I'm somewhat familiar with the contents of the Koller Probabilistic Graphical Models book (followed some of the Coursera course but didn't have time to do all the homework). I'd recently had the insight that working with pyMC is essentially creating a pgm and then auto-magically solving it. I just wanted to check with someone more knowledgeable before I start taking this idea too seriously.
So, what is the relationship between what is covered in PGM and what pyMC and related tools cover? Are they essentially the same thing? Is one a subset of the other? Or perhaps I have all wrong and they are just deceptively similar.