---
title: LLM Tutor
emoji: 👨‍🎓
colorFrom: indigo
colorTo: indigo
sdk: streamlit
sdk_version: 1.41.1
app_file: 2Tutor.py
pinned: false
license: mit
short_description: Learn ML/LLM
---

# Data Science Tutor

## Overview

The **Data Science Tutor** application is designed to guide users through the CRISP-DM process for data science projects. Each section in the sidebar highlights a different step in the process, providing structured lessons, best practices, and hands-on examples. The application also includes an AI-powered chat feature to assist users with their data science queries.

## Project Structure

The project is organized into the following main components:

### 1. Main Application (`Tutor.py`)

The main application file that sets up the Streamlit interface, including the sidebar navigation, chat functionality, and dynamic content loading based on the selected section.

### 2. Pages Directory (`pages/`)

Contains individual Python scripts for each section of the CRISP-DM process. Each script includes detailed content, explanations, and quizzes related to its respective topic.

- `1_Business_understanding.py`: Covers the Business Understanding phase.
- `2_Data_understanding.py`: Covers the Data Understanding phase.
- `3_Data_preparation.py`: Covers the Data Preparation phase.
- `4_Feature_engineering.py`: Covers Feature Engineering.
- `5_Modeling.py`: Covers the Modeling phase.
- `6_Evaluation.py`: Covers the Evaluation phase.
- `7_Deployment.py`: Covers Deployment and Testing.
- `8_Models.py`: Covers ML, Deep Learning, and Transformers.

### 3. Chat Functionality

The application includes an AI-powered chat feature that allows users to ask questions related to data science. The chat model's responses are tailored based on the selected section to provide relevant and focused answers.

### 4. Focus Areas

Users can select specific focus areas from the sidebar to further refine the context of their queries. The focus areas include:
- Data Cleaning & Wrangling
- Feature Engineering & Selection
- Model Selection & Tuning
- Interpretability & Explainability
- Model Deployment & Monitoring

## Installation

To run the application locally, follow these steps:

1. Clone the repository:
    ```sh
    git clone https://github.com/your-username/LLM-Tutor.git
    cd LLM-Tutor
    ```

2. Create a virtual environment and activate it:
    ```sh
    python -m venv venv
    source venv/bin/activate  # On Windows, use `venv\Scripts\activate`
    ```

3. Install the required dependencies:
    ```sh
    pip install -r requirements.txt
    ```

4. Set up your OpenAI API key:
    - Create a [.env](http://_vscodecontentref_/1) file in the root directory of the project.
    - Add your OpenAI API key to the [.env](http://_vscodecontentref_/2) file:
        ```
        OPENAI_API_KEY=your_openai_api_key
        ```

5. Run the application:
    ```sh
    streamlit run Tutor.py
    ```

## Usage

- **Select a CRISP-DM Step**: Use the sidebar to navigate through different steps of the CRISP-DM process.
- **Ask AI**: Enter your OpenAI API key in the sidebar and ask questions related to data science.
- **Focus Areas**: Select specific focus areas to refine the context of your queries.
- **Interactive Content**: Each section includes detailed explanations, key concepts, and quizzes to test your understanding.

## License

This project is licensed under the MIT License. See the [LICENSE](http://_vscodecontentref_/3) file for more details.

## Contributing

Contributions are welcome! Please read the CONTRIBUTING file for guidelines on how to contribute to this project.

## Acknowledgements

- [Streamlit](https://streamlit.io/)
- [OpenAI](https://www.openai.com/)
- [CRISP-DM](https://www.sv-europe.com/crisp-dm-methodology/)

---

pinned: false
license: mit
short_description: Learn ML/LLM