Skip to main content

Graphical Hypergeometric Networks

Project description

HNET - Graphical Hypergeometric Networks

PyPI Version License

This package detects associations in datasets across features with unknown function.

Background Real-world data sets often contain measurements with both continues and categorical values for the same sample. Despite the availability of many libraries, data sets with mixed data types require intensive pre-processing steps, and it remains a challenge to describe the relationships of one variable on another. The data understanding part is crucial but without making any assumptions on the model form, the search space is super-exponential in the number of variables and therefore not a common practice. Result We propose graphical hypergeometric networks (HNet), a method where associations across variables are tested for significance by statistical inference. The aim is to determine a network with significant associations that can shed light on the complex relationships across variables. HNet processes raw unstructured data sets and outputs a network that consists of (partially) directed or undirected edges between the nodes (i.e., variables). To evaluate the accuracy of HNet, we used well known data sets, and generated data sets with known ground truth by Bayesian sampling. In addition, the performance of HNet for the same data sets is compared to Bayesian structure learning. Conclusions We demonstrate that HNet showed high accuracy and performance in the detection of node links. In the case of the Alarm data set we can demonstrate an average MCC score 0.33 + 0.0002 (P<1x10-6), whereas Bayesian structure learning showed an average MCC score of 0.52 + 0.006 (P<1x10-11), and randomly assigning edges resulted in a MCC score of 0.004 + 0.0003 (P=0.49). Although Bayesian structure learning showed slightly better results, HNet overcomes some of the limitations of existing methods as it processes raw unstructured data sets, it allows analysis of mixed data types, it easily scales up in number of variables, and allows detailed examination of the detected associations.

Method overview



  • Install hnet from PyPI (recommended). Hnet is compatible with Python 3.6+ and runs on Linux, MacOS X and Windows. It is distributed under the Apache 2.0 license.
pip install hnet
  • Alternatively, install hnet from the GitHub source:
git clone
cd hnet
python install

Quick Start

  • Import hnet method
from hnet import hnet
  • Simple example for the sprinkler data set
df = pd.read_csv('')['close']
out =
figHEAT = hnet.plot_heatmap(out)
figNETW = hnet.plot_network(out)
figD3GR = hnet.plot_d3graph(out)

out =
figHEAT = hnet.plot_heatmap(out)
figNETW = hnet.plot_network(out)
figD3GR = hnet.plot_d3graph(out)



Please cite hnet in your publications if this is useful for your research. Here is an example BibTeX entry:

  author={Erdogan Taskesen},


© Copyright

See LICENSE for details.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for hnet, version 0.1.4
Filename, size File type Python version Upload date Hashes
Filename, size hnet-0.1.4-py3-none-any.whl (61.7 kB) File type Wheel Python version py3 Upload date Hashes View hashes
Filename, size hnet-0.1.4.tar.gz (65.3 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page