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 __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()
