This project is a complete, production-ready AutoML web app. Users can upload a dataset, explore data, train ML models, compare them, visualize results, and download a final model all through a simple GUI.

• Automatic data type detection
• Missing values summary
• Data preview + statistics
• Clear UI workflow (Data → Training → Visualization → Prediction)

• Automatic preprocessing
• Cross-validation
• Compare multiple ML models
• Auto-select best model
• Manual model selection supported

• Confusion Matrix
• ROC / PR Curve
• Residuals
• Feature Importance
• Error plots
• All charts rendered safely without caching errors

• Save the model safely
• Prevents filename duplication
• Download .pkl model file
• Load model for predictions

• Upload CSV for batch inference
• Manual form for single prediction
• Download prediction results as CSV

• Full Streamlit session state handling
• Bug-free PyCaret setup
• No excessive memory usage
• Safe chart rendering
• No threading errors

AutoML-App/
│
├── streamlit_app_automl.py   # Main Streamlit application
├── requirements.txt          # All dependencies
├── models/                   # Auto-generated saved models
├── temp/                     # Temporary experiment/charts
├── assets/                   # Logos, icons (optional)
└── README.md                 # Documentation (this file)

This section is step-by-step with zero assumptions.

Download and install Python from: https://www.python.org/downloads/

During installation check the box:

☑ Add Python to PATH

git clone https://github.com/<your-username>/<repo-name>.git
cd <repo-name>

1. Click Code → Download ZIP
2. Extract it
3. Open the extracted folder

python -m venv venv
venv\Scripts\activate

python3 -m venv venv
source venv/bin/activate

You should now see:

(venv) C:\YourProject>

pip install -r requirements.txt

This installs:

• Streamlit
• PyCaret
• Scikit-learn
• Pandas
• Plotly
• Matplotlib

Everything required to run the app.

streamlit run streamlit_app_automl.py

Now your browser will automatically open the app at:

👉 http://localhost:8501

Your virtual environment is not activated. Run:

➡ Windows

venv\Scripts\activate

➡ Mac/Linux

source venv/bin/activate

Restart the app:

streamlit run streamlit_app_automl.py

Make sure the repo has:

models/
temp/

If missing, create them manually.

1. Push repo to GitHub

2. Go to https://share.streamlit.io

3. Select your repo

4. Add this in "Python version":

   3.10
   

5. Deploy ✔️

No extra config required.

• SHAP explainability
• Auto PDF report generation
• Model monitoring dashboard
• Multi-page UI
• Cloud model registry

Sumit Chongder Machine Learning Engineer | AutoML Systems | Quantum & AI Research

🔗 LinkedIn: https://www.linkedin.com/in/sumit-chongder/

If this project helped you, please ⭐ star the GitHub repo — it motivates further development!