API → AI/ML Playground

Build something magical: connect an API, clean & visualise data, train a tiny model, and deploy it — step by colourful step.

🔗 API Integration in Detail

Tip: Drag to orbit. This shapeshifting torus-knot hints at tangled patterns models try to untie.

⚡ Training Loss by Epoch

Lower is better: the model is learning to make fewer mistakes.

🤖 Class Accuracy Snapshot

Which class needs more data or better features?

🧪 API → Clean → Visualise (Simulated)

// 1) Fetch data from an API (simulated here)
const rows = await fetch('/api').then(r => r.json())

// 2) Clean it
const clean = rows.map(r => ({ t: r.t, value: Number(r.value) }))

// 3) Visualise it with Chart.js
new Chart(ctx, { type: 'line', data: {...}, options: {...} })

This mimics the real flow you will build: fetch → clean → visualise → model.