Method to_dask_dataframe

xarray/core/dataset.py:7487–7569

Convert this dataset into a dask.dataframe.DataFrame. The dimensions, coordinates and data variables in this dataset form the columns of the DataFrame. Parameters ---------- dim_order : list, optional Hierarchical dimension order for the

(
        self, dim_order: Sequence[Hashable] | None = None, set_index: bool = False
    )

        return obj[dataframe.columns] if len(dataframe.columns) else obj

    def to_dask_dataframe(
        self, dim_order: Sequence[Hashable] | None = None, set_index: bool = False
    ) -> DaskDataFrame:
        """
        Convert this dataset into a dask.dataframe.DataFrame.

        The dimensions, coordinates and data variables in this dataset form
        the columns of the DataFrame.

        Parameters
        ----------
        dim_order : list, optional
            Hierarchical dimension order for the resulting dataframe. All
            arrays are transposed to this order and then written out as flat
            vectors in contiguous order, so the last dimension in this list
            will be contiguous in the resulting DataFrame. This has a major
            influence on which operations are efficient on the resulting dask
            dataframe.

            If provided, must include all dimensions of this dataset. By
            default, dimensions are sorted alphabetically.
        set_index : bool, default: False
            If set_index=True, the dask DataFrame is indexed by this dataset's
            coordinate. Since dask DataFrames do not support multi-indexes,
            set_index only works if the dataset only contains one dimension.

        Returns
        -------
        dask.dataframe.DataFrame
        """

        import dask.array as da
        import dask.dataframe as dd

        ordered_dims = self._normalize_dim_order(dim_order=dim_order)

        columns = list(ordered_dims)
        columns.extend(k for k in self.coords if k not in self.dims)
        columns.extend(self.data_vars)

        ds_chunks = self.chunks

        series_list = []
        df_meta = pd.DataFrame()
        for name in columns:
            try:
                var = self.variables[name]
            except KeyError:
                # dimension without a matching coordinate
                size = self.sizes[name]
                data = da.arange(size, chunks=size, dtype=np.int64)
                var = Variable((name,), data)

            # IndexVariable objects have a dummy .chunk() method
            if isinstance(var, IndexVariable):
                var = var.to_base_variable()

            # Make sure var is a dask array, otherwise the array can become too large