v0.1.7

Using new discrete noise distribution

v0.1.6

update internal computation of provided edge density, to become more precise

v0.1.5

Extend scaling option to include discrete variables

v0.1.4

add different transformations applied to the dataset after sampling

v0.1.3

Add an option to scale the influence of the parents on continuous variables

v0.1.2

Add option to normalize data after sampling

v0.1.1

allow for graph structure loaded from a networkx.DiGraph
note that only the provided graph structure, i.e., the nodes and edges are considered. Node types and edge characteristics are assigned according to the provided parameters
add a command-line argument to parse a file to a .gml file to load graph structure

v0.1.0

Package fixes (#43)

adds github action to run tests on PR
adds two parameters to specify custom output files
restructures packages (again) because I noticed errors when trying to use this in our library
fixes pypi tests, they were not properly testing the installation from testpypi but simply using the local files

Co-authored-by: Ben Hurdelhey <[email protected]>
Co-authored-by: Christopher Hagedorn <[email protected]>

Initial Release

Merge pull request #42 from hpi-epic/release-pypi

Release on pypi - thanks @benrobby. Well done!