A machine learning-based crop prediction system that helps farmers make informed decisions about crop selection. The model uses Deep Neural Networks (DNNs) trained on historical crop and weather data to predict the most suitable crop based on soil conditions, location, and seasonal factors.

🎯 Accuracy: 99% on both training and test data!

• 🧪 Soil Analysis - Considers N, P, K, and pH content of the soil
• 🌡️ Weather Integration - Fetches real-time temperature and humidity via API
• 🌧️ Rainfall Prediction - Uses historical rainfall data by region
• 📍 Location-Based - State and district-specific recommendations
• 🖥️ User-Friendly Interface - Interactive web interface for easy input
• ⚡ Fast API Backend - Quick and reliable predictions

The prediction model uses a Deep Neural Network with:

Input Layer (7 features) 
    ↓
Hidden Layer 1 (64 neurons, SeLU activation)
    ↓
Hidden Layer 2 (128 neurons, SeLU activation)
    ↓
Hidden Layer 3 (64 neurons, SeLU activation)
    ↓
Output Layer (22 neurons, Softmax activation)

1. Nitrogen (N) - Soil nitrogen content
2. Phosphorus (P) - Soil phosphorus content
3. Potassium (K) - Soil potassium content
4. pH - Soil pH level
5. Temperature - Regional temperature
6. Humidity - Regional humidity
7. Rainfall - Expected rainfall

Pairwise Correlation Plots	Correlation Matrix

• Python 3.8+
• pip

1. Clone the repository

   git clone https://github.com/yourusername/crop_prediction.git
   cd crop_prediction/crp-main

2. Create virtual environment (recommended)

   python -m venv venv
   source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install dependencies

   pip install -r requirements.txt

4. Run the application

   uvicorn main:app --reload

5. Open the interface

   • Navigate to http://localhost:8000
   • Or open index.html in your browser

Request Body:

{
  "nitrogen": 90,
  "phosphorous": 42,
  "potassium": 43,
  "ph": 6.5,
  "state": "Karnataka",
  "district": "Bangalore",
  "month": "June"
}

Response:

{
  "result": "rice"
}

crop_prediction/
├── crp-main/
│   ├── data/               # Dataset files
│   ├── model/              # Trained models and architecture
│   │   ├── net.py          # Neural network definition
│   │   └── *.hdf5          # Saved model weights
│   ├── utils/              # Utility functions
│   │   ├── pred_crop.py    # Crop prediction logic
│   │   ├── pred_rainfall.py # Rainfall data fetching
│   │   └── pred_temp_hum.py # Temperature & humidity API
│   ├── main.py             # FastAPI application
│   ├── index.html          # Web interface
│   ├── index.js            # Frontend logic
│   ├── style.css           # Styling
│   ├── requirements.txt    # Python dependencies
│   └── *.ipynb             # Jupyter notebooks for analysis
└── README.md

• Crop Recommendation Dataset - 2200 samples of 22 crops
• Rainfall in India - Historical rainfall data

Contributions are welcome! Please feel free to submit a Pull Request.

1. Fork the repository
2. Create your feature 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

Made with ❤️ for farmers