Is there any package in R that's commonly used for semi-supervised learning ? I have a dataset where I manually labeled 100 data points so I'd like to use semi-supervise learning for the rest of the data sets.


closed as off-topic by gung, whuber Aug 1 '16 at 14:15

This question appears to be off-topic. The users who voted to close gave this specific reason:

  • "This question appears to be off-topic because EITHER it is not about statistics, machine learning, data analysis, data mining, or data visualization, OR it focuses on programming, debugging, or performing routine operations within a statistical computing platform. If the latter, you could try the support links we maintain." – gung, whuber
If this question can be reworded to fit the rules in the help center, please edit the question.


You can try for example the upclass package


There you will find the standard pdf reference and a vignette explaining it all along with examples. I think the function upclassify() would match your requirements.


Probably irrelevant now, but it might make the answer more complete to also mention the spa package as well. It uses a graph-based technique to learn a model. Basically it uses information from both the data point features and how similar data points are to each other. If you have a distance matrix for the data points, it might work well. This article explains it with a bit more detail and some examples. You can find the package binary files here:


edited to provide some additional info about package.

  • 1
    $\begingroup$ Can you say anything about these? Just listing a package &/or a link is considered inadequate here. $\endgroup$ – gung Jul 31 '16 at 23:10
  • $\begingroup$ We are trying to build a permanent repository of high-quality statistical information in the form of questions & answers. We try to avoid link-only answers. If possible, could you expand it, perhaps by giving a brief discussion about what's in the spa package and perhaps a comparison with the other package mentioned before. $\endgroup$ – Glen_b Jul 31 '16 at 23:39
  • $\begingroup$ @gung @Glen_b, done. I don't understand how the initial answer was any different however. Also, upclass gathers a variety of different algorithms for data classification, so comparing that to this would be somewhat apples-and-orangesish. Also, with so little info about the inquirer's dataset, there is not much more to be said. $\endgroup$ – Mohammad Ansarin Aug 1 '16 at 13:13
  • $\begingroup$ Your answer came up in the 'low quality' review queue. Most likely, an algorithm picked it for additional scrutiny because it was short and without upvotes. I didn't see the other answer because it wasn't displayed, but you're right about it. $\endgroup$ – gung Aug 1 '16 at 13:21

Not the answer you're looking for? Browse other questions tagged or ask your own question.