| --- |
| title: Student Success Prediction |
| emoji: 🎓 |
| colorFrom: blue |
| colorTo: indigo |
| sdk: streamlit |
| app_file: app.py |
| pinned: false |
| license: mit |
| --- |
| |
| # 🎓 Student Success Prediction |
|
|
| An end-to-end Machine Learning web application that predicts a student's final score and success metrics based on various academic and behavioral features. This project is deployed on Hugging Face Spaces using Streamlit. |
|
|
| --- |
|
|
| ## 🚀 Features |
|
|
| - **Accurate Predictions:** Utilizes a trained machine learning regression pipeline. |
| - **Interactive UI:** Built with Streamlit for a smooth and user-friendly experience. |
| - **Robust Preprocessing:** Uses serialized scaling and column transformation to ensure data consistency. |
|
|
| --- |
|
|
| ## 📁 Repository Structure |
|
|
| - `app.py`: The main Streamlit application file handling user inputs and UI. |
| - `model.pickle`: The trained Machine Learning model serialized using Pickle. |
| - `scale.pickle`: The serialized StandardScaler instance used for feature scaling. |
| - `column.pickle`: The serialized column transformer or list of feature columns to maintain structural alignment. |
| - `README.md`: Model documentation and instructions. |
|
|
| --- |
|
|
| ## 🛠️ How It Works |
|
|
| 1. **User Input:** The user provides student details (e.g., study hours, attendance, previous grades) via the Streamlit frontend. |
| 2. **Data Transformation:** `column.pickle` aligns the features, and `scale.pickle` scales the numerical data to match the training distribution. |
| 3. **Inference:** The processed data is fed into `model.pickle` to predict the final student score instantly. |
|
|
| --- |
|
|
| ## 💻 Local Installation & Setup |
|
|
| If you want to run this project locally, follow these steps: |
|
|
| 1. **Clone the repository:** |
| ```bash |
| git clone [https://huggingface.co/spaces/amirsoahil101/Student_Success_Prediction](https://huggingface.co/spaces/amirsoahil101/Student_Success_Prediction) |
| ``` |
|
|
