🌾 Smart Crop Prediction

An end-to-end AgroTech Machine Learning application that recommends the optimal crop to plant based on soil and environmental conditions.

---

📖 About the Project

Making the right crop choice is crucial for farmers to maximize yield and optimize resource usage. Smart Crop Prediction addresses this challenge by leveraging machine learning to analyze soil nutrients and environmental factors, providing data-driven recommendations for the best crop to plant.

🎯 Problem Solved

Traditional crop selection often relies on intuition or outdated practices, leading to suboptimal harvests and resource waste. This application empowers farmers and agricultural professionals with:

• Instant predictions based on soil composition (N, P, K levels)
• Environmental analysis considering temperature, humidity, and rainfall
• Scientific backing through a trained ML model with 99.32% accuracy

🤖 Machine Learning Model

• Algorithm: Random Forest Classifier (100 estimators)
• Training Data: 2,200 samples across 22 different crop types
• Features: Nitrogen (N), Phosphorus (P), Potassium (K), Temperature, Humidity, pH, Rainfall
• Accuracy: 99.32% on test set

---

📸 Screenshots

Initial Form	Prediction Result

---

🛠️ Tech Stack

Layer	Technology
Frontend	Next.js 16, React 19, Tailwind CSS 4, Axios
Backend	FastAPI, Python 3.11+, Uvicorn
Machine Learning	Scikit-Learn, Pandas, NumPy, Joblib
DevOps	Docker, Docker Compose
Data Visualization	Matplotlib, Seaborn (Jupyter Notebooks)

---

🚀 How to Run

Option A: Docker (Recommended) 🐳

The easiest way to get started. Just make sure you have Docker installed.

# Clone the repository
git clone https://github.com/cauegrassi7/smart-crop-prediction.git
cd smart-crop-prediction

# Build and run with Docker Compose
docker-compose up --build

Once running:

• 🌐 Frontend: http://localhost:3000
• ⚡ Backend API: http://localhost:8000
• 📚 API Docs: http://localhost:8000/docs

---

Option B: Manual Setup 🔧

1. Backend Setup

# Navigate to backend directory
cd backend

# Create virtual environment
python -m venv venv

# Activate virtual environment
# On macOS/Linux:
source venv/bin/activate
# On Windows:
# venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

2. Train the Model (Optional)

The model is pre-trained and included in the repository. If you want to retrain it:

# From the backend directory
python train_model.py

This will generate the crop_prediction_model.pkl file in the models/ folder.

3. Start the Backend Server

# From the backend directory
uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

4. Frontend Setup

Open a new terminal:

# Navigate to frontend directory
cd frontend

# Install dependencies
npm install

# Start development server
npm run dev

---

📁 Project Structure

smart-crop-prediction/
│
├── 📂 backend/                    # FastAPI Backend
│   ├── app/
│   │   ├── __init__.py
│   │   ├── main.py               # API routes & FastAPI app
│   │   └── schemas.py            # Pydantic data models
│   ├── models/
│   │   └── crop_prediction_model.pkl  # Trained ML model
│   ├── train_model.py            # Model training script
│   ├── requirements.txt          # Python dependencies
│   └── Dockerfile
│
├── 📂 frontend/                   # Next.js Frontend
│   ├── app/
│   │   ├── page.tsx              # Main application page
│   │   ├── layout.tsx            # Root layout
│   │   └── globals.css           # Global styles
│   ├── public/                   # Static assets
│   ├── package.json
│   └── Dockerfile
│
├── 📂 data/                       # Dataset
│   └── Crop_recommendation.csv   # Training data (2,200 samples)
│
├── 📂 notebooks/                  # Jupyter Notebooks
│   └── 01_model_training.ipynb   # EDA & model development
│
├── docker-compose.yml            # Multi-container orchestration
└── README.md

---

📡 API Documentation

The API documentation is automatically generated and available via Swagger UI when the backend is running:

🔗 http://localhost:8000/docs

Main Endpoints

Method	Endpoint	Description
GET	/	Health check & welcome message
GET	/health	Health check for Docker/K8s
POST	/predict	Get crop recommendation

Example Request

curl -X POST "http://localhost:8000/predict" \
  -H "Content-Type: application/json" \
  -d '{
    "N": 90,
    "P": 42,
    "K": 43,
    "temperature": 20.8,
    "humidity": 82.0,
    "ph": 6.5,
    "rainfall": 202.9
  }'

Example Response

{
  "input": {
    "N": 90.0,
    "P": 42.0,
    "K": 43.0,
    "temperature": 20.8,
    "humidity": 82.0,
    "ph": 6.5,
    "rainfall": 202.9
  },
  "recommended_crop": "rice"
}

---

🌱 Input Features

Feature	Description	Unit
N	Nitrogen content in soil	kg/ha
P	Phosphorus content in soil	kg/ha
K	Potassium content in soil	kg/ha
Temperature	Average temperature	°C
Humidity	Relative humidity	%
pH	Soil pH level	0-14
Rainfall	Annual rainfall	mm

---

🌾 Supported Crops

The model can predict among 22 different crop types, including:

Rice, Wheat, Maize, Chickpea, Kidney Beans, Pigeon Peas, Moth Beans, Mung Bean, Black Gram, Lentil, Pomegranate, Banana, Mango, Grapes, Watermelon, Muskmelon, Apple, Orange, Papaya, Coconut, Cotton, Jute, Coffee

---

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

---

🤝 Contributing

Contributions are welcome! Feel free to open issues or submit pull requests.

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 sustainable agriculture