H2O, Fast Scalable Machine Learning, for python

H2O, Fast Scalable Machine Learning, for python

Stars: 6815, Watchers: 6815, Forks: 1994, Open Issues: 2822

The h2oai/h2o-3 repo was created 10 years ago and the last code push was 17 hours ago.
The project is extremely popular with a mindblowing 6815 github stars!

How to Install h2o

You can install h2o using pip

pip install h2o

or add it to a project with poetry

poetry add h2o

Package Details

Apache v2
GitHub Repo:


  • Scientific/Engineering/Artificial Intelligence
  • Scientific/Engineering/Information Analysis
No  h2o  pypi packages just yet.


A list of common h2o errors.

Code Examples

Here are some h2o code examples and snippets.

GitHub Issues

The h2o package has 2822 open issues on GitHub

  • Question
  • GH-15584: Fix python explain re-rendering [nocheck]
  • Enable saving explain objects
  • Fix python explain plots re-rendering
  • GH-15574: Extended tests that consistently timeout. Py3.6, 3.7, 3.9 medium-large. [nocheck]
  • Rename uplift tree models prediction columns from p_y1_ct1 p_y1_ct0 to p_y1_without_treatment and p_y1_with_treatment
  • Create blog post on Uniform Robust method for histogram type
  • Add documentation on Uniform Robust method for histogram type
  • GH-15559: Add custom metric to SE [nocheck]
  • GH-6784: Custom metric for deeplearning [no-check]
  • GH-15565: Add custom metric to automl [nocheck]
  • GH-15575: Fix custom metric calculation in CV [nocheck]
  • Fix custom_metric computation for cross-validation
  • Extend Jenkins job timeout intervals to avoid tests not being run.
  • Inference for single row arff file fails

See more issues on GitHub

Related Packages & Articles

fastai 2.7.15

fastai simplifies training fast and accurate neural nets using modern best practices

dtreeviz 2.2.2

A Python 3 library for sci-kit learn, XGBoost, LightGBM, Spark, and TensorFlow decision tree visualization

deepspeed 0.14.4

DeepSpeed is a Python package developed by Microsoft that provides a deep learning optimization library designed to scale across multiple GPUs and servers. It is capable of training models with billions or even trillions of parameters, achieving excellent system throughput and efficiently scaling to thousands of GPUs.

DeepSpeed is particularly useful for training and inference of large language models, and it falls under the category of Machine Learning Frameworks and Libraries. It is designed to work with PyTorch and offers system innovations such as Zero Redundancy Optimizer (ZeRO), 3D parallelism, and model-parallelism to enable efficient training of large models.

combo 0.1.3

A Python Toolbox for Machine Learning Model Combination