ENH treeple tutorials should use native functions in scikit-tree

[sampan501]

From #256:

We should fix the tutorials to use native functions in scikit-tree, like build_coleman_forest etc. It should be clear to the user that they don't need to write their own custom function to compute a p-value using MIGHT.

[PSSF23]

Jovo wants to add a figure similar to this one, which would require all the intermediate statistics (the ones that 2 permuted forest make). build_coleman_forest doesn't return those values, unfortunately, so I'll postpone the conversion for now.

[sampan501]

Sure, we could write it like this instead. Show all the intermediate stats figures, and at the end show how to compute the stat and p-value using treeple

[adam2392]

The statistics we need are the null distribution? What else?