Skip to content

CSharpTeoMan911/WeatherPrediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

🌤️ WeatherPrediction

WebSite-ezgif com-video-to-gif-converter

Prediction-ezgif com-video-to-gif-converter

WeatherPrediction is a weather forecasting app powered by machine learning that predicts temperatures for Global and London locations. The app predicts the average temperature between the maximum and minimum values for a given day.

🌍 Global: Predicts the average global temperature for a specific date.

🏙️ London: Predicts the average temperature within London for the selected date.

You can access the app here: WeatherPrediction App

🤖 Machine Learning Model

Algorithm:

  • Multivariate Polynomial Regression
  • Global Model Accuracy: 90% (Error rate: 12%)
  • London Model Accuracy: 72% (Error rate: 26%)

Polynomial

For more details, check out the Jupyter Notebook GitHub Repository.

🛠️ Tech Stack

Weather prediction (1)

Frontend:

  • Languages: JavaScript, CSS, HTML
  • Frameworks: React, Bootstrap

Web Technologies:

  • Pyodide & WebAssembly - Allows running Python and ML libraries natively in the browser.

Machine Learning:

  • Python & Scikit-learn - Robust libraries for machine learning.


🔄 ML Model Integration

The machine learning model is integrated into the app using Pyodide (a Python interpreter for the browser) and WebAssembly. This combination allows the app to run the model with native capabilities directly in the browser.

The integration flow includes:

  1. Web-worker loads Pyodide and required Python libraries.
  2. The selected date is passed to either the Global or London temperature prediction model.
Flowchart

How it works:

  1. Web-worker: Communicates between the frontend and the ML backend.
  2. It processes:
  • Loading Pyodide
  • Passing the selected date for Global or London temperature predictions..
WeatherPredictionWebWorker

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published