Update Case Studies NBs for BCM

[AlexAndorra]

Updates NBs for the Case Studies folder of BCM, as discussed in #36
This (painful) PR is now ready for review 🍾

[review-notebook-app]

Check out this pull request on 

You'll be able to see Jupyter notebook diff and discuss changes. Powered by ReviewNB.

[AlexAndorra]

@junpenglao and @aloctavodia I can't update SignalDetectionTheory.ipynb yet because it uses heit_rotello.RData and I don't have R on my laptop.
If one of you has R installed, can you convert this R file into .csv or .txt please ? I think it's the good thing to do to make this port even more usable.
Thanks in advance, and tell me if you have any questions!

[canyon289]

Yep, I'll do it by tonight max(16 hours)

…

On Tue, Apr 28, 2020 at 5:44 AM Alexandre ANDORRA ***@***.***> wrote: @junpenglao and @aloctavodia I can't update SignalDetectionTheory.ipynb yet because it uses heit_rotello.RData and I don't have R on my laptop. If one of you has R installed, can you convert this R file into .csv or .txt please ? I think it's the good thing to do to make this port even more usable. Thanks in advance, and tell me if you have any questions! — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub, or unsubscribe.

[canyon289]

I realized I misread the comment and you weren't asking me but I'll do so anyway :D

If you're feeling like you want a challenge you could spin up an R docker container and do it yourself ;) But otherwise can you add a link to the .r file and I'll do it on my computer

[AlexAndorra]

Ooh you're right, that could be fun! Let me try to do that then and I'll keep you posted 😉

[canyon289]

The arviz docker container file in ./scripts has all the commands you need! you can either mount your local file system or copy a file to and from the running container. Mounting is easier imo but do what you like!

[AlexAndorra]

@canyon289 I managed to build and lauch an R Docker container (after some head scratching TBH), but I'm running into an issue when trying to load the file:

> load("/heit_rotello.RData")
Error in load("/heit_rotello.RData") :
  bad restore file magic number (file may be corrupted) -- no data loaded
In addition: Warning message:
file ‘heit_rotello.RData’ has magic number '"cond'
  Use of save versions prior to 2 is deprecated

After Googling, it seems to mean that the file was not saved properly. Unfortunately, I don't know the book, the data and R enough to solve that in a reasonable amount of time. So it'd be great if you or someone else could convert this R file into .csv or .txt 🙏
I'll be happy to update the NB afterwards. Thanks a lot!

PS: Note for the future: always save the files to universal file formats

[aloctavodia]

@AlexAndorra I will send you the data in CSV format

[AlexAndorra]

Thanks for the files Osvaldo! They are now updated.
Trying to update the SignalDetectionTheory NB though, I got a super weird error in the terminal: libc++abi.dylib: terminating with uncaught exception of type std::runtime_error: Couldn't close file -- this appears when sampling a PyMC model and makes sampling hanging indefinitely around 75%.
If someone knows what this is about and / or can run the NB without issue I'm all ears!
PyMCheers 🖖

[AlexAndorra]

I suggest merging this next week -- potential fixes can go on subsequent PRs.