L3-nny/Kenya-Constitution-Chatbot

This project is designed to simplify the retrieval of the content in the Constitution of Kenya through a user-friendly chatbot interface # Kenya Constitution Chatbot Project ## Overview The Kenya Constitution Analysis Project is a Jupyter Notebook-based application designed to extract, process, and analyze the text of the Kenya Constitution from a PDF file. This project leverages natural language processing (NLP) techniques to enable users to query specific sections of the constitution, making it a valuable tool for legal studies, civic education, and research. ## Features - **PDF Text Extraction**: Extracts text from specified pages of the Kenya Constitution PDF using `pdfplumber`. - **Text Processing**: Organizes the extracted text into structured chapters and sections for easy access. - **Natural Language Processing**: Utilizes `spaCy` for preprocessing user queries, including lemmatization and stopword removal. - **Question Answering System**: Allows users to ask questions related to specific sections of the constitution and receive relevant answers. - **Synonym Mapping**: Enhances query recognition by mapping synonyms to key terms in the constitution. ## Installation To run this project, you need to have Python installed on your machine. Follow these steps to set up the environment: 1. **Clone the repository**: ```bash git clone github.com cd kenya-constitution-analysis ``` 2. **Install the required libraries**: You can install the necessary libraries using pip. Run the following command: ```bash pip install spacy pdfplumber pyspellchecker ``` 3. **Download the spaCy model**: You will also need to download the English language model for spaCy: ```bash python -m spacy download en_core_web_sm ``` 4. **Add the Kenya Constitution PDF**: Place the Kenya Constitution PDF file in the project directory and update the file path in the notebook accordingly. ## Usage 1. Open the Jupyter Notebook in your preferred environment (e.g., Jupyter Lab, Jupyter Notebook). 2. Run the cells sequentially to extract and process the text from the Kenya Constit …