Method apply

dask/dataframe/dask_expr/_collection.py:4345–4400

Parallel version of pandas.Series.apply Parameters ---------- func : function Function to apply $META args : tuple Positional arguments to pass to function in addition to the value. Additional keyword arguments will be passed

(self, function, *args, meta=no_default, axis=0, **kwargs)

    @insert_meta_param_description(pad=12)
    def apply(self, function, *args, meta=no_default, axis=0, **kwargs):
        """Parallel version of pandas.Series.apply

        Parameters
        ----------
        func : function
            Function to apply
        $META
        args : tuple
            Positional arguments to pass to function in addition to the value.

        Additional keyword arguments will be passed as keywords to the function.

        Returns
        -------
        applied : Series or DataFrame if func returns a Series.

        Examples
        --------
        >>> import dask.dataframe as dd
        >>> s = pd.Series(range(5), name='x')
        >>> ds = dd.from_pandas(s, npartitions=2)

        Apply a function elementwise across the Series, passing in extra
        arguments in ``args`` and ``kwargs``:

        >>> def myadd(x, a, b=1):
        ...     return x + a + b
        >>> res = ds.apply(myadd, args=(2,), b=1.5)  # doctest: +SKIP

        By default, dask tries to infer the output metadata by running your
        provided function on some fake data. This works well in many cases, but
        can sometimes be expensive, or even fail. To avoid this, you can
        manually specify the output metadata with the ``meta`` keyword. This
        can be specified in many forms, for more information see
        ``dask.dataframe.utils.make_meta``.

        Here we specify the output is a Series with name ``'x'``, and dtype
        ``float64``:

        >>> res = ds.apply(myadd, args=(2,), b=1.5, meta=('x', 'f8'))

        In the case where the metadata doesn't change, you can also pass in
        the object itself directly:

        >>> res = ds.apply(lambda x: x + 1, meta=ds)

        See Also
        --------
        Series.map_partitions
        """
        self._validate_axis(axis)
        if meta is no_default:
            meta = expr.emulate(M.apply, self, function, args=args, udf=True, **kwargs)
            warnings.warn(meta_warning(meta))
        return new_collection(self.expr.apply(function, *args, meta=meta, **kwargs))

    @classmethod