Documentation restructuring, some fixes, clustering docs

[clonker]

• The documentation is now split into apidocs and a more narrative documentation
• the more narrative documentation is composed out of jupyter notebooks which are converted into html by the nbsphinx sphinx extension
• added first draft of clustering narrative documentation
• AMMs and OOMs are now part of the apidocs
• in mini batch clustering: when calling fit() the previous behavior was falling back to ordinary k-means. Now it takes shuffled samples of the dataset and performs clustering on these mini batches

[brookehus]

awesome, will check this out today!!

[brookehus]

Some questions but nothing major.

I looked at the clustering notebook here because git didn't want to render it in the PR diffs

I'm not looking at this with a copy editing mind, just basic stuff:

• API docs link didn't work for me
• Why does a fixed random seed make it only "quasi" reproducible?
• Do you want the notebooks to have citations? Could cite something with MSMs
• I love the visualization in block 11
• I would appreciate more informative plot titles - e.g. in the plots in blocks 8, 11, 15, 17, and 24, to distinguish them
• Can a custom metric only be defined in cpp or is python fine too?
• I like this example a lot

[clonker]

• quasi reproducibility: i will remove the quasi although it is in fact quasi, even ify ou fix the seed you can get different results on different machines, depending on implementation specifics of the underlying random engine
• the notebooks have citation keys - i will add msm citations as soon as im doing the msm docs
• will add more descriptive plot titles, thanks!
• custom metric is cpp only

[brookehus]

awesome good to merge pending plot titles!

[brookehus]

New titles look great! I like how you did it

[clonker]

Thanks! Will merge then once CI gives green light