Method _to_dataframe

xarray/core/dataset.py:7241–7298

(self, ordered_dims: Mapping[Any, int])

        )

    def _to_dataframe(self, ordered_dims: Mapping[Any, int]):
        from xarray.core.extension_array import PandasExtensionArray

        # All and only non-index arrays (whether data or coordinates) should
        # become columns in the output DataFrame. Excluding indexes rather
        # than dims handles the case of a MultiIndex along a single dimension.
        columns_in_order = [k for k in self.variables if k not in self.xindexes]
        non_extension_array_columns = [
            k
            for k in columns_in_order
            if not pd.api.types.is_extension_array_dtype(self.variables[k].data)  # noqa: TID251
        ]
        extension_array_columns = [
            k
            for k in columns_in_order
            if pd.api.types.is_extension_array_dtype(self.variables[k].data)  # noqa: TID251
        ]
        extension_array_columns_different_index = [
            k
            for k in extension_array_columns
            if set(self.variables[k].dims) != set(ordered_dims.keys())
        ]
        extension_array_columns_same_index = [
            k
            for k in extension_array_columns
            if k not in extension_array_columns_different_index
        ]
        data = [
            self._variables[k].set_dims(ordered_dims).values.reshape(-1)
            for k in non_extension_array_columns
        ]
        index = self.coords.to_index([*ordered_dims])
        broadcasted_df = pd.DataFrame(
            {
                **dict(zip(non_extension_array_columns, data, strict=True)),
                **{
                    c: self.variables[c].data
                    for c in extension_array_columns_same_index
                },
            },
            index=index,
        )
        for extension_array_column in extension_array_columns_different_index:
            extension_array = self.variables[extension_array_column].data
            index = self[
                self.variables[extension_array_column].dims[0]
            ].coords.to_index()
            extension_array_df = pd.DataFrame(
                {extension_array_column: extension_array},
                index=pd.Index(index.array)
                if isinstance(index, PandasExtensionArray)  # type: ignore[redundant-expr]
                else index,
            )
            extension_array_df.index.name = self.variables[extension_array_column].dims[
                0
            ]
            broadcasted_df = broadcasted_df.join(extension_array_df)
        return broadcasted_df[columns_in_order]