Function interval_join

python/pathway/stdlib/temporal/_interval_join.py:577–775

Performs an interval join of self with other using a time difference and join expressions. If `self_time + lower_bound <= other_time <= self_time + upper_bound` and conditions in `on` are satisfied, the rows are joined. Args: other: the right side of a join. self_ti

(
    self: pw.Table,
    other: pw.Table,
    self_time: pw.ColumnExpression,
    other_time: pw.ColumnExpression,
    interval: Interval[int] | Interval[float] | Interval[datetime.timedelta],
    *on: pw.ColumnExpression,
    behavior: CommonBehavior | None = None,
    how: pw.JoinMode = pw.JoinMode.INNER,
    left_instance: pw.ColumnReference | None = None,
    right_instance: pw.ColumnReference | None = None,
)

@check_arg_types
@trace_user_frame
def interval_join(
    self: pw.Table,
    other: pw.Table,
    self_time: pw.ColumnExpression,
    other_time: pw.ColumnExpression,
    interval: Interval[int] | Interval[float] | Interval[datetime.timedelta],
    *on: pw.ColumnExpression,
    behavior: CommonBehavior | None = None,
    how: pw.JoinMode = pw.JoinMode.INNER,
    left_instance: pw.ColumnReference | None = None,
    right_instance: pw.ColumnReference | None = None,
) -> IntervalJoinResult:
    """Performs an interval join of self with other using a time difference
    and join expressions. If `self_time + lower_bound <=
    other_time <= self_time + upper_bound`
    and conditions in `on` are satisfied, the rows are joined.

    Args:
        other:  the right side of a join.
        self_time (pw.ColumnExpression[int | float | datetime]):
            time expression in self.
        other_time (pw.ColumnExpression[int | float | datetime]):
            time expression in other.
        lower_bound: a lower bound on time difference between other_time
            and self_time.
        upper_bound: an upper bound on time difference between other_time
            and self_time.
        on:  a list of column expressions. Each must have == as the top level
            operation and be of the form LHS: ColumnReference == RHS: ColumnReference.
        behavior: defines a temporal behavior of a join - features like delaying entries
            or ignoring late entries. You can see examples below or read more in the
            `temporal behavior of interval join tutorial </developers/user-guide/temporal-data/temporal_behavior>`_ .
        how: decides whether to run `interval_join_inner`, `interval_join_left`, `interval_join_right`
            or `interval_join_outer`. Default is INNER.
        left_instance/right_instance: optional arguments describing partitioning of the data into separate instances

    Returns:
        IntervalJoinResult: a result of the interval join. A method `.select()`
        can be called on it to extract relevant columns from the result of a join.

    Examples:

    >>> import pathway as pw
    >>> t1 = pw.debug.table_from_markdown(
    ...     ''&#x27;
    ...     | t
    ...   1 | 3
    ...   2 | 4
    ...   3 | 5
    ...   4 | 11
    ... ''&#x27;
    ... )
    >>> t2 = pw.debug.table_from_markdown(
    ...     ''&#x27;
    ...     | t
    ...   1 | 0
    ...   2 | 1
    ...   3 | 4