ARMA demo

[albertpod]

This PR adds a new demo on the Bayesian treatment of the ARMA model.

[review-notebook-app[bot]]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[codecov-commenter]

Codecov Report

Base: 80.12% // Head: 80.21% // Increases project coverage by +0.08% :tada:

Coverage data is based on head (dc5549e) compared to base (a7cb2ce). Patch has no changes to coverable lines.

Additional details and impacted files

```diff @@ Coverage Diff @@ ## main #33 +/- ## ========================================== + Coverage 80.12% 80.21% +0.08% ========================================== Files 10 10 Lines 1107 1122 +15 ========================================== + Hits 887 900 +13 - Misses 220 222 +2 ``` | [Impacted Files](https://codecov.io/gh/biaslab/RxInfer.jl/pull/33?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=biaslab) | Coverage Δ | | |---|---|---| | [src/graphppl.jl](https://codecov.io/gh/biaslab/RxInfer.jl/pull/33/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=biaslab#diff-c3JjL2dyYXBocHBsLmps) | `87.00% <0.00%> (-0.50%)` | :arrow_down: | | [src/model.jl](https://codecov.io/gh/biaslab/RxInfer.jl/pull/33/diff?src=pr&el=tree&utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=biaslab#diff-c3JjL21vZGVsLmps) | `86.47% <0.00%> (+0.75%)` | :arrow_up: | Help us with your feedback. Take ten seconds to tell us [how you rate us](https://about.codecov.io/nps?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=biaslab). Have a feature suggestion? [Share it here.](https://app.codecov.io/gh/feedback/?utm_medium=referral&utm_source=github&utm_content=comment&utm_campaign=pr+comments&utm_term=biaslab)

:umbrella: View full report at Codecov.
:loudspeaker: Do you have feedback about the report comment? Let us know in this issue.

[bvdmitri]

Thanks @albertpod for the new demo! There a couple of missing parts in this PR though. Currently your demo is not compatible with our examples pipeline: read documentation here.

Important points:

• You need to modify and add your example to the .meta.jl file in the examples/ folder (also read comments in this file).
• The jupyter to markdown converter does not work well with Latex, so equations must be in a special form (read comments in the file or in the documentation)
• Add a little bit of text after Load dataset and before the inference, it looks like you do the inference procedure in the Load dataset section.
• Add a little bit of text after the inference with the results analysis (are they bad/good, expected or not).
• Minor, but could you please use @meta instead of where { meta = ... }
• Set (or remove) showprogress = false, the CI pipeline runs once and it looks like RxInfer is very slow, but its actually Julia's compilation time
• To check if your example compiles run make examples specific=ARMA (specific=<Part of the title>)

[bvdmitri]

The demo is working now. Thanks @albertpod, I want to tag a new release with 3 new demos, so I'll merge your PR now. If you think it needs further improvements please open a new PR. Thanks!