0
$\begingroup$

I am trying to find a dataset which is linearly non-separable. I checked the Iris dataset and the UCI website says:

The data set contains 3 classes of 50 instances each, where each class refers to a type of iris plant. One class is linearly separable from the other 2; the latter are NOT linearly separable from each other

Source: https://archive.ics.uci.edu/ml/datasets/iris)

However, I need a two class dataset which is linearly non-separable.

Please give some pointers.

$\endgroup$
  • 2
    $\begingroup$ Why not drop the linearly seperable iris class, leaving you to use the two that aren't? $\endgroup$ – redhqs Jun 21 at 10:17
0
$\begingroup$

The easiest way is to generate your data artificially. For example generate points from two circles with different radius and same center, that gives two groups of points which are not linearly separable.

$\endgroup$
0
$\begingroup$

In Python you can use the in-built make_moons and make_blobs functionalities of scikit-learn, changing the parameters accordingly.

The "titanic dataset" and "mpgcars" also contain non-linearly separable categories, in addition.

$\endgroup$

Your Answer

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

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