Fixed #203 Added Shapelet Discovery Tutorial

[Attol8]

Shapelet Discovery and Classifier Tutorial

Hi @seanlaw, I have modified a notebook in /docs containing an existing tutorial on how to discover shapelets through the MP using STUMPY. I have followed the guidelines that you mentioned to me in issue #85. However, this notebooks solves issue #203. I have started reproducing the paper from this already existing solution as it contained some useful starting code.

The new notebook implements:

• Successfully reproduced code and results from The Matrix Profile Top Ten paper, particularly regarding section 3.7 "Shapelet discovery".
• Added comments, codes, plots, explanations and citations to make everything clearer. I tried to go into the details while keeping things simple
• As an extra, in the last section of the notebook, I implement a shapelet classification model that beats the results of the paper by 2%

Let me know how you want to proceed with this. When I have a bit of time I will start implementing other sections of the paper. 😃

Pull Request Checklist

Below is a simple checklist but please do not hesitate to ask for assistance!

• Fork, clone, and checkout the newest version of the code
• Create a new branch
• Make necessary code changes
• Install black (i.e., python -m pip install black or conda install black)
• Install flake8 (i.e., python -m pip install flake8 or conda install flake8)
• Install pytest-cov (i.e., python -m pip install pytest-cov or conda install pytest-cov)
• Run black . in the root stumpy directory
• Run flake8 . in the root stumpy directory
• Run ./setup.sh && ./test.sh in the root stumpy directory
• Reference a Github issue (and create one if one doesn't already exist)

[review-notebook-app]

Check out this pull request on 

Review Jupyter notebook visual diffs & provide feedback on notebooks.

---

Powered by ReviewNB

[seanlaw]

@Attol8 Thank you for this wonderful contribution!! I really appreciate that you've taken the time to follow the look/feel of the other existing tutorials and I think the level of information density is great. I love how you've added the sklearn section too. It all feels very thoughtfully executed :)

I've only read through it quickly but, overall, I think this is ready to be merged. There are some typos and some other minor things that I'd like to add but let that be my problem now. I am more than happy with what you've done! Thank you again and I am already looking forward to your future PR contributions!

P.S. Do you happen to have a Twitter handle? I'd like to acknowledge your contribution during our next release

[Attol8]

@seanlaw No problem! happy to contribute. Of course, if you see typos or would like to change the style of my comments to be adapted to the docs, feel free to do so.

My twitter handle is @JacopoAttolini, I don't use Twitter that much but please do mention me in your tweets, that's very kind of you 😃

[seanlaw]

Awesome! Will do