Function interpolate

python/pathway/stdlib/statistical/_interpolate.py:56–167

Interpolates missing values in a column using the previous and next values based on a timestamps column. Args: timestamp (ColumnReference): Reference to the column containing timestamps. *values (ColumnReference): References to the columns containing values to be interpolat

(
    self: pw.Table,
    timestamp: pw.ColumnReference,
    *values: pw.ColumnReference,
    mode: InterpolateMode = InterpolateMode.LINEAR,
)

@trace_user_frame
def interpolate(
    self: pw.Table,
    timestamp: pw.ColumnReference,
    *values: pw.ColumnReference,
    mode: InterpolateMode = InterpolateMode.LINEAR,
):
    """
    Interpolates missing values in a column using the previous and next values based on a timestamps column.

    Args:
        timestamp (ColumnReference): Reference to the column containing timestamps.
        *values (ColumnReference): References to the columns containing values to be interpolated.
        mode (InterpolateMode, optional): The interpolation mode. Currently,\
            only InterpolateMode.LINEAR is supported. Default is InterpolateMode.LINEAR.

    Returns:
        Table: A new table with the interpolated values.

    Raises:
        ValueError: If the columns are not ColumnReference or if the interpolation mode is not supported.

    Note:
        - The interpolation is performed based on linear interpolation between the previous and next values.
        - If a value is missing at the beginning or end of the column, no interpolation is performed.

    Example:

    >>> import pathway as pw
    >>> table = pw.debug.table_from_markdown('''
    ... timestamp | values_a | values_b
    ... 1         | 1        | 10
    ... 2         |          |
    ... 3         | 3        |
    ... 4         |          |
    ... 5         |          |
    ... 6         | 6        | 60
    ... ''')
    >>> table = table.interpolate(pw.this.timestamp, pw.this.values_a, pw.this.values_b)
    >>> pw.debug.compute_and_print(table, include_id=False)
    timestamp | values_a | values_b
    1         | 1.0      | 10.0
    2         | 2.0      | 20.0
    3         | 3.0      | 30.0
    4         | 4.0      | 40.0
    5         | 5.0      | 50.0
    6         | 6.0      | 60.0
    """

    if mode != InterpolateMode.LINEAR:
        raise ValueError(
            """interpolate: Invalid mode. Only Interpolate.LINEAR is currently available."""
        )

    if isinstance(timestamp, pw.ColumnReference):
        timestamp = self[timestamp]
    else:
        if isinstance(timestamp, str):
            raise ValueError(