Function diff

python/pathway/stdlib/ordered/diff.py:10–123

Compute the difference between the values in the ``values`` columns and the previous values according to the order defined by the column ``timestamp``. Args: timestamp (pw.ColumnReference[int | float | datetime | str | bytes]): The column reference to the ``timesta

(
    self: pw.Table,
    timestamp: pw.ColumnReference,
    *values: pw.ColumnReference,
    instance: pw.ColumnReference | None = None,
)

@check_arg_types
@trace_user_frame
def diff(
    self: pw.Table,
    timestamp: pw.ColumnReference,
    *values: pw.ColumnReference,
    instance: pw.ColumnReference | None = None,
) -> pw.Table:
    """
    Compute the difference between the values in the ``values`` columns and the previous values
    according to the order defined by the column ``timestamp``.

    Args:

        timestamp (pw.ColumnReference[int | float | datetime | str | bytes]):
            The column reference to the ``timestamp`` column on which the order is computed.
        *values (pw.ColumnReference[int | float | datetime]):
            Variable-length argument representing the column references to the ``values`` columns.
        instance (pw.ColumnReference):
            Can be used to group the values. The difference is only computed between rows with
            the same ``instance`` value.

    Returns:
        ``Table``: A new table where each column is replaced with a new column containing
        the difference and whose name is the concatenation of `diff_` and the former name.

    Raises:
        ValueError: If the columns are not ColumnReference.

    Note:
        - The value of the "first" value (the row with the lowest value \
        in the ``timestamp`` column) is ``None``.

    Example:

    >>> import pathway as pw
    >>> table = pw.debug.table_from_markdown('''
    ... timestamp | values
    ... 1         | 1
    ... 2         | 2
    ... 3         | 4
    ... 4         | 7
    ... 5         | 11
    ... 6         | 16
    ... ''')
    >>> table += table.diff(pw.this.timestamp, pw.this.values)
    >>> pw.debug.compute_and_print(table, include_id=False)
    timestamp | values | diff_values
    1         | 1      |
    2         | 2      | 1
    3         | 4      | 2
    4         | 7      | 3
    5         | 11     | 4
    6         | 16     | 5

    >>> table = pw.debug.table_from_markdown(
    ...     '''
    ... timestamp | instance | values
    ... 1         | 0        | 1
    ... 2         | 1        | 2