コード例 #1
0
ファイル: numeric.py プロジェクト: elileswap/arkouda-splunk
def value_counts(pda):
    """
    Count the occurrences of the unique values of an array.

    Parameters
    ----------
    pda : pdarray, int64
        The array of values to count

    Returns
    -------
    unique_values : pdarray, int64
        The unique values, sorted in ascending order

    counts : pdarray, int64
        The number of times the corresponding unique value occurs

    See Also
    --------
    unique, histogram

    Notes
    -----
    This function differs from ``histogram()`` in that it only returns counts 
    for values that are present, leaving out empty "bins".

    Examples
    --------
    >>> A = ak.array([2, 0, 2, 4, 0, 0])
    >>> ak.value_counts(A)
    (array([0, 2, 4]), array([3, 2, 1]))
    """
    return unique(pda, return_counts=True)
コード例 #2
0
def value_counts(pda: pdarray) -> Union[Categorical,  # type: ignore
                                        Tuple[Union[pdarray, Strings],
                                              Optional[pdarray]]]:
    """
    Count the occurrences of the unique values of an array.

    Parameters
    ----------
    pda : pdarray, int64
        The array of values to count

    Returns
    -------
    unique_values : pdarray, int64 or Strings
        The unique values, sorted in ascending order

    counts : pdarray, int64
        The number of times the corresponding unique value occurs
        
    Raises
    ------
    TypeError
        Raised if the parameter is not a pdarray

    See Also
    --------
    unique, histogram

    Notes
    -----
    This function differs from ``histogram()`` in that it only returns
    counts for values that are present, leaving out empty "bins". This
    function delegates all logic to the unique() method where the 
    return_counts parameter is set to True.

    Examples
    --------
    >>> A = ak.array([2, 0, 2, 4, 0, 0])
    >>> ak.value_counts(A)
    (array([0, 2, 4]), array([3, 2, 1]))
    """
    return unique(pda, return_counts=True)
コード例 #3
0
    def _binop(self, other: Union[Categorical, str_scalars],
               op: str_scalars) -> pdarray:
        """
        Executes the requested binop on this Categorical instance and returns 
        the results within a pdarray object.

        Parameters
        ----------
        other : Union[Categorical,str_scalars]
            the other object is a Categorical object or string scalar
        op : str_scalars
            name of the binary operation to be performed 
      
        Returns
        -------
        pdarray
            encapsulating the results of the requested binop      

        Raises
    -   -----
        ValueError
            Raised if (1) the op is not in the self.BinOps set, or (2) if the
            sizes of this and the other instance don't match
        RuntimeError
            Raised if a server-side error is thrown while executing the
            binary operation
        """
        if op not in self.BinOps:
            raise NotImplementedError("Categorical: unsupported operator: {}".\
                                      format(op))
        if np.isscalar(other) and resolve_scalar_dtype(other) == "str":
            idxresult = self.categories._binop(other, op)
            return idxresult[self.codes]
        if self.size != cast(Categorical, other).size:
            raise ValueError("Categorical {}: size mismatch {} {}".\
                             format(op, self.size, cast(Categorical,other).size))
        if isinstance(other, Categorical):
            if (self.categories.size
                    == other.categories.size) and (self.categories
                                                   == other.categories).all():
                # Because categories are identical, codes can be compared directly
                return self.codes._binop(other.codes, op)
            else:
                # Remap both codes to the union of categories
                union = unique(
                    concatenate((self.categories, other.categories),
                                ordered=False))
                newinds = arange(union.size)
                # Inds of self.categories in unioned categories
                selfnewinds = newinds[in1d(union, self.categories)]
                # Need a permutation and segments to broadcast new codes
                if self.permutation is None or self.segments is None:
                    g = GroupBy(self.codes)
                    self.permutation = g.permutation
                    self.segments = g.segments
                # Form new codes by broadcasting new indices for unioned categories
                selfnewcodes = broadcast(self.segments, selfnewinds, self.size,
                                         self.permutation)
                # Repeat for other
                othernewinds = newinds[in1d(union, other.categories)]
                if other.permutation is None or other.segments is None:
                    g = GroupBy(other.codes)
                    other.permutation = g.permutation
                    other.segments = g.segments
                othernewcodes = broadcast(other.segments, othernewinds,
                                          other.size, other.permutation)
                # selfnewcodes and othernewcodes now refer to same unioned categories
                # and can be compared directly
                return selfnewcodes._binop(othernewcodes, op)
        else:
            raise NotImplementedError(
                ("Operations between Categorical and " +
                 "non-Categorical not yet implemented. " +
                 "Consider converting operands to Categorical."))