I am looking for the unit labels for the variables in the "Wine" benchmark set deposited on the UCI Machine Learning Repository?


I searched online and also looked through the reference but couldn't find anything. In certain cases it is not so hard to infer the units, e.g., "% ABV" for "alcohol" and "mg/L" for the "proline" content. But for some others this might be trickier.

Knowing those labels doesn't really matter in the application, however, it certainly looks more professional for presenting some data (e.g., decision boundaries/regions for benchmarking new classifiers etc.) and having the axes labeled correctly.

If someone has the correct labels, it would be also great if someone could submit them to the UCI repo for future reference.

  • Did you contact either of the contact people listed with the data set? – philshem Feb 23 '15 at 10:17
  • Yes, I tried to email them, but it seems that the email addresses are not active anymore :( A message that you sent could not be delivered to one or more of its recipients. This is a permanent error. The following address(es) failed: Unrouteable address – user4331 Feb 23 '15 at 10:37

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy