| import streamlit as st | |
| st.set_page_config(page_title="AutoML - Classification & Regression", layout="wide") | |
| st.title("Automated Machine Learning (AutoML) Pipeline") | |
| st.subheader("Effortless ML Model Training for Classification & Regression") | |
| st.markdown(""" | |
| ### 🔹 About the Project | |
| This AutoML project, built using Streamlit and deployed on Hugging Face, simplifies machine learning model training. Users can upload a dataset, and the system will: | |
| - **Detect the problem type** (Classification or Regression) | |
| - **Preprocess the data** (handling missing values, encoding categorical variables, feature scaling, etc.) | |
| - **Train multiple models** automatically | |
| - **Evaluate performance** based on accuracy or other relevant metrics | |
| - **Display results** interactively with visualizations | |
| ### 🚀 How It Works | |
| 1. **Upload a dataset (CSV format)** | |
| 2. **Select the type of machine learning problem** (or let the system auto-detect) | |
| 3. **Choose an algorithm** or let the system try multiple models | |
| 4. **View model performance and accuracy** | |
| 5. **Download the trained model (optional)** | |
| ### 📌 Features in Development | |
| - Hyperparameter tuning | |
| - Model interpretability | |
| - Deployment options for trained models | |
| """) | |