Complete Free Track

  • ID: DS-L06X1
  • Type: Wrap-up
  • Audience: Public
  • Theme: Consolidation, reproducibility, and next steps

You have completed the Foundations Track of CDI Data Science Foundations in Python.

This guide is Quarto-first. Every chapter is written as a .qmd file and executed during rendering, so the figures and outputs you see are reproducible.

What You Built

Across Lessons 01–06, you built a complete, end-to-end workflow:

  • Set up a reproducible Python environment (.venv) and rendered a Quarto book
  • Loaded a dataset and saved it into a consistent project structure (data/)
  • Cleaned and validated the dataset (data/iris_clean.csv)
  • Performed core data wrangling operations (filter, group, reshape)
  • Created foundational visualizations and saved figures reproducibly
  • Produced summary statistics and wrote careful interpretations

Your Project Structure

Your repo is already organized like a real, reproducible data project:

  • index.qmd and chapter .qmd files define the book content
  • data/ contains datasets used by the lessons
  • figures/ stores saved plots created during rendering
  • cdi_viz/ contains reusable plotting and saving utilities
  • scripts/bash/ contains build and setup helpers
  • docs/ contains the rendered website (GitHub Pages output)

How to Rebuild Anytime

From the project root:

#| label: 06x1-build-book
bash scripts/bash/build.sh

After rendering, open the site:

#| label: 06x1-open-site-mac
open docs/index.html

If you are editing chapters and want live reload, you can use quarto preview. For a quick verification after a build, opening docs/index.html is usually sufficient.

What This Track Did Not Cover

This Foundations Track focused on the core workflow. It did not yet cover:

  • Feature engineering and transformation design
  • Train/test splitting and evaluation discipline
  • Supervised learning (classification and regression)
  • Model tuning, validation strategies, and leakage avoidance
  • End-to-end project packaging and deployment workflows

Those topics belong to the extended track.

Next Steps

Solidify your practice

Choose a new dataset (for example: housing, health, finance) and repeat Lessons 02–06.

Improve readability and reproducibility

Adopt a consistent style: - clear variable names - small, named code chunks - explicit validation checks before saving outputs

Continue into the extended track

If you want to move from foundations to applied projects, the extended track continues with:

  • deeper exploratory analysis
  • feature engineering
  • machine learning workflows
  • model evaluation and interpretation
  • end-to-end project structure and deployment

Summary

You now have a complete foundation workflow and a reproducible Quarto project that you can reuse for future datasets and future guides.