Method split

python/pathway/internals/table.py:538–575

Split a table according to `split_expression` condition. Args: split_expression: `ColumnExpression` that specifies the split condition. Returns: positive_table, negative_table: tuple of tables, with the same schemas as `self` and with ids that are

(
        self, split_expression: expr.ColumnExpression
    )

    @desugar
    @check_arg_types
    def split(
        self, split_expression: expr.ColumnExpression
    ) -> tuple[Table[TSchema], Table[TSchema]]:
        """Split a table according to `split_expression` condition.


        Args:
            split_expression: `ColumnExpression` that specifies the split condition.

        Returns:
           positive_table, negative_table: tuple of tables,
           with the same schemas as `self` and with ids that are subsets of `self.id`,
           and provably disjoint.


        Example:

        >>> import pathway as pw
        >>> vertices = pw.debug.table_from_markdown('''
        ... label outdegree
        ...     1         3
        ...     7         0
        ... ''')
        >>> positive, negative = vertices.split(vertices.outdegree == 0)
        >>> pw.debug.compute_and_print(positive, include_id=False)
        label | outdegree
        7     | 0
        >>> pw.debug.compute_and_print(negative, include_id=False)
        label | outdegree
        1     | 3
        """
        positive = self.filter(split_expression)
        negative = self.filter(~split_expression)
        universes.promise_are_pairwise_disjoint(positive, negative)
        universes.promise_are_equal(
            self, Table.concat(positive, negative)
        )  # TODO: add API method for this
        return positive, negative

    @contextualized_operator
    def _filter(self, filter_expression: expr.ColumnExpression) -> Table[TSchema]: