docs(website): explain how users can perform train-test splitting with Ibis

[jitingxu1]

randomly partition a dataset into subsets while ensuring reproducibility

Reference:

• https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html
• https://rsample.tidymodels.org/reference/initial_split.html

[deepyaman]

#60 implements a basic (approximate) train-test split using Ibis. It could be very nice to wrap this up as part of a utility in IbisML, but it would be the only non-Step utility at this time. Maybe it's sufficient to just show it in the demo notebook for now? I'm not sure.

@lostmygithubaccount do you think users would really like to have this utility exposed directly, or it would increase the value prop? Happy to make it P0 then.

[lostmygithubaccount]

demonstrating how it's done w/ sufficient explanation seems fine for now

[deepyaman]

demonstrating how it's done w/ sufficient explanation seems fine for now

Updated the issue title to reflect this.