Skip to content

pathananas2007/Ai-rainfall-prediction-platform

Repository files navigation

RainAI - AI-Powered Rainfall Prediction SaaS

A production-ready AI-powered full-stack SaaS platform for rainfall prediction, analytics, and weather intelligence using Machine Learning.


Features

  • Premium AI SaaS UI with Tailwind CSS
  • JWT Authentication System
  • Rainfall Prediction using Machine Learning
  • Interactive Analytics Dashboard
  • Prediction History Tracking
  • MongoDB Integration
  • Protected Routes
  • Responsive Dashboard
  • Confidence Score Visualization
  • Real-time Prediction Insights
  • AI-powered Weather Analytics
  • Modern Glassmorphism UI
  • Animated Dashboard Components
  • Secure REST API Architecture
  • Machine Learning Model Integration
  • Responsive Mobile-Friendly Design

Tech Stack

Frontend

  • React.js
  • Vite
  • Tailwind CSS
  • Framer Motion
  • Recharts
  • Lucide React
  • Axios
  • React Router DOM

Backend

  • Flask
  • Flask JWT Extended
  • Flask CORS
  • MongoDB
  • Bcrypt

Machine Learning

  • Scikit-learn
  • Random Forest
  • Pandas
  • NumPy
  • Joblib

Project Structure

RainAI/
│
├── backend/
│   ├── app.py
│   ├── requirements.txt
│   ├── database/
│   │   ├── db.py
│   │   └── seed.py
│   │
│   ├── ml/
│   │   ├── train_model.py
│   │   ├── rainfall_model.pkl
│   │   ├── scaler.pkl
│   │   └── feature_columns.pkl
│   │
│   ├── routes/
│   │   ├── auth_routes.py
│   │   ├── predict_routes.py
│   │   └── analytics_routes.py
│   │
│   └── services/
│       ├── auth_service.py
│       ├── predict_service.py
│       └── analytics_service.py
│
├── frontend/
│   ├── public/
│   ├── src/
│   │   ├── assets/
│   │   ├── components/
│   │   ├── context/
│   │   ├── pages/
│   │   ├── services/
│   │   ├── App.jsx
│   │   └── main.jsx
│   │
│   ├── package.json
│   ├── vite.config.js
│   └── tailwind.config.js
│
├── data/
│   ├── data final.csv
│   └── final 2.ipynb
│
└── README.md

About

End-to-end Rainfall Prediction pipeline using Python. Implements data cleaning, feature engineering (Season), preprocessing, and multiple ML models (Random Forest, XGBoost, SVM, KNN, Logistic Regression, Gradient Boosting) with hyperparameter tuning, evaluation, and model comparison.

Topics

Resources

License

Stars

Watchers

Forks

Contributors