If you would like to buy me a coffee

tsBNgen: A Python Library to Generate Time Series Data Based on an Arbitrary Bayesian Network Structure

Description

Citation

Features

Instruction

License

---

Description

tsBNgen is a Python package to generate time series data based on an arbitrary Bayesian Network Structures.

---

Citation

If you find this package useful or if you use it in your research or work please consider citing it as follows:

@article{tadayon2020tsbngen,
  title={tsBNgen: A Python Library to Generate Time Series Data from an Arbitrary Dynamic Bayesian Network Structure},
  author={Tadayon, Manie and Pottie, Greg},
  journal={arXiv preprint arXiv:2009.04595},
  year={2020}
}

---

Features

• It handles discrete nodes, continous nodes and hybrid (Mixture of discrete and continuous) network.

• It uses multinomila distribution for the discrete nodes and Gaussian distribution for the continuous nodes.

• It handles arbitrary Bayesian network structure.

• It supports arbitrary loopback values.

• The code can be modified easily to handle arbitrary static and temporal structures.

---

Instruction

To run this code either clone this repo or use the package distribution in PyPI using the following commands:

pip install tsBNgen

Then Run through the set of examples in

Time_Series_Generation_Examples.ipynb

For more information on how to use the package please visit the following:

1. Watch my Youtube tutorial (I go over the package) Watch the videos
2. Original paper
3. Documentation in PDF available in this repository.

License

This software is released under the MIT liecense.