docs: Update README to surface ML/data-science concepts

[Copilot]

The README only described setup steps with no context on the underlying data-science patterns the project demonstrates.

Changes

• New "Machine Learning / Data Science Concepts" section — table mapping each concept to its concrete location in the codebase:

  • ETL Pipeline (Read → Map → Write class separation)
  • Data Cleaning / Pre-processing (stripping $/,, casting to float)
  • Categorical Feature Mapping / Label Encoding (mapper.map_data() merging raw Amazon categories via categories.csv lookup)
  • Feature Engineering (deriving month from Order Date for time-series aggregation)
  • Data Aggregation (groupby/sum, pivot_table)
  • Pandas DataFrame API as the ML-ecosystem backbone

• Prerequisites — inlined the categories.csv schema example (was previously buried in data/lookup/readme.md)

• Output section — lists and describes the three generated CSV files (orders_by_monthly_spend, orders_by_category, orders_by_parent_category)

---

🔒 GitHub Advanced Security automatically protects Copilot coding agent pull requests. You can protect all pull requests by enabling Advanced Security for your repositories. Learn more about Advanced Security.