I am using the sklearn GaussianMixture library. I got my GMM which is working fine, now I would like to sample from it. According to the docs I can use the model.sample(n) function to get n samples. This works, however I would like to sample, based on the fit probability, from a certain range of of values, not all the values.

To be precise, I want to be able to split the cumulative probability function into k equally probable ranges, like here:

And then be able to say I want to sample from range 5 (0.57~ to 0.71~ in the picture). Is there a way to do this?