ML based Pairs Selection

[AaronDeb]

Description

Implementation in this module are based on the book by Simão Moraes Sarmento and Nuno Horta "A Machine Learning based Pairs Trading Investment Strategy".

Type of Change

• New feature (non-breaking change which adds functionality)
• This change requires a documentation update

How Has This Been Tested?

This unit test file was created to test the added functions:

• test_pairs_selector.py
• test_data_importer.py
• test_indexed_highlight.py

Test Configuration:

• Ubuntu 18.04
• Text Editor

Checklist:

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes
• Any dependent changes have been merged and published in downstream modules

[PanPip]

Added comments to the code part. Quite a lot of code you've added here 🙂

Now will go over the unit tests and the sphinx docs.

[PanPip]

Great documentation! 👍

Will cover a few ways how it can be improvd over the call.

[PanPip]

Great implementation! 👍

Left a few comments on the code. Will check the documentation now.

[PanPip]

Good docs 🙂

Please split lines in sphinx docs so they are not more than 120-160 characters.

I might add more comments once I go over the Research notebook and use cases.

[PanPip]

Great work! Thank you for fixing previous comments 👍

After a few minor adjustments will approve this PR.

[PanPip]

Thank you for adjusting the code! Approving this PR. 🙂

Ready for review @Jackal08.

[PanPip]

Just thought that we might want to add a quick note to the docs that the pair selection step might take some time to calculate.

[Jackal08]

Just a few comments that need correction and then I will approve. Excellent work with this. Very happy.

Also:

You get the following 2 deprecation warnings:

The pprint_val function was deprecated in Matplotlib 3.1 and will be removed in 3.3.
  return formatter.pprint_val(x)

The line2d_seg_dist function was deprecated in Matplotlib 3.1 and will be removed in 3.3.
  i, (p0, p1) in enumerate(edges)]

Can we please fix this?

[Jackal08]

Approved. @PanPip, please merge and delete branch.