Mexico City Air Quality Prediction System

Citizens with accurate air quality forecasts and personalized health recommendations

🌍 Project Overview

This repository is part of the Omdena Local Chapter project "Air Quality Prediction and Personalized Health Recommendations for Mexico City." It contains all resources developed by our team for this initiative.

📌 Project Website: https://www.omdena.com/chapter-challenges/air-quality-prediction-and-personalized-health-recommendations-for-mexico-city

📂 Repository Structure:

• Official Guidelines and Documents: Guidelines provided by the Mexican government regarding the standards which was followed during the development
• Data Collection: Air quality data gathered from all monitoring stations, along with festivals and weather data.
• Data Analysis: Insights and trends derived from the collected data.
• Model Development: Training and fine-tuning model for forecasting major pollutants.
• Model Deployment: A Streamlit application that provides accurate 24-hour air quality forecasts, ensuring accessibility and actionable insights for all citizens. Our goal is to leverage data-driven approaches to enhance air quality awareness and provide personalized health recommendations for Mexico City.

🎯 Key Objectives

• Achieve 85% accuracy in 24-hour forecasts for major pollutants
• Serve 90% of Mexico City's neighbourhoods
• Support multiple languages (Spanish, English, and Indigenous languages)
• Meet WCAG 2.1 AA accessibility standards
• Handle real-time data from 30+ monitoring stations

🚀 Current Phase: Streamlit Deployment

We are currently focusing on building a user-friendly web interface using Streamlit. This phase includes:

• Basic dashboard setup
• Forecast display system
• User profile management
• Personalized recommendations
• Accessibility features
• Multi-language support

💻 Tech Stack

• Python 3.8+
• Streamlit
• Pandas
• NumPy
• Plotly/Matplotlib
• FastAPI (API integration)

🤝 How to Contribute

1. Fork the repository ()
2. Create a new branch (git checkout -b feature/AmazingFeature)
3. Commit your changes (git commit -m 'Add some AmazingFeature')
4. Push to the branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

Activating the Application (Locally)

This section details how any newbie Python user can debug or preview the Streamlit application from their local repository.

1. Ensure that you have set-up and are currently accessing a virtual environment in your local repo. You may refer to the Installation Steps listed above this.
2. From the Terminal, where the current working directory is the root folder, type streamlit run Main_dashboard/Main_landing_page_custom.py. This will initialize the Streamlit application locally.
3. To close the application fully, you may Press CTRL+C from the terminal to close the application.

Priority Areas for Contribution

• Streamlit component development
• Accessibility improvements
• Language localization
• Data visualization enhancements
• Performance optimization
• Documentation