medil.models.NeuroCausalFactorAnalysis.fit

NeuroCausalFactorAnalysis.fit(dataset: numpy.typing.NDArray, split_idcs=None) → NeuroCausalFactorAnalysis[source]

Fit a NeuroCausalFactorAnalysis model to a dataset using a masked VAE.

Parameters:

  • dataset (ndarray of shape (n_samples, n_features)) – Observed data matrix. Should be standardized (zero mean, unit variance per feature) for best results.

  • split_idcs (tuple of index arrays, optional) – (train_indices, valid_indices). If None, a 70/30 train/valid split is created automatically using self.seed.

Returns:

self

Return type:

NeuroCausalFactorAnalysis