0
$\begingroup$

Could you please tell me how a dataset should look like for one class classification. If I have web links, do I need a csv file of link_id and label of a class (for example all links will have a label 0 (target class identifier), because they are considered as positive samples).

$\endgroup$

closed as unclear what you're asking by Ferdi, cbeleites, Michael Chernick, whuber Mar 16 at 14:51

Please clarify your specific problem or add additional details to highlight exactly what you need. As it's currently written, it’s hard to tell exactly what you're asking. See the How to Ask page for help clarifying this question. If this question can be reworded to fit the rules in the help center, please edit the question.

  • $\begingroup$ I think it would be helpful to give some more info about your classification problem. What sort of features/variables will you have? Will they be generated from the content of those web links? Is there any way to generate observations from a different class (as binary classification is generally a simpler task)? $\endgroup$ – hamedbh Mar 15 at 16:02
  • $\begingroup$ Thanks for your answer. It will be extraction of words from each link, n_features are words, n_samples are number of links. There is no information about other classes. Can it be outlier detection and in what form I have to represent a dataset. It can be a sort of unsupervised learning. If supervised then how this dataset should be prepared. $\endgroup$ – Migel Mar 16 at 11:33
  • $\begingroup$ I think if you can add this detail to your question you can maybe have it taken off of hold. Worth a try anyway. It sounds like a natural language processing problem maybe, so your decisions would be about how to represent the text data and links. $\endgroup$ – hamedbh Mar 17 at 8:08