Skip to content
/ HCMLE Public

A hands-on, block-based journey to becoming a Human-Centered Machine Learning Engineer — with clean code, real data, and practical insight.

Notifications You must be signed in to change notification settings

flyboi96/HCMLE

Repository files navigation

Python 3.11 Jupyter License: MIT

Human-Centered Machine Learning Engineer (HCMLE)

This is a curated, self-directed journey toward becoming a Human-Centered Machine Learning Engineer — a role at the intersection of data science, human factors, and responsible AI. The focus is on developing robust technical skills and human-centered intuition for building ML systems that are usable, interpretable, and ethically sound.

This repository is structured into focused learning "blocks," each with Jupyter notebooks, hands-on projects, and curated readings. The goal is to build deep technical understanding and the human-centered thinking needed to design useful, ethical, and interpretable ML systems.


Project Structure

Path Description
Block1/ Python fundamentals and environment setup
Block2/ Data manipulation with Pandas
block3_intro_to_ml/ Intro to Machine Learning: Regression & Classification
block4_human_ai/ Human-AI Interaction & Interpretability
block5_mini_project/ Mini ML Projects, Modeling, UX, Prototyping, Ethics
block6_intro_to_deep_learning/ Neural networks and deep learning fundamentals
block7_deep_learning_tabular_data/ Deep learning with tabular data and embedding models
block8_data_visualization/ Communicating ML insights through Python visualization and design
block9_human_centered_design/ Fundamentals of UX and human-centered design for ML solutions
block12_XAI/ Explainable AI techniques: SHAP, LIME, PDP
environment.yml Reproducible Conda environment
HCMLE.code-workspace VS Code workspace for auto-loading settings
README.md Project goals, learning blocks, and setup instructions
.gitignore Ignore notebooks, data, and system clutter

Blocks Overview

Block Focus Status
1 Python Fundamentals & Environment Setup Completed
2 Data Manipulation with Pandas Completed
3 Intro to Machine Learning: Regression & Classification Completed
4 Human-AI Interaction & Interpretability Completed
5 Mini ML Project Completed
6 Introduction to Deep Learning Completed
7 Deep Learning for NLP or Tabular Data Completed
8 Data Visualization & Communication Completed
9 Human-Centered Design Fundamentals In Progress
12 Explainable AI Techniques In Progress

Each block includes:

  • notebooks/ – clean and commented Jupyter notebooks
  • data/ – sample datasets (if applicable)
  • README.md – block-specific goals and progress
  • model_card.md – model transparency summary
  • project_schedule.md – daily task plan for hands-on blocks

Setup Instructions

To run this project locally with Jupyter + Conda + VS Code:

1. Clone the repository

git clone https://github.com/flyboi96/HCMLE.git
cd HCMLE

2. Create and activate the environment

Make sure you have Anaconda or Miniconda installed.

conda env create -f environment.yml
conda activate hcmle-env

3. Open in VS Code

To launch the project with the correct kernel, folders, and settings:

code HCMLE.code-workspace

Make sure you have the Python and Jupyter extensions installed in VS Code.

4. Optional: Clean and update the environment

If you add new packages:

conda env update -f environment.yml --prune

To export your environment:

conda env export --from-history > environment.yml

Progress Tracking

I’m using a GitHub Project Board and Issues to track tasks and milestones for each block. This keeps everything visible, organized, and reviewable over time.


Tools Used

  • Python 3.11
  • Pandas, NumPy, Matplotlib, Seaborn
  • scikit-learn
  • JupyterLab & VS Code Notebooks
  • Git, GitHub, Conda
  • Markdown, GitHub Project Boards

Sample Resources

  • Python Data Science Handbook by Jake VanderPlas
  • Designing with the Mind in Mind by Jeff Johnson
  • Real-world datasets (e.g., Titanic, Iris, UCI ML Repository)
  • People + AI Guidebook by Google PAIR
  • Storytelling with Data by Cole Nussbaumer Knaflic
  • Interpretable Machine Learning by Christoph Molnar
  • Kaggle & DataCamp tutorials on Explainability (LIME, SHAP)

License

This project is open-source under the MIT License. Feel free to fork, adapt, or use this project as inspiration for your own ML learning journey.