Add in 2021 Weeks 1-8 location tracking data

[Sam-v6]

What does this PR do?

Brings in 2021, Weeks 1-8 location tracking data, expanding training sample up to about 1 million

What are some specific details on the changes?

• Brings in new training data
  • Converted data to parquet, stored in git LFS
  • Updated various data cleaning, engineering, etc functions to include new data based a few different columns names and season
  • Re-trained model with new data, new split is 92% training and 8% validation
• Moved the processing of predictions into a proper py file (from a notebook) and now making confusion matrix
• Updated CI to include processing of predictions with generation of artifacts
• Updated README with new details on additional script and extra 2021 data

How has this been tested?

Current CI covers changes to existing code, expanded CI to include post processing of predictions

Important Notes

Required model tuning to bring in precision of man identification as shown it's not great in classification report

Checklist

• [ X ] Tests have been added or updated to cover the changes.
• [ X ] Documentation has been updated (if necessary)

[Sam-v6]

@codex review this PR

[chatgpt-codex-connector]

To use Codex here, create a Codex account and connect to github.