Side by side
Feature-engine vs timeseriesflattener
Both stand on data preparation software. Which one you can start free with, which one lets you read the code, and what each costs once you pay.
Choose Feature-engine if your machine-learning work uses pandas dataframes and scikit-learn, and you want feature transformations that fit into scikit-learn workflows. Its free BSD-licensed package covers a broad set of preparation and selection tasks. It is intended for Python 3.9 or later and is listed for Linux.
Visit Feature-enginePick timeseriesflattener when you need configurable feature construction from irregular time series before training machine-learning models. Consider another option if you want a hosted service or a non-Python workflow rather than a self-hosted package installed with pip.
Visit timeseriesflattenerThe facts
| Feature-engine | timeseriesflattener | |
|---|---|---|
| Free plan | Yes | Yes |
| Open source | Not published | Not published |
| Runs on | Linux | API, Linux |
| Lowest paid plan | Not published | Not published |
| Plans published | None | None |
| Maker | Not published | Not published |
| Website | feature-engine.trainindata.com | aarhus-psychiatry-research.github.io |
| On data preparation software | #14 of 28 | #18 of 28 |
Feature-engine: what it does well
- Covers imputation, encoding, discretisation and outlier handling.
- Retains dataframe column names and order after transformation.
- Works with scikit-learn pipelines, cross-validation and hyperparameter search.
- Allows users to select which variables transformers process.
- Free to use under the BSD 3-Clause License.
What to know first
- Requires Python 3.9 or later.
- The listed platform is Linux.
- Users need a Python environment to install the package.
timeseriesflattener: what it does well
- Handles irregular time-series observations
- Supports pandas and Polars dataframes
- Offers many documented aggregation functions
- Defines predictor and outcome windows
- Allows fallback values for empty windows
What to know first
- Requires Python and pip installation
- Runs as self-hosted software
- Designed around dataframe-based inputs
Alternatives to Feature-engine Alternatives to timeseriesflattener The whole list