AutoNova

AutoNova is a modern AutoML framework that can handle everything from data preprocessing to model training in just 3 lines of code.
It is designed to save your time, boost productivity, and make Machine Learning workflows effortless.

Features

🔹 Preprocessing Class

• Cleaning & Transforming – Handle missing values, scaling, encoding
• Feature Engineering – Generate new useful features automatically
• Feature Selection – Select only the most important features
• Balancing – Fix imbalanced datasets with SMOTE
• Splitting – Train-test splits with ease

🔹 Model Training Class

• Automated Model Selection & Training
• Hyperparameter Tuning with Optuna
• Performance Metrics (Accuracy, Precision, Recall, F1, ROC-AUC)

Installation

pip install autonova

Usage Description

from autonova.auto import AutoNova
import pandas as pd

df = pd.read_csv("star_classification.csv")
target_col = "class"

automl = AutoNova(data=df, target_col=target_col)
automl.go(use_gpu=False, fast_mode=False, cv_splits=5, n_trials=50)

print("Best Model:", mode.best_model)
print("Preprocessing Steps:", mode.preprocess_logic)
print("Score:", mode.score)
print("Train Data Shapes:", [x.shape for x in mode.train_data])
print("Test Data Shapes:", [x.shape for x in mode.test_data])

• use_gpu=True GPU for Optuna training
• fast_mode=True only Faster models
• cv_splits=5 number of Splits
• n_trials=50 number of Trials

Contributing

Pull requests are welcome! For major changes, please open an issue first to discuss what you would like to change. Take use of CONTRIBUTING.md file to make contributions.
Github Link : https://github.com/Sanjaypal1916/ProjectX

License

MIT License – do anything, just give credit.

Need Help?

If you’re stuck, don’t worry — we’ve got your back!

• Open a Discussion for general questions.
• Create an Issue for bug reports or feature requests.
• Or contact the maintainers directly.

We’d love to see your contributions and help you along the way.

✨ Keep learning, keep building, and keep innovating!
💡 Together, we can make AutoNova even better.

Best,
The AutoNova Team 🚀