Method with_id_from

python/pathway/internals/table.py:1942–1989

Compute new ids based on values in columns. Ids computed from `columns` must be row-wise unique. The uniqueness is not checked by pathway. Failing to provide unique ids can cause unexpected errors downstream. Args: columns: columns to be used as primary

(
        self,
        *args: expr.ColumnExpression | Value,
        instance: expr.ColumnReference | None = None,
    )

    @desugar
    @check_arg_types
    def with_id_from(
        self,
        *args: expr.ColumnExpression | Value,
        instance: expr.ColumnReference | None = None,
    ) -> Table:
        """Compute new ids based on values in columns.
        Ids computed from `columns` must be row-wise unique.
        The uniqueness is not checked by pathway. Failing to provide unique ids can
        cause unexpected errors downstream.

        Args:
            columns:  columns to be used as primary keys.

        Returns:
            Table: `self` updated with recomputed ids.

        Example:

        >>> import pathway as pw
        >>> t1 = pw.debug.table_from_markdown('''
        ...    | age | owner  | pet
        ...  1 | 10  | Alice  | 1
        ...  2 | 9   | Bob    | 1
        ...  3 | 8   | Alice  | 2
        ... ''')
        >>> t2 = t1 + t1.select(old_id=t1.id)
        >>> t3 = t2.with_id_from(t2.age)
        >>> pw.debug.compute_and_print(t3) # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
             | age | owner | pet | old_id
        ^... | 8   | Alice | 2   | ^...
        ^... | 9   | Bob   | 1   | ^...
        ^... | 10  | Alice | 1   | ^...
        >>> t4 = t3.select(t3.age, t3.owner, t3.pet, same_as_old=(t3.id == t3.old_id),
        ...     same_as_new=(t3.id == t3.pointer_from(t3.age)))
        >>> pw.debug.compute_and_print(t4) # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
             | age | owner | pet | same_as_old | same_as_new
        ^... | 8   | Alice | 2   | False       | True
        ^... | 9   | Bob   | 1   | False       | True
        ^... | 10  | Alice | 1   | False       | True
        """
        # new_index should be a column, so a little workaround
        new_index = self.select(
            ref_column=self.pointer_from(*args, instance=instance)
        ).ref_column

        return self._with_new_index(
            new_index=new_index,
        )

    @trace_user_frame
    @contextualized_operator