PyBanshee version (1.0): A Python implementation of the MATLAB toolbox BANSHEE for Non-Parametric Bayesian Networks with updated features

M.A. Mendoza Lugo; O. Morales Napoles; D. Paprotny; P.J.P. Koot; E. Ragno

doi:10.1016/j.softx.2022.101279

PyBanshee version (1.0): A Python implementation of the MATLAB toolbox BANSHEE for Non-Parametric Bayesian Networks with updated features

M.A. Mendoza Lugo, O. Morales Napoles, D. Paprotny, P.J.P. Koot, E. Ragno

Hydraulic Structures and Flood Risk

Research output: Contribution to journal › Article › Scientific › peer-review

58 Downloads (Pure)

Abstract

In this paper we discuss PyBanshee, which is a Python-based open-source implementation of the MATLAB toolbox BANSHEE. PyBanshee constitutes the first fully open-source package to quantify, visualize and validate Non-Parametric Bayesian Networks (NPBNs). The architecture of PyBanshee is heavily based on its MATLAB predecessor. It presents the full implementation of existing tools and introduces new modules. Specifically, PyBanshee allows for: (i) choosing fully parametric one-dimensional margins, (ii) choosing different sample sizes for the model-validation tests based on the Hellinger distance, (iii) drawing user-defined sample sizes of the NPBN, (iv) sample-based conditioning sampling (similarly to the closed-source proprietary package UNINET by LightTwist Software) and (v) visualizing the comparison between the histograms of the unconditional and conditional marginal distributions. New detailed examples demonstrating new features are provided.

Original language	English
Article number	101279
Journal	SoftwareX
Volume	21
DOIs	https://doi.org/10.1016/j.softx.2022.101279
Publication status	Published - 2023

Keywords

Bayesian network
Copulas
Python
Non-Parametric Bayesian Networks
BANSHEE
Python library

Access to Document

10.1016/j.softx.2022.101279

1-s2.0-S2352711022001972-mainFinal published version, 474 KBLicence: CC BY

Cite this

@article{af0e1bf48d9c42888af828a1d9beaba4,

title = "PyBanshee version (1.0): A Python implementation of the MATLAB toolbox BANSHEE for Non-Parametric Bayesian Networks with updated features",

abstract = "In this paper we discuss PyBanshee, which is a Python-based open-source implementation of the MATLAB toolbox BANSHEE. PyBanshee constitutes the first fully open-source package to quantify, visualize and validate Non-Parametric Bayesian Networks (NPBNs). The architecture of PyBanshee is heavily based on its MATLAB predecessor. It presents the full implementation of existing tools and introduces new modules. Specifically, PyBanshee allows for: (i) choosing fully parametric one-dimensional margins, (ii) choosing different sample sizes for the model-validation tests based on the Hellinger distance, (iii) drawing user-defined sample sizes of the NPBN, (iv) sample-based conditioning sampling (similarly to the closed-source proprietary package UNINET by LightTwist Software) and (v) visualizing the comparison between the histograms of the unconditional and conditional marginal distributions. New detailed examples demonstrating new features are provided.",

keywords = "Bayesian network, Copulas, Python, Non-Parametric Bayesian Networks, BANSHEE, Python library",

author = "{Mendoza Lugo}, M.A. and {Morales Napoles}, O. and D. Paprotny and P.J.P. Koot and E. Ragno",

year = "2023",

doi = "10.1016/j.softx.2022.101279",

language = "English",

volume = "21",

journal = "SoftwareX",

issn = "2352-7110",

publisher = "Elsevier",

}

TY - JOUR

T1 - PyBanshee version (1.0): A Python implementation of the MATLAB toolbox BANSHEE for Non-Parametric Bayesian Networks with updated features

AU - Mendoza Lugo, M.A.

AU - Morales Napoles, O.

AU - Paprotny, D.

AU - Koot, P.J.P.

AU - Ragno, E.

PY - 2023

Y1 - 2023

N2 - In this paper we discuss PyBanshee, which is a Python-based open-source implementation of the MATLAB toolbox BANSHEE. PyBanshee constitutes the first fully open-source package to quantify, visualize and validate Non-Parametric Bayesian Networks (NPBNs). The architecture of PyBanshee is heavily based on its MATLAB predecessor. It presents the full implementation of existing tools and introduces new modules. Specifically, PyBanshee allows for: (i) choosing fully parametric one-dimensional margins, (ii) choosing different sample sizes for the model-validation tests based on the Hellinger distance, (iii) drawing user-defined sample sizes of the NPBN, (iv) sample-based conditioning sampling (similarly to the closed-source proprietary package UNINET by LightTwist Software) and (v) visualizing the comparison between the histograms of the unconditional and conditional marginal distributions. New detailed examples demonstrating new features are provided.

AB - In this paper we discuss PyBanshee, which is a Python-based open-source implementation of the MATLAB toolbox BANSHEE. PyBanshee constitutes the first fully open-source package to quantify, visualize and validate Non-Parametric Bayesian Networks (NPBNs). The architecture of PyBanshee is heavily based on its MATLAB predecessor. It presents the full implementation of existing tools and introduces new modules. Specifically, PyBanshee allows for: (i) choosing fully parametric one-dimensional margins, (ii) choosing different sample sizes for the model-validation tests based on the Hellinger distance, (iii) drawing user-defined sample sizes of the NPBN, (iv) sample-based conditioning sampling (similarly to the closed-source proprietary package UNINET by LightTwist Software) and (v) visualizing the comparison between the histograms of the unconditional and conditional marginal distributions. New detailed examples demonstrating new features are provided.

KW - Bayesian network

KW - Copulas

KW - Python

KW - Non-Parametric Bayesian Networks

KW - BANSHEE

KW - Python library

U2 - 10.1016/j.softx.2022.101279

DO - 10.1016/j.softx.2022.101279

M3 - Article

SN - 2352-7110

VL - 21

JO - SoftwareX

JF - SoftwareX

M1 - 101279

ER -

PyBanshee version (1.0): A Python implementation of the MATLAB toolbox BANSHEE for Non-Parametric Bayesian Networks with updated features

Abstract

Keywords

Access to Document

Fingerprint

Cite this