pyconstruct.datasets.load

pyconstruct.datasets.load(dataset, *, base=None, fetch=True, force=False, remove_raw=False)

Load a dataset.

This method loads one of the predefined dataset. The list of available datasets can be found in the DATASETS variable.

The returned dataset is preprocessed in order to be usable out-of-the-box by the Weaver algorithms. The preprocessed version is automatically cached.

Parameters:
  • dataset (str) – The name of the dataset.
  • base (str) – The base directory where to look for the dataset or to fetch it into. Default is a system-dependent data directory.
  • fetch (bool) – Whether to fetch the dataset in case it is not found.
  • force (bool) – Whether to force the preprocessing of the dataset.
  • remove_raw (bool) – Wether to remove the download raw files.
Returns:

dataset – A collection of properties of the dataset.
Return type:

sklearn.utils.Bunch