sdv.relational.hma.HMA1

class sdv.relational.hma.HMA1(metadata, root_path=None, model=None, model_kwargs=None)[source]

Hierarchical Modeling Algorithm One.

Parameters

  • metadata (dict, str or Metadata) – Metadata dict, path to the metadata JSON file or Metadata instance itself.

  • root_path (str or None) – Path to the dataset directory. If None and metadata is a path, the metadata location is used. If None and metadata is a dict, the current working directory is used.

  • model (type) – Class of the copula to use. Defaults to sdv.models.copulas.GaussianCopula.

  • model_kwargs (dict) – Keyword arguments to pass to the model. If the default model is used, this defaults to using a gaussian distribution and a categorical_fuzzy transformer.

__init__(metadata, root_path=None, model=None, model_kwargs=None)[source]

Initialize self. See help(type(self)) for accurate signature.

Methods

__init__(metadata[, root_path, model, …])

Initialize self.

fit([tables])

Fit this relational model instance to the dataset data.

load(path)

Load a model from a given path.

sample([table_name, num_rows, …])

Generate synthetic data for one table or the entire dataset.

save(path)

Save this instance to the given path using pickle.

Attributes

DEFAULT_MODEL_KWARGS

metadata

HMA1 sdv.relational.hma.HMA1.fit