tsBNgen: A Python Library to Generate Time Series Data from an Arbitrary Dynamic Bayesian Network Structure
This provides a tool for researchers and practitioners needing synthetic time series data, but it is incremental as it builds on existing dynamic Bayesian network methods.
The authors tackled the problem of generating synthetic time series data by introducing tsBNgen, a Python library that produces data from any dynamic Bayesian network structure, enabling easier access to training data for algorithms.
Synthetic data is widely used in various domains. This is because many modern algorithms require lots of data for efficient training, and data collection and labeling usually are a time-consuming process and are prone to errors. Furthermore, some real-world data, due to its nature, is confidential and cannot be shared. Bayesian networks are a type of probabilistic graphical model widely used to model the uncertainties in real-world processes. Dynamic Bayesian networks are a special class of Bayesian networks that model temporal and time series data. In this paper, we introduce the tsBNgen, a Python library to generate time series and sequential data based on an arbitrary dynamic Bayesian network. The package, documentation, and examples can be downloaded from https://github.com/manitadayon/tsBNgen.