustrating. But, this qn is a recommendation, as it does not have necessary details. It isn't clear why would you want another package similar to caret when there's caret? – Dawny33 Apr 14 '16 at 12:35
  • @Dawny33: I edited my qn accordingly ;-). Giving an answer and being helpful wasn't actually that hard as it seems... – Make42 Apr 14 '16 at 12:42

1 Answers1

10

MLR is similar to caret, MLR offers a high-level interface to various statistical and machine learning packages.

According to the package description:

Interface to a large number of classification and regression techniques, including machine-readable parameter descriptions. There is also an experimental extension for survival analysis, clustering and general, example-specific cost-sensitive learning. Generic resampling, including cross-validation, bootstrapping and subsampling. Hyperparameter tuning with modern optimization techniques, for single- and multi-objective problems. Filter and wrapper methods for feature selection. Extension of basic learners with additional operations common in machine learning, also allowing for easy nested resampling. Most operations can be parallelized.

Please check the Reference and Homepage.

Stephen Rauch
  • 1,783
  • 11
  • 22
  • 34
krishna Prasad
  • 1,147
  • 1
  • 14
  • 23
  • 1
    Yeah, I think this was the one. – Make42 Apr 14 '16 at 12:38
  • I do not dare to ask... but do you have a recommendation :-D in comparing those two? I haven't found anything useful on the net so far. Which one is more comprehensive and intuitive in the long run (not necessarily "how fast can I learn it") in practical data science tasks? (This site is about practical data science, as far as I know.) – Make42 Apr 14 '16 at 12:46
  • 1
    @Make42 Caught you asking for recommendations again :P. Btw, I would vote for caret just due to the number of contributors and the number of users using the package. I haven't used it personally, however, MLR seems to be boasting more functionalities than caret. – Dawny33 Apr 14 '16 at 12:51
  • I also vote for caret package. – krishna Prasad Apr 14 '16 at 17:38