def argsort(self):
__doc__ = argsort.__doc__
idxperm = argsort(self.categories)
inverse = zeros_like(idxperm)
inverse[idxperm] = arange(idxperm.size)
newvals = inverse[self.codes]
return argsort(newvals)
def sort(self):
__doc__ = sort.__doc__
idxperm = argsort(self.categories)
inverse = zeros_like(idxperm)
inverse[idxperm] = arange(idxperm.size)
newvals = inverse[self.codes]
return Categorical.from_codes(newvals, self.categories[idxperm])
def group(self):
"""
Return the permutation that groups the array, placing equivalent
categories together. All instances of the same category are guaranteed to lie
in one contiguous block of the permuted array, but the blocks are not
necessarily ordered.
Returns
-------
pdarray
The permutation that groups the array by value
See Also
--------
GroupBy, unique
Notes
-----
This method is faster than the corresponding Strings method. If the Categorical
was created from a Strings object, then this function simply returns the
cached permutation. Even if the Categorical was created using from_codes(),
this function will be faster than Strings.group() because it sorts dense
integer values, rather than 128-bit hash values.
"""
if self.permutation is None:
return argsort(self.codes)
else:
return self.permutation
def intersect1d(pda1: pdarray,
pda2: pdarray,
assume_unique: bool = False) -> pdarray:
"""
Find the intersection of two arrays.
Return the sorted, unique values that are in both of the input arrays.
Parameters
----------
pda1 : pdarray
Input array
pda2 : pdarray
Input array
assume_unique : bool
If True, the input arrays are both assumed to be unique, which
can speed up the calculation. Default is False.
Returns
-------
pdarray
Sorted 1D array of common and unique elements.
Raises
------
TypeError
Raised if either pda1 or pda2 is not a pdarray
RuntimeError
Raised if the dtype of either pdarray is not supported
See Also
--------
unique, union1d
Notes
-----
ak.intersect1d is not supported for bool or float64 pdarrays
Examples
--------
>>> ak.intersect1d([1, 3, 4, 3], [3, 1, 2, 1])
array([1, 3])
"""
if pda1.size == 0:
return pda1 # nothing in the intersection
if pda2.size == 0:
return pda2 # nothing in the intersection
if pda1.dtype == int and pda2.dtype == int:
repMsg = generic_msg(cmd="intersect1d", args="{} {} {}".\
format(pda1.name, pda2.name, assume_unique))
return create_pdarray(cast(str, repMsg))
if not assume_unique:
pda1 = unique(pda1)
pda2 = unique(pda2)
aux = concatenate((pda1, pda2), ordered=False)
aux_sort_indices = argsort(aux)
aux = aux[aux_sort_indices]
mask = aux[1:] == aux[:-1]
int1d = aux[:-1][mask]
return int1d
def __init__(self, keys):
self.per_locale = False
self.keys = keys
if isinstance(keys, pdarray):
self.nkeys = 1
self.size = keys.size
if self.per_locale:
self.permutation = local_argsort(keys)
else:
self.permutation = argsort(keys)
elif isinstance(keys, Strings):
self.nkeys = 1
self.size = keys.size
if self.per_locale:
raise ValueError("per-locale groupby not supported on strings")
else:
self.permutation = keys.group()
else:
self.nkeys = len(keys)
self.size = keys[0].size
for k in keys:
if k.size != self.size:
raise ValueError("Key arrays must all be same size")
self.permutation = coargsort(keys)
# self.permuted_keys = self.keys[self.permutation]
self.find_segments()
def __init__(self, keys : List[Union[pdarray,np.int64,Strings]],
assume_sorted : bool=False, hash_strings : bool=True) -> None:
self.logger = getArkoudaLogger(name=self.__class__.__name__)
self.assume_sorted = assume_sorted
self.hash_strings = hash_strings
self.keys = keys
if isinstance(keys, pdarray):
self.nkeys = 1
self.size = keys.size
if assume_sorted:
self.permutation = arange(self.size)
else:
self.permutation = argsort(keys)
# for Strings or Categorical
elif hasattr(keys, "group"):
self.nkeys = 1
self.size = keys.size
if assume_sorted:
self.permutation = arange(self.size)
else:
self.permutation = keys.group()
else:
self.nkeys = len(keys)
self.size = keys[0].size
for k in keys:
if k.size != self.size:
raise ValueError("Key arrays must all be same size")
if assume_sorted:
self.permutation = arange(self.size)
else:
self.permutation = coargsort(keys)
# self.permuted_keys = self.keys[self.permutation]
self.find_segments()
def setxor1d(pda1: pdarray,
pda2: pdarray,
assume_unique: bool = False) -> pdarray:
"""
Find the set exclusive-or (symmetric difference) of two arrays.
Return the sorted, unique values that are in only one (not both) of the
input arrays.
Parameters
----------
pda1 : pdarray
Input array.
pda2 : pdarray
Input array.
assume_unique : bool
If True, the input arrays are both assumed to be unique, which
can speed up the calculation. Default is False.
Returns
-------
pdarray
Sorted 1D array of unique values that are in only one of the input
arrays.
Raises
------
TypeError
Raised if either pda1 or pda2 is not a pdarray
RuntimeError
Raised if the dtype of either pdarray is not supported
Notes
-----
ak.setxor1d is not supported for bool or float64 pdarrays
Examples
--------
>>> a = ak.array([1, 2, 3, 2, 4])
>>> b = ak.array([2, 3, 5, 7, 5])
>>> ak.setxor1d(a,b)
array([1, 4, 5, 7])
"""
if pda1.size == 0:
return pda2 # return other pdarray if pda1 is empty
if pda2.size == 0:
return pda1 # return other pdarray if pda2 is empty
if pda1.dtype == int and pda2.dtype == int:
repMsg = generic_msg(cmd="setxor1d", args="{} {} {}".\
format(pda1.name, pda2.name, assume_unique))
return create_pdarray(cast(str, repMsg))
if not assume_unique:
pda1 = cast(pdarray, unique(pda1))
pda2 = cast(pdarray, unique(pda2))
aux = concatenate((pda1, pda2), ordered=False)
aux_sort_indices = argsort(aux)
aux = aux[aux_sort_indices]
flag = concatenate((array([True]), aux[1:] != aux[:-1], array([True])))
return aux[flag[1:] & flag[:-1]]
def intersect1d(pda1, pda2, assume_unique=False):
"""
Find the intersection of two arrays.
Return the sorted, unique values that are in both of the input arrays.
Parameters
----------
pda1 : pdarray
Input array
pda2 : pdarray
Input array
assume_unique : bool
If True, the input arrays are both assumed to be unique, which
can speed up the calculation. Default is False.
Returns
-------
pdarray
Sorted 1D array of common and unique elements.
See Also
--------
unique, union1d
Examples
--------
>>> ak.intersect1d([1, 3, 4, 3], [3, 1, 2, 1])
array([1, 3])
"""
if isinstance(pda1, pdarray) and isinstance(pda2, pdarray):
if pda1.size == 0:
return pda1 # nothing in the intersection
if pda2.size == 0:
return pda2 # nothing in the intersection
if pda1.dtype == int and pda2.dtype == int:
repMsg = generic_msg("intersect1d {} {} {}".format(pda1.name, pda2.name, assume_unique))
return create_pdarray(repMsg)
if not assume_unique:
pda1 = unique(pda1)
pda2 = unique(pda2)
aux = concatenate((pda1, pda2))
aux_sort_indices = argsort(aux)
aux = aux[aux_sort_indices]
mask = aux[1:] == aux[:-1]
int1d = aux[:-1][mask]
return int1d
else:
raise TypeError("must be pdarray {} or {}".format(pda1,pda2))
def setxor1d(pda1, pda2, assume_unique=False):
"""
Find the set exclusive-or (symmetric difference) of two arrays.
Return the sorted, unique values that are in only one (not both) of the
input arrays.
Parameters
----------
pda1 : pdarray
Input array.
pda2 : pdarray
Input array.
assume_unique : bool
If True, the input arrays are both assumed to be unique, which
can speed up the calculation. Default is False.
Returns
-------
pdarray
Sorted 1D array of unique values that are in only one of the input
arrays.
Examples
--------
>>> a = ak.array([1, 2, 3, 2, 4])
>>> b = ak.array([2, 3, 5, 7, 5])
>>> ak.setxor1d(a,b)
array([1, 4, 5, 7])
"""
if isinstance(pda1, pdarray) and isinstance(pda2, pdarray):
if pda1.size == 0:
return pda2 # return other pdarray if pda1 is empty
if pda2.size == 0:
return pda1 # return other pdarray if pda2 is empty
if pda1.dtype == int and pda2.dtype == int:
repMsg = generic_msg("setxor1d {} {} {}".format(pda1.name, pda2.name, assume_unique))
return create_pdarray(repMsg)
if not assume_unique:
pda1 = unique(pda1)
pda2 = unique(pda2)
aux = concatenate((pda1, pda2))
aux_sort_indices = argsort(aux)
aux = aux[aux_sort_indices]
flag = concatenate((array([True]), aux[1:] != aux[:-1], array([True])))
return aux[flag[1:] & flag[:-1]]
else:
raise TypeError("must be pdarray {} or {}".format(pda1,pda2))
def __init__(self,
keys: Union[pdarray, Strings, 'Categorical',
List[Union[pdarray, np.int64, Strings]]],
assume_sorted: bool = False,
hash_strings: bool = True) -> None:
from arkouda.categorical import Categorical
self.logger = getArkoudaLogger(name=self.__class__.__name__)
self.assume_sorted = assume_sorted
self.hash_strings = hash_strings
self.keys: Union[pdarray, Strings, Categorical]
if isinstance(keys, pdarray):
if keys.dtype != int64:
raise TypeError(
'GroupBy only supports pdarrays with a dtype int64')
self.keys = cast(pdarray, keys)
self.nkeys = 1
self.size = cast(int, keys.size)
if assume_sorted:
self.permutation = cast(pdarray, arange(self.size))
else:
self.permutation = cast(pdarray, argsort(keys))
elif hasattr(keys, "group"): # for Strings or Categorical
self.nkeys = 1
self.keys = cast(Union[Strings, Categorical], keys)
self.size = cast(int, self.keys.size) # type: ignore
if assume_sorted:
self.permutation = cast(pdarray, arange(self.size))
else:
self.permutation = cast(Union[Strings, Categorical],
keys).group()
else:
self.keys = cast(Union[pdarray, Strings, Categorical], keys)
self.nkeys = len(keys)
self.size = cast(int, keys[0].size) # type: ignore
for k in keys:
if k.size != self.size:
raise ValueError("Key arrays must all be same size")
if assume_sorted:
self.permutation = cast(pdarray, arange(self.size))
else:
self.permutation = cast(
pdarray, coargsort(cast(Sequence[pdarray], keys)))
# self.permuted_keys = self.keys[self.permutation]
self.find_segments()
def __init__(self, keys, assume_sorted=False, hash_strings=True):
self.assume_sorted = assume_sorted
self.hash_strings = hash_strings
self.per_locale = False
self.keys = keys
if isinstance(keys, pdarray):
self.nkeys = 1
self.size = keys.size
if assume_sorted:
self.permutation = arange(self.size)
elif self.per_locale:
self.permutation = local_argsort(keys)
else:
self.permutation = argsort(keys)
# for Strings or Categorical
elif hasattr(keys, "group"):
self.nkeys = 1
self.size = keys.size
if assume_sorted:
self.permutation = arange(self.size)
elif self.per_locale:
raise ValueError("per-locale groupby not supported on Strings or Categorical")
else:
self.permutation = keys.group()
else:
self.nkeys = len(keys)
self.size = keys[0].size
for k in keys:
if k.size != self.size:
raise ValueError("Key arrays must all be same size")
if assume_sorted:
self.permutation = arange(self.size)
else:
self.permutation = coargsort(keys)
# self.permuted_keys = self.keys[self.permutation]
self.find_segments()
