daft.functions.levenshtein_distance#

def levenshtein_distance(left: Expression, right: Expression) -> Expression:
    """Compute the Levenshtein edit distance between two strings.

    The Levenshtein distance is the minimum number of single-character insertions,
    deletions, or substitutions required to transform one string into the other.

    Args:
        left: The left string expression to compare.
        right: The right string expression to compare against.

    Returns:
        The Levenshtein distance for each pair of strings. Returns null when either
        input is null.

    Examples:
        >>> import daft
        >>> from daft.functions import levenshtein_distance
        >>> df = daft.from_pydict({"x": ["kitten", "saturday", ""], "y": ["sitting", "sunday", "abc"]})
        >>> df = df.with_column("distance", levenshtein_distance(df["x"], df["y"]))
        >>> df.collect()
        ╭──────────┬─────────┬──────────╮
        │ x        ┆ y       ┆ distance │
        │ ---      ┆ ---     ┆ ---      │
        │ String   ┆ String  ┆ Int64    │
        ╞══════════╪═════════╪══════════╡
        │ kitten   ┆ sitting ┆ 3        │
        ├╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌┤
        │ saturday ┆ sunday  ┆ 3        │
        ├╌╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌┼╌╌╌╌╌╌╌╌╌╌┤
        │          ┆ abc     ┆ 3        │
        ╰──────────┴─────────┴──────────╯
        <BLANKLINE>
        (Showing first 3 of 3 rows)
    """
    return Expression._call_builtin_scalar_fn("levenshtein_distance", left, right)