data_set.py 文件源码

def concat_features(data_sets: Iterable[DataSet],
                    dimension: str = "generated") -> DataSet:
    """
    Concatenates the specified data sets along the specified feature dimension.

    The feature matrices of each instance are concatenated along the specified dimension. All data sets must have the 
    specified feature dimension. Additionally, all metadata, including names and sizes of other feature dimensions must 
    be identical for all data sets.

    Parameters
    ----------
    data_sets: list of DataSet
        Data sets which should be concatenated
    dimension: str, default "generated"
        Feature dimension along which features should be concatenated.

    Returns
    -------
    DataSet
        A new data set created by concatenating the specified data sets along the specified feature dimension

    Raises
    ------
    ValueError
        If the specified feature dimension is not present in some data sets
    """
    for data_set in data_sets:
        # noinspection PyProtectedMember
        if dimension not in data_set._data.dims:
            raise ValueError("dimension '{}' missing in some data sets".format(dimension))

    # noinspection PyProtectedMember
    mutable = all([data_set._mutable for data_set in data_sets])

    # noinspection PyProtectedMember
    new_data = xr.concat([data_set._data for data_set in data_sets],
                         dim=dimension,
                         data_vars="minimal",
                         compat="identical")

    # noinspection PyTypeChecker
    return DataSet(data=new_data,
                   mutable=mutable)