A Little Halloween Magic for Any Website

Ajiboye Toluwalase — Sun, 01 Nov 2026 21:45:41 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine

Every October, the internet fills with spooky colors, glowing pumpkins, and tiny bats flying across the screen. I wanted to bring some of that seasonal fun to the websites people already use—not by rebuilding them, but by giving them a temporary Halloween makeover.

That idea became the Halloween Website Decorator: a small web app that takes a public website or uploaded HTML files and turns them into an isolated, Halloween-themed preview.

What I Built

The app accepts either a public URL or a website upload. For uploads, you can provide one HTML file with optional CSS and images, or a ZIP containing those files. It then prepares a static copy, chooses a theme, adds decorations, and opens the result beside an original-page view.

The design is intentionally a collaboration between code and AI:

The AI can suggest decoration placements, an accent color, and optional CSS flourishes.
The app checks those suggestions against its theme, placement, and intensity rules.
A CSS allowlist sanitizer filters model-generated styles before they reach the preview.
If an AI response is unavailable or unusable, the app tries a configured fallback provider, then its built-in sample provider, and finally a code-only design.

The result is meant to feel like a seasonal mode—not a claim that every website can be copied perfectly. Static HTML works best; JavaScript is removed for safety, and sites that require login or client-side rendering may not display completely.

Demo

Try the live demo at halloween-decor.onrender.com. You can also run the app locally with the built-in provider, which works without API credentials:

python -m venv halloween_env
.\halloween_env\Scripts\Activate.ps1
python -m pip install -r requirements.txt
Copy-Item .env.example .env
python run.py

Then open http://127.0.0.1:5000. The demo helper pre-warms three sample pages before starting the server:

python scripts\demo.py

Code

The source is organized around a few focused pieces:

app/parser.py reads and validates the design response.
app/pipeline.py coordinates provider calls, retries, fallback, and CSS sanitization.
app/content/themes.py and app/content/decor/ hold the curated themes and individual SVG decorations.
app/steps/assemble.py places decorations into the prepared page.
app/__init__.py provides the Flask routes, bounded background jobs, cache, and request limits.

The project also includes a fixture matrix that checks five sample pages across all three intensity levels:

python scripts\matrix.py --provider fake

How I Built It

I built the app in milestones, starting with a working upload-and-preview flow and adding themes, decorations, and reliability features as the project grew.

The model does not generate HTML. Instead, it returns a small line-based design description, such as a theme choice and a few allowed decoration slots. Keeping markup and SVG assets hand-authored makes the output easier to validate and keeps the model focused on visual decisions.

The provider interface supports OpenAI-compatible chat-completion APIs. That makes it possible to configure different compatible services without changing the app’s design pipeline. A primary provider can be followed by a secondary LLM; a deterministic sample provider and code-only design are available as further fallbacks. API credentials are configured server-side or supplied transiently for a request, rather than being saved in job results.

For reliability, the app also has bounded background jobs, visible progress and errors, request limits, result caching, and a regeneration option. The fixture matrix exercises output preservation, decoration budgets, CSS filtering, and preview security headers. The test suite currently covers the parser, uploads, provider behavior, and app routes.

Why Does Open Innovation Matter?

For this project, open innovation means being able to experiment with different compatible models and providers while keeping the rest of the application stable. The provider can change; the design format, validation rules, curated decorations, and preview assembly remain under the project’s control.

That separation also makes failure less dramatic. If a provider is down or returns a response the app cannot use, the user can still get a themed preview from the sample or code-only design. The app does not need to trust a model with arbitrary page markup to make something fun.

The Spirit of It

The goal is small and cheerful: let someone take a page they know and see it wearing a Halloween costume. Maybe a familiar article gets a tiny moon in the corner, a pumpkin between sections, and a warmer palette—without losing the words that made the page theirs.

It’s a playful way to make the web feel seasonal, one little decoration at a time.

Built a Hospital Lenght Of Stay Predictor Web app

Ajiboye Toluwalase — Sun, 15 Feb 2026 07:51:55 +0000

Introduction

Heya, i built a Hospital lenght of stay predictor web app in which the user selects the conditions of his or her predicament in the hospital and the model predicts how long they stay at the hospital.

its a full-stack machine learning web application that predicts patient hospital stay duration using XGBoost. Features interactive map-based hospital selection across New York State, a 13-feature clinical assessment form, and real-time predictions with risk factor analysis. Built with Flask, JavaScript, Leaflet.js, and deployed on Render.

Overview

This predictor dashboard was built using the Hospital Inpatient Discharges (SPARCS De-Identified) 2017 dataset released by the New York State Department of Health. The platform addresses a real-world scenario: when patients or their relatives visit hospitals, they can predict the expected length of stay based on clinical, demographic, and facility factors.

Why This Matters

For Patients & Families: Plan work leave, childcare, and financial arrangements
For Hospitals: Optimize bed management and discharge planning
For Healthcare Administrators: Resource allocation and capacity forecasting
For Researchers: Explore social determinants of health and disparities in care

Demo

Here is a live demo on web app on Render

Check out the Github Repo here pls comment,star and fork

metrosmash / Hospital_LOS_Predictor

A full-stack machine learning web application that predicts patient hospital stay duration using XGBoost. Features interactive map-based hospital selection across New York State, a 13-feature clinical assessment form, and real-time predictions with risk factor analysis. Built with Flask, JavaScript, Leaflet.js, and deployed on Render

🏥 Hospital Length of Stay Predictor

An interactive web-based healthcare analytics platform that predicts hospital Length of Stay (LOS) using machine learning. Built with real-world data from 2.3+ million hospital discharges across New York State, this tool helps patients, families, and healthcare administrators make informed decisions about hospital admissions.

📋 Overview

This predictor dashboard was built using the Hospital Inpatient Discharges (SPARCS De-Identified) 2017 dataset released by the New York State Department of Health. The platform addresses a real-world scenario: when patients or their relatives visit hospitals, they can predict the expected length of stay based on clinical, demographic, and facility factors.

Why This Matters

For Patients & Families: Plan work leave, childcare, and financial arrangements
For Hospitals: Optimize bed management and discharge planning
For Healthcare Administrators: Resource allocation and capacity forecasting
For Researchers: Explore social determinants of health and disparities in care

✨ Features

🗺️

…

View on GitHub

*Thank you for your time *

DEV Community: Ajiboye Toluwalase

A Little Halloween Magic for Any Website

What I Built

Demo

Code

How I Built It

Why Does Open Innovation Matter?

The Spirit of It

Built a Hospital Lenght Of Stay Predictor Web app

Introduction

Overview

Why This Matters

Demo

metrosmash / Hospital_LOS_Predictor

🏥 Hospital Length of Stay Predictor

📋 Overview

Why This Matters

✨ Features

🗺️