def __init__(self, values, **kwargs):
if 'codes' in kwargs and 'categories' in kwargs:
# This initialization is called by Categorical.from_codes()
# The values arg is ignored
self.codes = kwargs['codes']
self.categories = kwargs['categories']
if 'permutation' in kwargs:
self.permutation = kwargs['permutation']
if 'segments' in kwargs:
self.segments = kwargs['segments']
else:
# Typical initialization, called with values
if not isinstance(values, Strings):
raise ValueError("Categorical: inputs other than Strings not yet supported")
g = GroupBy(values)
self.categories = g.unique_keys
self.codes = zeros(values.size, dtype=int64)
self.codes[g.permutation] = g.broadcast(arange(self.categories.size))
self.permutation = g.permutation
self.segments = g.segments
# Always set these values
self.size = self.codes.size
self.nlevels = self.categories.size
self.ndim = self.codes.ndim
self.shape = self.codes.shape
def __init__(self, values, **kwargs) -> None:
self.logger = getArkoudaLogger(name=__class__.__name__) # type: ignore
if 'codes' in kwargs and 'categories' in kwargs:
# This initialization is called by Categorical.from_codes()
# The values arg is ignored
self.codes = kwargs['codes']
self.categories = kwargs['categories']
if 'permutation' in kwargs:
self.permutation = cast(pdarray, kwargs['permutation'])
if 'segments' in kwargs:
self.segments = cast(pdarray, kwargs['segments'])
else:
# Typical initialization, called with values
if not isinstance(values, Strings):
raise ValueError(("Categorical: inputs other than " +
"Strings not yet supported"))
g = GroupBy(values)
self.categories = g.unique_keys
self.codes = g.broadcast(arange(self.categories.size),
permute=True)
self.permutation = cast(pdarray, g.permutation)
self.segments = g.segments
# Always set these values
self.size: int_scalars = self.codes.size
self.nlevels = self.categories.size
self.ndim = self.codes.ndim
self.shape = self.codes.shape
self.name: Optional[str] = None
def reset_categories(self):
"""
Recompute the category labels, discarding any unused labels. This method
is often useful after slicing or indexing a Categorical array, when the
resulting array only contains a subset of the original categories. In
this case, eliminating unused categories can speed up other operations.
"""
g = GroupBy(self.codes)
idx = self.categories[g.unique_keys]
newvals = zeros(self.codes.size, int64)
newvals[g.permutation] = g.broadcast(arange(idx.size))
return Categorical.from_codes(newvals, idx, permutation=g.permutation, segments=g.segments)
def reset_categories(self) -> Categorical:
"""
Recompute the category labels, discarding any unused labels. This
method is often useful after slicing or indexing a Categorical array,
when the resulting array only contains a subset of the original
categories. In this case, eliminating unused categories can speed up
other operations.
Returns
-------
Categorical
A Categorical object generated from the current instance
"""
g = GroupBy(self.codes)
idx = self.categories[g.unique_keys]
newvals = g.broadcast(arange(idx.size), permute=True)
return Categorical.from_codes(newvals,
idx,
permutation=g.permutation,
segments=g.segments)
def concatenate(self,
others: Sequence[Categorical],
ordered: bool = True) -> Categorical:
"""
Merge this Categorical with other Categorical objects in the array,
concatenating the arrays and synchronizing the categories.
Parameters
----------
others : Sequence[Categorical]
The Categorical arrays to concatenate and merge with this one
ordered : bool
If True (default), the arrays will be appended in the
order given. If False, array data may be interleaved
in blocks, which can greatly improve performance but
results in non-deterministic ordering of elements.
Returns
-------
Categorical
The merged Categorical object
Raises
------
TypeError
Raised if any others array objects are not Categorical objects
Notes
-----
This operation can be expensive -- slower than concatenating Strings.
"""
if isinstance(others, Categorical):
others = [others]
elif len(others) < 1:
return self
samecategories = True
for c in others:
if not isinstance(c, Categorical):
raise TypeError(("Categorical: can only merge/concatenate " +
"with other Categoricals"))
if (self.categories.size != c.categories.size) or not \
(self.categories == c.categories).all():
samecategories = False
if samecategories:
newvals = cast(
pdarray,
concatenate([self.codes] + [o.codes for o in others],
ordered=ordered))
return Categorical.from_codes(newvals, self.categories)
else:
g = GroupBy(concatenate([self.categories] + \
[o.categories for o in others],
ordered=True))
newidx = g.unique_keys
wherediditgo = g.broadcast(arange(newidx.size), permute=True)
idxsizes = np.array([self.categories.size] + \
[o.categories.size for o in others])
idxoffsets = np.cumsum(idxsizes) - idxsizes
oldvals = concatenate([c + off for c, off in \
zip([self.codes] + [o.codes for o in others], idxoffsets)],
ordered=ordered)
newvals = wherediditgo[oldvals]
return Categorical.from_codes(newvals, newidx)
