Smart-Crop-Recommendation-System

Crop Recommendation system using Blended XGBoost and SVM machine learning models

Features

• Predicts the most suitable crop to grow based on soil and environmental conditions.
• Utilizes a hybrid approach combining XGBoost and SVM for accurate predictions.
• Easy-to-use interface for farmers and agricultural experts.

Installation

1. Clone the repository:

   git clone https://github.com/Akhil-peram/Smart-Crop-Recommendation-System.git

2. Navigate to the project directory:

   cd Smart-Crop-Recommendation-System

3. Install the required dependencies:

   pip install -r requirements.txt

Usage

1. Prepare your dataset with the required features (e.g., soil type, temperature, humidity).
2. Run the main script to get crop recommendations:

   python app.py

3. Follow the prompts to input your data and receive recommendations.

Dataset

The system uses a dataset containing information about soil conditions, weather parameters, and crop yields. Ensure your dataset is formatted correctly before use.

Starting the Project

After installing the requirements, click "Run". Then, at the bottom, click on the running local server.

This is our home page:

User Input

The user enters the Environmental details like Nitrogen, Phosphorous, Posttasium, pH of soil and submit.

Results of the crop recommendation

These will be results of the crop recommendation, we are recommendting top five crops that can be grown on that soil which have the specitic attributes.

Details of 22 Crops

We have scraped the data fron the official website, which consists details , how each crop can be grown , what are the fertilizers has to be used, what must be the soil fertility and duration of the crop.

Model Performance based on Accuracy and Sensitivity

Correlation Matrix for the Features

Performance of different models

NOTE: Use Pycharm for Running the Project , for better management of dependencies

Contributing

Contributions are welcome! Please fork the repository and submit a pull request with your changes.

License

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