Jesse Raffa

Couple of comments: 1) Percentages: Seems like within a (row) variable the column percentages add up to 100%. This is fine, but may not be the desired result. I wonder...

So, what I was think of was `explainr`. https://github.com/hilaryparker/explainr ``` ptest

I think it still think it needs a little work. I posted a couple reproducible examples in the PR where the functionality I think needs to be tweaked.

You mean like this? 

I think the histograms are represented as text: ▇▅▃▅▇ Seems to be unicode characters: https://www.i2symbol.com/symbols/blocks/x2587-lower-seven-eighths-block-symbol-blocks-symbol-smiley-face

Thanks for the idea and the PR. A couple suggestions: using the `README.md` example: ``` import pandas as pd data=load_dataset('pn2012') columns = ['Age', 'SysABP', 'Height', 'Weight', 'ICU', 'death'] categorical =...

I think the type of equipment is likely not going to be available, because it varies across hospitals. The methods are going to vary depending on where you are pulling...

hi @mtwayne Unfortunately we don't have the procedure codes in eICU-CRD.

I think what you've inferred is likely the case. 90% of the rows in that table/field are non-null, which make it quite probably that it is done by pulse oximeter.

I think it would depend on the hospital and the situation, but is likely recorded at hospital admission. e.g., An unresponsive patient is not able to self-report. It's unlikely that...