According to definition, the prior term should be

$$ \log p(G) = \sum_{i=1}^{d} \left[ |PA_i| \log\left(\frac{\kappa}{d-1}\right) + (d - 1 - |PA_i|)\log\left(1 - \frac{\kappa}{d-1}\right) \right] $$

where $d$ is number of variables. But it seems that in LocalScoreFunction.py line 151, where Data is of shape (n_samples, n_variables), Data.shape[0] is used instead of Data.shape[1]. Could you please let me know if this was intentional, or if it might have been unintentionally missed?

I have opened a pull request (#248) that proposes this change for your consideration.