Hello

I have 200k documents and I create 100 topics. I look at the terms and see that the topics are good.
But when I want to look at examples for each topic I do probs, _ = topic_model.transform(count_matrix, details=True). Then I create new column for each for example dataframe['topic=0']=pd.Series(probs[:, 0]). Then I sort dataframe by prob value decrease and I see that about 1/3 of the

We should probably have a more unified and robust method of logging and warning. Logbook is a particularly friendly way of doing this.

The readme file lacks installation instructions -- I think it would be very helpful to include that.

I was able to puzzle out that

$ python3 setup.py build
$ python3 setup.py install

are enough to build and install the package. Maybe that info, or something like it, could be in the readme.

Also, I found that after installing, import entropy_estimators fails, but `imp

Base is confusing, it conveys that it's the base of the logarithm. Something about alphabet size will be more direct.

The user facing side of the code talks about sources wherever the source random processes feeding information into are target are meant.

Inside some classes, the word "sources" is used to specify a single random variable, i.e. the combination of the index of a random process and a time lag.

This can be pretty confusing for newcomers trying to contribute.

List of various issues I found in the documentation of inform while developing the R wrapper (rinform):

• many time series measures point to a wiki page, Transfer Entropy lacks this link although there is a wiki page (https://en.wikipedia.org/wiki/Transfer_entropy)
• transfer entropy: "between an information source and destination" -> missing "a destination"
• transfer entropy: "int