This repository is a personal learning and experimentation space designed to explore machine learning concepts through hands-on coding. The goal is simple: build, test, and better understand how different models behave by working directly with them.
Overview This project contains pre-built machine learning examples that are meant to be easy to run, modify, and experiment with. Each model walks through a full pipeline—from loading data to training, predicting, and evaluating results—so you can see how everything connects in practice.
What’s Included:
- Ready to run and/or modify python scripts
- Accuracy scores
- Precision, recall, and F1-score
- Confusion matrices (visualized)
- Feature importance plots
- Loss curves (neural networks)
- Decision boundaries
- && MORE!
Setup: Run the following before using the code:
pip install -r requirements.txt
Important Notes:
- You must upload or include the requirements.txt file within your working environment or repository before running any scripts.
- Any required CSV datasets must also be uploaded into your working directory or correctly referenced in the code. Ensure file paths match your local or notebook environment.
- Some libraries, such as TensorFlow, may fail to install depending on your Python version.
Environment Recommended: Jupyter Notebook / JupyterLab
Purpose This repo is for learning, experimenting, and building intuition—not production use.
Final Note The best way to learn machine learning is to tinker with it.
– Taylor