How can I model total CPU millicores used to CPU millicore namespace limit?

Greetings Kubernetes Land,

I am still new to Kubernetes and to OpenShift. I am trying to come up with a way to plot total CPU millicores for a Kubernetes namespace over time to its namespace millicore resource limit. The goal is to try and look for namespaces that are overprovisioned and reduce limits. What statistics do people use for capacity of namespaces.

This is Kubernetes V1.x.

Again, I am still a newbie, so if my terms are not right, please let me know.

Thanks!