skrub-data/skrub

Machine learning with dataframes

What it solves

skrub is designed to simplify the process of preparing dataframes for machine learning. It bridges the gap between raw dataframes and the numerical arrays required by most machine learning algorithms, making it easier to handle mixed-type data in ML pipelines.

How it works

It provides a Python library that facilitates the integration of dataframes into machine learning workflows, allowing users to handle dataframes directly within their ML processes without manual, tedious preprocessing steps.

Who it’s for

Data scientists and machine learning engineers who work with dataframes (such as pandas) and use Python-based machine learning libraries.

Highlights

  • own Python library dedicated to machine learning with dataframes
  • easy installation via pip or conda
  • comprehensive learning materials and examples available
  • active community support via Discord

Related

  • Project
    online-ml/river

    A Python library for online machine learning on streaming data, allowing models to learn from new data points sequentially without needing to revisit past datasets.

  • Project
    scikit-learn/scikit-learn

    A Python module for machine learning built on top of SciPy, providing a wide range of tools for implementing ML algorithms.

  • Project
    rodmarkun/SmolML

    A pure Python machine learning library built from scratch for educational purposes, providing transparent implementations of core ML algorithms and an autograd engine.

  • Project
    Kaggle/kagglehub

    A Python library for programmatically downloading, uploading, and loading Kaggle datasets, models, and competition resources into data science frameworks.

  • Project
    roboflow/roboflow-python

    The official Python package for Roboflow, enabling developers to programmatically manage computer vision datasets, train models, and run inference.