The Justice Prediction System is an Machine Learning application which uses scikit-learn to predict the potential outcome in legal cases based on a dataset sourced from Kaggle. The model takes three inputs: the first party, the second party, and the case description, to forecast the possible winner of the case. The web interface, powered by Streamlit, offers an interactive and user-friendly experience.
The dataset used for training the model can be found on Kaggle. You can access it here.
The pre-trained machine learning model can be downloaded from the following link: Trained Model.
Ensure you have the following dependencies installed:
- Python (>=3.6)
- scikit-learn
- streamlit
- pandas
- numpy
You can install the required Python packages using the following command:
pip install -r requirements.txt
To run the Justice Prediction System, follow these steps:
- Open the provided Colab file
Model_training_and_testing.ipynb
in Google Colab. - Navigate to the "Web Interface for ML Model" section.
- Execute the cells in that section to load the pre-trained model and set up the Streamlit web application.
- Once the setup is complete, run the Streamlit application cells to launch the web interface.
- Upon launching the web application, you will be presented with an intuitive interface.
- Input the first party, second party, and case description for the legal case to be predicted.
- Click the "Predict" button to obtain the prediction result.
- Explore additional functionalities and visualizations available in the application.
This project is licensed under the MIT License - see the LICENSE file for details.
- The Justice Prediction System utilizes scikit-learn, Streamlit, pandas, and numpy.
- Special thanks to the open-source community for their contributions to the development of the libraries used in this project.