NitroFE
A Python feature engineering engine that internally manages past dependent values for continuous calculation of time-based features.
What is NitroFE?
NitroFE is a Python feature engineering engine specifically designed for time-series data. It provides a variety of modules that internally manage past dependent values, enabling continuous calculation of features like moving averages, weighted windows, and technical indicators. This solves the challenge of externally saving state and implementing logic when moving feature pipelines from training to production.
Data scientists and machine learning engineers working with time-series data who need to create and deploy stateful feature engineering pipelines, particularly those transitioning models from research to production environments.
Developers choose NitroFE because it abstracts away the complexity of state management for time-dependent features, offering a production-ready solution with a rich library of pre-built indicators and window functions, reducing boilerplate code and deployment hurdles.
Overview
NitroFE is a Python feature engineering engine which provides a variety of modules designed to internally save past dependent values for providing continuous calculation.
Use Cases
Best For
- Creating rolling window features for time-series forecasting models
- Implementing technical indicators (e.g., RSI, MACD) for financial or sensor data analysis
- Building feature pipelines that require state persistence across batches or streaming data
- Transitioning time-based feature engineering from Jupyter notebooks to production systems
- Simplifying the deployment of machine learning models with complex, stateful feature dependencies
- Experimenting with a wide variety of moving average types and weighted window operations
Related Projects
tsfreshAutomatic extraction of relevant features from time series:
FeaturetoolsAn open source python library for automated feature engineering
Feature EngineFeature engineering and selection open-source Python library compatible with sklearn.
OpenFEOpenFE: automated feature generation with expert-level performance
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.