I would like to generate a dataset of data with 3-dimensional each such that the data is linearly separable. In addition, I would like to be able to rotate the "hyperplane" of the dataset to generate different of datasets with rotating hyperplanes (as described in the second section here -- see image below). Is there a way for me to do this in Python without relying on Massive Online Analysis (MOA)? Ideally I would like to be able to do it with simpler packages like numpy, scipy, sklearn. I've explored sklearn and found this but I don't think it is able to do what I asked. I found an API for what I want but have trouble installing it and therefore am finding an alternative. If you are able to answer with a sample code, then that would help me greatly too! Continue reading...
