Dr Andi Lowe

The problem is that if the predicate is very long, such as in the example above, the predicate is split up and `name.of.predicate` holds the predicate as a vector of...

H'mmm... knitron doesn't produce inline output, which would have been nice, but I can live with exporting from a Jupyter Notebook before running knitron.

Perhaps nbconvert might handle the case of other kernels? (I'm not a Python expert, sorry.) I found this: http://nbconvert.readthedocs.io/en/latest/execute_api.html http://nbconvert.readthedocs.io/en/latest/config_options.html

> Use these keys from the TwidereX app: > > ``` > ConsumerKey=wmtrtTaVOjUnH5pWQp4LDI5Qs > ConsumerSecret=E9Q9u2yK0COJae2tLcNEdY75OPA3bxqJiGZQztraHaQUtoI2cu > ``` How exactly? Can you provide clarification, please?

> > > Use these keys from the TwidereX app: > > > ``` > > > ConsumerKey=wmtrtTaVOjUnH5pWQp4LDI5Qs > > > ConsumerSecret=E9Q9u2yK0COJae2tLcNEdY75OPA3bxqJiGZQztraHaQUtoI2cu > > > ``` > > > >...

There is also [distance correlation](https://en.wikipedia.org/wiki/Distance_correlation), but I never found it useful for my own work because it involves constructing a distance matrix that maxed-out RAM. Something to try if your...

Look here: [DataResponsibly/DataSynthesizer](https://github.com/DataResponsibly/DataSynthesizer). Specifically, the `lib` directory that contains a Python implementation of GreedyBayes and MI calculation from sklearn.