Method sum

python/ray/data/grouped_data.py:394–435

r"""Compute grouped sum aggregation. Examples: >>> import ray >>> ray.data.from_items([ # doctest: +SKIP ... (i % 3, i, i**2) # doctest: +SKIP ... for i in range(100)]) # doctest: +SKIP ... .groupby(lambda x: x[0] % 3)

(
        self, on: Union[str, List[str]] = None, ignore_nulls: bool = True
    )

    @PublicAPI(api_group=CDS_API_GROUP)
    def sum(
        self, on: Union[str, List[str]] = None, ignore_nulls: bool = True
    ) -> Dataset:
        r"""Compute grouped sum aggregation.

        Examples:
            >>> import ray
            >>> ray.data.from_items([ # doctest: +SKIP
            ...     (i % 3, i, i**2) # doctest: +SKIP
            ...     for i in range(100)])  # doctest: +SKIP
            ...     .groupby(lambda x: x[0] % 3)  # doctest: +SKIP
            ...     .sum(lambda x: x[2]) # doctest: +SKIP
            >>> ray.data.range(100).groupby("id").sum() # doctest: +SKIP
            >>> ray.data.from_items([ # doctest: +SKIP
            ...     {"A": i % 3, "B": i, "C": i**2} # doctest: +SKIP
            ...     for i in range(100)])  # doctest: +SKIP
            ...     .groupby("A")  # doctest: +SKIP
            ...     .sum(["B", "C"]) # doctest: +SKIP

        Args:
            on: a column name or a list of column names to aggregate.
            ignore_nulls: Whether to ignore null values. If ``True``, null
                values will be ignored when computing the sum; if ``False``,
                if a null value is encountered, the output will be null.
                We consider np.nan, None, and pd.NaT to be null values.
                Default is ``True``.

        Returns:
            The sum result.

            For different values of ``on``, the return varies:

            - ``on=None``: a dataset containing a groupby key column,
              ``"k"``, and a column-wise sum column for each original column
              in the dataset.
            - ``on=["col_1", ..., "col_n"]``: a dataset of ``n + 1``
              columns where the first column is the groupby key and the second
              through ``n + 1`` columns are the results of the aggregations.

            If groupby key is ``None`` then the key part of return is omitted.
        """
        return self._aggregate_on(Sum, on, ignore_nulls=ignore_nulls)

    @PublicAPI(api_group=CDS_API_GROUP)
    def min(