This library wraps popular tabular regression/classification model enabling rapid evaluation and optimization.
Project description
[![Pre-Commit Status](https://github.com/xaviernogueira/Tabular_ML/actions/workflows/pre-commit.yml/badge.svg)](https://github.com/xaviernogueira/Tabular_ML/actions/workflows/pre-commit.yml) [![Tests Status](https://github.com/xaviernogueira/Tabular_ML/actions/workflows/tests.yml/badge.svg)](https://github.com/xaviernogueira/Tabular_ML/actions/workflows/tests.yml) [![Coverage](https://codecov.io/gh/xaviernogueira/Tabular_ML/graph/badge.svg)](https://codecov.io/gh/xaviernogueira/Tabular_ML)
# tabular_ml - tabular machine learning simplified! I’ve packaged and open sourced my personal machine learning tools to speed up your next data science project.
Train, evaluate, ensemble, and optimize hyperparameters from a standardized interface.
![repo_schematic](images/readme_image.png)
## Key Features * Train models efficiently without worrying about library differences! tabular_ml implements library specific, performance oriented, patterns/classes under-the-hood (i.e., xgboost.DMatrix -> xgboost.Booster). * Automate the K-Fold evaluation process across multiple models simultaneously (including ensembles). * Rapidly optimize hyperparameters using [optuna](https://optuna.org/). Leverage our built-in parameter search spaces, or adjust to your needs. * Plugin-able. Write your own plugins to extend functionality without forking (and consider contributing your plugins!).
For full documentation see our GitHub ReadMe [here](https://github.com/xaviernogueira/Tabular_ML).
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for tabular_ml-0.0.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b6fcc4ff2bdd2201ad62eeb8a02898c04a45da16be90c54ca990542d062066bc |
|
MD5 | 86c0e5ec557474d888a704fce0de6941 |
|
BLAKE2b-256 | 6659a5a368486f0f02b6225edd5b855e3f389f876f2164924e35f2c26e5e14b1 |