Kia ora 👋

I’m Western, a software engineer moving from infrastructure/devops into machine learning.

Right now I’m completing Google’s Machine Learning Crash Course, focusing on:

• Supervised learning (linear & logistic regression)
• Model evaluation (loss, accuracy, precision, recall, AUC)
• Preparing data for ML (numerical & categorical features, feature engineering)
• Introductory neural networks and how ML systems run in production

The goal here is for me to blend my DevOps experience with Machine Learning to become an effective ML Ops Engineer of some description.

If you want to connect, I'm keen to yarn. You can find my contact details on my website: https://westernwilson.com

These repos will be where I apply MLCC concepts in Python:

• 📈 [Regression Playground – repo TBD]
  Implementing linear regression models on real datasets, experimenting with learning rate, regularisation, and feature engineering.

• ✅ [Binary Classification – repo TBD]
  Building and evaluating classifiers (e.g. logistic regression) using metrics like accuracy, precision, recall, and AUC.

• 🤖 [Neural Network Experiments – repo TBD]
  Simple feed-forward networks inspired by MLCC exercises, exploring activation functions and overfitting/regularisation.

• Languages: Python, Javascript, Bash (Some C# & Java)
• ML: Pandas, NumPy, scikit-learn, TensorFlow (from MLCC exercises)
• Infra: Docker, Kubernetes, AWS, GitHub Actions, Terraform, Vercel
• Front-end Javascript, React, Vue.js, Nuxt