Method sample

dask/dataframe/dask_expr/_collection.py:2576–2622

Random sample of items Parameters ---------- n : int, optional Number of items to return is not supported by dask. Use frac instead. frac : float, optional Approximate fraction of items to return. This sampling fraction is

(self, n=None, frac=None, replace=False, random_state=None)

            return func(self, *args, **kwargs)

    def sample(self, n=None, frac=None, replace=False, random_state=None):
        """Random sample of items

        Parameters
        ----------
        n : int, optional
            Number of items to return is not supported by dask. Use frac
            instead.
        frac : float, optional
            Approximate fraction of items to return. This sampling fraction is
            applied to all partitions equally. Note that this is an
            **approximate fraction**. You should not expect exactly ``len(df) * frac``
            items to be returned, as the exact number of elements selected will
            depend on how your data is partitioned (but should be pretty close
            in practice).
        replace : boolean, optional
            Sample with or without replacement. Default = False.
        random_state : int or ``np.random.RandomState``
            If an int, we create a new RandomState with this as the seed;
            Otherwise we draw from the passed RandomState.

        See Also
        --------
        DataFrame.random_split
        pandas.DataFrame.sample
        """
        if n is not None:
            msg = (
                "sample does not support the number of sampled items "
                "parameter, 'n'. Please use the 'frac' parameter instead."
            )
            if isinstance(n, Number) and 0 <= n <= 1:
                warnings.warn(msg)
                frac = n
            else:
                raise ValueError(msg)

        if frac is None:
            raise ValueError("frac must not be None")

        if random_state is None:
            random_state = np.random.RandomState()

        state_data = random_state_data(self.npartitions, random_state)
        return new_collection(
            expr.Sample(self, state_data=state_data, frac=frac, replace=replace)
        )

    def _repr_data(self):
        raise NotImplementedError