def from_array(cls, data):
try:
labels, levels, _ = factorize(data, sort=True)
except TypeError:
labels, levels, _ = factorize(data, sort=False)
return Categorical(labels, levels, name=getattr(data, "name", None))
def test_datelike(self):
# M8
v1 = pd.Timestamp('20130101 09:00:00.00004')
v2 = pd.Timestamp('20130101')
x = Series([v1, v1, v1, v2, v2, v1])
labels, uniques = algos.factorize(x)
self.assert_numpy_array_equal(labels, np.array(
[0, 0, 0, 1, 1, 0], dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array(
[v1.value, v2.value], dtype='M8[ns]'))
labels, uniques = algos.factorize(x, sort=True)
self.assert_numpy_array_equal(labels, np.array(
[1, 1, 1, 0, 0, 1], dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array(
[v2.value, v1.value], dtype='M8[ns]'))
# period
v1 = pd.Period('201302', freq='M')
v2 = pd.Period('201303', freq='M')
x = Series([v1, v1, v1, v2, v2, v1])
# periods are not 'sorted' as they are converted back into an index
labels, uniques = algos.factorize(x)
self.assert_numpy_array_equal(labels, np.array(
[0, 0, 0, 1, 1, 0], dtype=np.int64))
self.assert_numpy_array_equal(uniques, pd.PeriodIndex([v1, v2]))
labels, uniques = algos.factorize(x, sort=True)
self.assert_numpy_array_equal(labels, np.array(
[0, 0, 0, 1, 1, 0], dtype=np.int64))
self.assert_numpy_array_equal(uniques, pd.PeriodIndex([v1, v2]))
def from_array(cls, data):
try:
labels, levels, _ = factorize(data, sort=True)
except TypeError:
labels, levels, _ = factorize(data, sort=False)
return Factor(labels, levels)
def from_array(cls, data):
from pandas.core.algorithms import factorize
try:
labels, levels, _ = factorize(data, sort=True)
except TypeError:
labels, levels, _ = factorize(data, sort=False)
return Factor(labels, levels)
def from_array(cls, data):
if isinstance(data, Index) and hasattr(data, 'factorize'):
labels, levels = data.factorize()
else:
try:
labels, levels = factorize(data, sort=True)
except TypeError:
labels, levels = factorize(data, sort=False)
return Categorical(labels, levels,
name=getattr(data, 'name', None))
def __init__(self, labels, levels=None, name=None):
if levels is None:
if name is None:
name = getattr(labels, 'name', None)
try:
labels, levels = factorize(labels, sort=True)
except TypeError:
labels, levels = factorize(labels, sort=False)
self.labels = labels
self.levels = levels
self.name = name
def test_mixed(self):
# doc example reshaping.rst
x = Series(['A', 'A', np.nan, 'B', 3.14, np.inf])
labels, uniques = algos.factorize(x)
self.assert_numpy_array_equal(labels, np.array([ 0, 0, -1, 1, 2, 3],dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array(['A', 'B', 3.14, np.inf], dtype=object))
labels, uniques = algos.factorize(x, sort=True)
self.assert_numpy_array_equal(labels, np.array([ 2, 2, -1, 3, 0, 1],dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array([3.14, np.inf, 'A', 'B'], dtype=object))
def __new__(cls, data):
from pandas.core.index import _ensure_index
from pandas.core.algorithms import factorize
try:
labels, levels, _ = factorize(data, sort=True)
except TypeError:
labels, levels, _ = factorize(data, sort=False)
labels = labels.view(Factor)
labels.levels = _ensure_index(levels)
return labels
def __init__(self, labels, levels=None, name=None):
if levels is None:
if name is None:
name = getattr(labels, 'name', None)
if isinstance(labels, Index) and hasattr(labels, 'factorize'):
labels, levels = labels.factorize()
else:
try:
labels, levels = factorize(labels, sort=True)
except TypeError:
labels, levels = factorize(labels, sort=False)
self.labels = labels
self.levels = levels
self.name = name
def __init__(self, labels, levels=None, name=None):
if levels is None:
if name is None:
name = getattr(labels, 'name', None)
if isinstance(labels, Index) and hasattr(labels, 'factorize'):
labels, levels = labels.factorize()
else:
try:
labels, levels = factorize(labels, sort=True)
except TypeError:
labels, levels = factorize(labels, sort=False)
self.labels = labels
self.levels = levels
self.name = name
def _codes_and_uniques(self) -> tuple[np.ndarray, ArrayLike]:
if self._passed_categorical:
# we make a CategoricalIndex out of the cat grouper
# preserving the categories / ordered attributes
cat = self.grouper
categories = cat.categories
if self.observed:
ucodes = algorithms.unique1d(cat.codes)
ucodes = ucodes[ucodes != -1]
if self.sort or cat.ordered:
ucodes = np.sort(ucodes)
else:
ucodes = np.arange(len(categories))
uniques = Categorical.from_codes(
codes=ucodes, categories=categories, ordered=cat.ordered
)
return cat.codes, uniques
elif isinstance(self.grouper, ops.BaseGrouper):
# we have a list of groupers
codes = self.grouper.codes_info
uniques = self.grouper.result_arraylike
else:
# GH35667, replace dropna=False with na_sentinel=None
if not self.dropna:
na_sentinel = None
else:
na_sentinel = -1
codes, uniques = algorithms.factorize(
self.grouper, sort=self.sort, na_sentinel=na_sentinel
)
return codes, uniques
def test_mixed(self):
# doc example reshaping.rst
x = Series(['A', 'A', np.nan, 'B', 3.14, np.inf])
labels, uniques = algos.factorize(x)
self.assert_numpy_array_equal(labels, np.array(
[0, 0, -1, 1, 2, 3], dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array(
['A', 'B', 3.14, np.inf], dtype=object))
labels, uniques = algos.factorize(x, sort=True)
self.assert_numpy_array_equal(labels, np.array(
[2, 2, -1, 3, 0, 1], dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array(
[3.14, np.inf, 'A', 'B'], dtype=object))
def test_mixed(self):
# doc example reshaping.rst
x = Series(['A', 'A', np.nan, 'B', 3.14, np.inf])
labels, uniques = algos.factorize(x)
exp = np.array([0, 0, -1, 1, 2, 3], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
exp = pd.Index(['A', 'B', 3.14, np.inf])
tm.assert_index_equal(uniques, exp)
labels, uniques = algos.factorize(x, sort=True)
exp = np.array([2, 2, -1, 3, 0, 1], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
exp = pd.Index([3.14, np.inf, 'A', 'B'])
tm.assert_index_equal(uniques, exp)
def test_mixed(self):
# doc example reshaping.rst
x = Series(['A', 'A', np.nan, 'B', 3.14, np.inf])
labels, uniques = algos.factorize(x)
exp = np.array([0, 0, -1, 1, 2, 3], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
exp = pd.Index(['A', 'B', 3.14, np.inf])
tm.assert_index_equal(uniques, exp)
labels, uniques = algos.factorize(x, sort=True)
exp = np.array([2, 2, -1, 3, 0, 1], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
exp = pd.Index([3.14, np.inf, 'A', 'B'])
tm.assert_index_equal(uniques, exp)
def factorize(self):
"""
Specialized factorize that boxes uniques
"""
from pandas.core.algorithms import factorize
labels, uniques = factorize(self.values)
uniques = PeriodIndex(ordinal=uniques, freq=self.freq)
return labels, uniques
def factorize(self):
"""
Specialized factorize that boxes uniques
"""
from pandas.core.algorithms import factorize
labels, uniques, counts = factorize(self.values)
uniques = PeriodIndex(ordinal=uniques, freq=self.freq)
return labels, uniques
def factorize(
self,
sort: bool = False,
na_sentinel: int | lib.NoDefault = lib.no_default,
use_na_sentinel: bool | lib.NoDefault = lib.no_default,
):
return algorithms.factorize(
self, sort=sort, na_sentinel=na_sentinel, use_na_sentinel=use_na_sentinel
)
def factorize(self, na_sentinel=-1):
# Currently, ExtensionArray.factorize -> Tuple[ndarray, EA]
# The sparsity on this is backwards from what Sparse would want. Want
# ExtensionArray.factorize -> Tuple[EA, EA]
# Given that we have to return a dense array of codes, why bother
# implementing an efficient factorize?
codes, uniques = algos.factorize(np.asarray(self), na_sentinel=na_sentinel)
uniques = SparseArray(uniques, dtype=self.dtype)
return codes, uniques
def from_array(cls, data):
"""
Make a Categorical type from a single array-like object.
Parameters
----------
data : array-like
Can be an Index or array-like. The levels are assumed to be
the unique values of `data`.
"""
if isinstance(data, Index) and hasattr(data, 'factorize'):
labels, levels = data.factorize()
else:
try:
labels, levels = factorize(data, sort=True)
except TypeError:
labels, levels = factorize(data, sort=False)
return Categorical(labels, levels, name=getattr(data, 'name', None))
def _make_labels(self):
if self._was_factor: # pragma: no cover
raise Exception('Should not call this method grouping by level')
else:
labs, uniques, counts = algos.factorize(self.grouper,
sort=self.sort)
uniques = Index(uniques, name=self.name)
self._labels = labs
self._group_index = uniques
self._counts = counts
def _make_labels(self):
if self._was_factor: # pragma: no cover
raise Exception('Should not call this method grouping by level')
else:
labs, uniques, counts = algos.factorize(self.grouper,
sort=self.sort)
uniques = Index(uniques, name=self.name)
self._labels = labs
self._group_index = uniques
self._counts = counts
def from_array(cls, data):
"""
Make a Categorical type from a single array-like object.
Parameters
----------
data : array-like
Can be an Index or array-like. The levels are assumed to be
the unique values of `data`.
"""
if isinstance(data, Index) and hasattr(data, "factorize"):
labels, levels = data.factorize()
else:
try:
labels, levels = factorize(data, sort=True)
except TypeError:
labels, levels = factorize(data, sort=False)
return Categorical(labels, levels, name=getattr(data, "name", None))
def _make_labels(self):
if self._labels is None or self._group_index is None:
# we have a list of groupers
if isinstance(self.grouper, BaseGrouper):
labels = self.grouper.label_info
uniques = self.grouper.result_index
else:
labels, uniques = algorithms.factorize(self.grouper, sort=self.sort)
uniques = Index(uniques, name=self.name)
self._labels = labels
self._group_index = uniques
def _make_codes(self) -> None:
if self._codes is None or self._group_index is None:
# we have a list of groupers
if isinstance(self.grouper, ops.BaseGrouper):
codes = self.grouper.codes_info
uniques = self.grouper.result_index
else:
codes, uniques = algorithms.factorize(self.grouper, sort=self.sort)
uniques = Index(uniques, name=self.name)
self._codes = codes
self._group_index = uniques
def _make_labels(self):
if self._labels is None or self._group_index is None:
# we have a list of groupers
if isinstance(self.grouper, BaseGrouper):
labels = self.grouper.label_info
uniques = self.grouper.result_index
else:
labels, uniques = algorithms.factorize(
self.grouper, sort=self.sort)
uniques = Index(uniques, name=self.name)
self._labels = labels
self._group_index = uniques
def indices(self):
# we have a list of groupers
if isinstance(self.grouper, ops.BaseGrouper):
return self.grouper.indices
# Return a dictionary of {group label: [indices belonging to the group label]}
# respecting whether sort was specified
codes, uniques = algorithms.factorize(self.grouper, sort=self.sort)
return {
category: np.flatnonzero(codes == i)
for i, category in enumerate(Index(uniques))
}
def test_basic(self):
labels, uniques = algos.factorize(['a', 'b', 'b', 'a',
'a', 'c', 'c', 'c'])
# self.assert_numpy_array_equal(labels, np.array([ 0, 1, 1, 0, 0, 2, 2, 2],dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array(['a','b','c'], dtype=object))
labels, uniques = algos.factorize(['a', 'b', 'b', 'a',
'a', 'c', 'c', 'c'], sort=True)
self.assert_numpy_array_equal(labels, np.array([ 0, 1, 1, 0, 0, 2, 2, 2],dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array(['a','b','c'], dtype=object))
labels, uniques = algos.factorize(list(reversed(range(5))))
self.assert_numpy_array_equal(labels, np.array([0, 1, 2, 3, 4], dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array([ 4, 3, 2, 1, 0],dtype=np.int64))
labels, uniques = algos.factorize(list(reversed(range(5))), sort=True)
self.assert_numpy_array_equal(labels, np.array([ 4, 3, 2, 1, 0],dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array([0, 1, 2, 3, 4], dtype=np.int64))
labels, uniques = algos.factorize(list(reversed(np.arange(5.))))
self.assert_numpy_array_equal(labels, np.array([0., 1., 2., 3., 4.], dtype=np.float64))
self.assert_numpy_array_equal(uniques, np.array([ 4, 3, 2, 1, 0],dtype=np.int64))
labels, uniques = algos.factorize(list(reversed(np.arange(5.))), sort=True)
self.assert_numpy_array_equal(labels, np.array([ 4, 3, 2, 1, 0],dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array([0., 1., 2., 3., 4.], dtype=np.float64))
def test_basic(self):
labels, uniques = algos.factorize(["a", "b", "b", "a", "a", "c", "c", "c"])
# self.assert_numpy_array_equal(labels, np.array([ 0, 1, 1, 0, 0, 2, 2, 2],dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array(["a", "b", "c"], dtype=object))
labels, uniques = algos.factorize(["a", "b", "b", "a", "a", "c", "c", "c"], sort=True)
self.assert_numpy_array_equal(labels, np.array([0, 1, 1, 0, 0, 2, 2, 2], dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array(["a", "b", "c"], dtype=object))
labels, uniques = algos.factorize(list(reversed(range(5))))
self.assert_numpy_array_equal(labels, np.array([0, 1, 2, 3, 4], dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array([4, 3, 2, 1, 0], dtype=np.int64))
labels, uniques = algos.factorize(list(reversed(range(5))), sort=True)
self.assert_numpy_array_equal(labels, np.array([4, 3, 2, 1, 0], dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array([0, 1, 2, 3, 4], dtype=np.int64))
labels, uniques = algos.factorize(list(reversed(np.arange(5.0))))
self.assert_numpy_array_equal(labels, np.array([0.0, 1.0, 2.0, 3.0, 4.0], dtype=np.float64))
self.assert_numpy_array_equal(uniques, np.array([4, 3, 2, 1, 0], dtype=np.int64))
labels, uniques = algos.factorize(list(reversed(np.arange(5.0))), sort=True)
self.assert_numpy_array_equal(labels, np.array([4, 3, 2, 1, 0], dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array([0.0, 1.0, 2.0, 3.0, 4.0], dtype=np.float64))
def test_basic(self):
labels, uniques = algos.factorize(['a', 'b', 'b', 'a',
'a', 'c', 'c', 'c'])
# self.assert_numpy_array_equal(labels, np.array([ 0, 1, 1, 0, 0, 2, 2, 2],dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array(['a','b','c'], dtype=object))
labels, uniques = algos.factorize(['a', 'b', 'b', 'a',
'a', 'c', 'c', 'c'], sort=True)
self.assert_numpy_array_equal(labels, np.array([ 0, 1, 1, 0, 0, 2, 2, 2],dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array(['a','b','c'], dtype=object))
labels, uniques = algos.factorize(list(reversed(range(5))))
self.assert_numpy_array_equal(labels, np.array([0, 1, 2, 3, 4], dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array([ 4, 3, 2, 1, 0],dtype=np.int64))
labels, uniques = algos.factorize(list(reversed(range(5))), sort=True)
self.assert_numpy_array_equal(labels, np.array([ 4, 3, 2, 1, 0],dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array([0, 1, 2, 3, 4], dtype=np.int64))
labels, uniques = algos.factorize(list(reversed(np.arange(5.))))
self.assert_numpy_array_equal(labels, np.array([0., 1., 2., 3., 4.], dtype=np.float64))
self.assert_numpy_array_equal(uniques, np.array([ 4, 3, 2, 1, 0],dtype=np.int64))
labels, uniques = algos.factorize(list(reversed(np.arange(5.))), sort=True)
self.assert_numpy_array_equal(labels, np.array([ 4, 3, 2, 1, 0],dtype=np.int64))
self.assert_numpy_array_equal(uniques, np.array([0., 1., 2., 3., 4.], dtype=np.float64))
def factorize(self,
na_sentinel: int = -1) -> Tuple[np.ndarray, "RLEArray"]:
# optimized version of `ExtensionArray.factorize`:
# 1. replace `_values_for_factorize` with a version that does not decompress the data
# 2. passing compressed data to `factorize` (instead of `_factorize_array` because that does not handle NA
# values nicely)
# 3. decompress `codes`
arr = self._data
codes, uniques = factorize(arr, na_sentinel=na_sentinel)
uniques = self._from_factorized(uniques, self)
codes = decompress(codes, self._positions)
return codes, uniques
def _get_compressed_labels(self):
all_labels = [ping.labels for ping in self.groupings]
if self._overflow_possible:
tups = lib.fast_zip(all_labels)
labs, uniques, _ = algos.factorize(tups)
if self.sort:
uniques, labs = _reorder_by_uniques(uniques, labs)
return labs, uniques
else:
if len(all_labels) > 1:
group_index = get_group_index(all_labels, self.shape)
else:
group_index = all_labels[0]
comp_ids, obs_group_ids = _compress_group_index(group_index)
return comp_ids, obs_group_ids
def _make_codes(self) -> None:
if self._codes is None or self._group_index is None:
# we have a list of groupers
if isinstance(self.grouper, ops.BaseGrouper):
codes = self.grouper.codes_info
uniques = self.grouper.result_index
else:
# GH35667, replace dropna=False with na_sentinel=None
if not self.dropna:
na_sentinel = None
else:
na_sentinel = -1
codes, uniques = algorithms.factorize(self.grouper,
sort=self.sort,
na_sentinel=na_sentinel)
uniques = Index(uniques, name=self.name)
self._codes = codes
self._group_index = uniques
def factorize(self, sort=False, na_sentinel=-1):
"""
Encode the object as an enumerated type or categorical variable
Parameters
----------
sort : boolean, default False
Sort by values
na_sentinel: int, default -1
Value to mark "not found"
Returns
-------
labels : the indexer to the original array
uniques : the unique Index
"""
from pandas.core.algorithms import factorize
return factorize(self, sort=sort, na_sentinel=na_sentinel)
def _levels_to_axis(
ss,
levels: tuple[int] | list[int],
valid_ilocs: npt.NDArray[np.intp],
sort_labels: bool = False,
) -> tuple[npt.NDArray[np.intp], list[IndexLabel]]:
"""
For a MultiIndexed sparse Series `ss`, return `ax_coords` and `ax_labels`,
where `ax_coords` are the coordinates along one of the two axes of the
destination sparse matrix, and `ax_labels` are the labels from `ss`' Index
which correspond to these coordinates.
Parameters
----------
ss : Series
levels : tuple/list
valid_ilocs : numpy.ndarray
Array of integer positions of valid values for the sparse matrix in ss.
sort_labels : bool, default False
Sort the axis labels before forming the sparse matrix. When `levels`
refers to a single level, set to True for a faster execution.
Returns
-------
ax_coords : numpy.ndarray (axis coordinates)
ax_labels : list (axis labels)
"""
# Since the labels are sorted in `Index.levels`, when we wish to sort and
# there is only one level of the MultiIndex for this axis, the desired
# output can be obtained in the following simpler, more efficient way.
if sort_labels and len(levels) == 1:
ax_coords = ss.index.codes[levels[0]][valid_ilocs]
ax_labels = ss.index.levels[levels[0]]
else:
levels_values = lib.fast_zip(
[ss.index.get_level_values(lvl).values for lvl in levels]
)
codes, ax_labels = factorize(levels_values, sort=sort_labels)
ax_coords = codes[valid_ilocs]
ax_labels = ax_labels.tolist()
return ax_coords, ax_labels
def test_datelike(self):
# M8
v1 = pd.Timestamp('20130101 09:00:00.00004')
v2 = pd.Timestamp('20130101')
x = Series([v1, v1, v1, v2, v2, v1])
labels, uniques = algos.factorize(x)
exp = np.array([0, 0, 0, 1, 1, 0], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
exp = pd.DatetimeIndex([v1, v2])
self.assert_index_equal(uniques, exp)
labels, uniques = algos.factorize(x, sort=True)
exp = np.array([1, 1, 1, 0, 0, 1], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
exp = pd.DatetimeIndex([v2, v1])
self.assert_index_equal(uniques, exp)
# period
v1 = pd.Period('201302', freq='M')
v2 = pd.Period('201303', freq='M')
x = Series([v1, v1, v1, v2, v2, v1])
# periods are not 'sorted' as they are converted back into an index
labels, uniques = algos.factorize(x)
exp = np.array([0, 0, 0, 1, 1, 0], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
self.assert_index_equal(uniques, pd.PeriodIndex([v1, v2]))
labels, uniques = algos.factorize(x, sort=True)
exp = np.array([0, 0, 0, 1, 1, 0], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
self.assert_index_equal(uniques, pd.PeriodIndex([v1, v2]))
# GH 5986
v1 = pd.to_timedelta('1 day 1 min')
v2 = pd.to_timedelta('1 day')
x = Series([v1, v2, v1, v1, v2, v2, v1])
labels, uniques = algos.factorize(x)
exp = np.array([0, 1, 0, 0, 1, 1, 0], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
self.assert_index_equal(uniques, pd.to_timedelta([v1, v2]))
labels, uniques = algos.factorize(x, sort=True)
exp = np.array([1, 0, 1, 1, 0, 0, 1], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
self.assert_index_equal(uniques, pd.to_timedelta([v2, v1]))
def test_datelike(self):
# M8
v1 = pd.Timestamp('20130101 09:00:00.00004')
v2 = pd.Timestamp('20130101')
x = Series([v1, v1, v1, v2, v2, v1])
labels, uniques = algos.factorize(x)
exp = np.array([0, 0, 0, 1, 1, 0], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
exp = pd.DatetimeIndex([v1, v2])
self.assert_index_equal(uniques, exp)
labels, uniques = algos.factorize(x, sort=True)
exp = np.array([1, 1, 1, 0, 0, 1], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
exp = pd.DatetimeIndex([v2, v1])
self.assert_index_equal(uniques, exp)
# period
v1 = pd.Period('201302', freq='M')
v2 = pd.Period('201303', freq='M')
x = Series([v1, v1, v1, v2, v2, v1])
# periods are not 'sorted' as they are converted back into an index
labels, uniques = algos.factorize(x)
exp = np.array([0, 0, 0, 1, 1, 0], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
self.assert_index_equal(uniques, pd.PeriodIndex([v1, v2]))
labels, uniques = algos.factorize(x, sort=True)
exp = np.array([0, 0, 0, 1, 1, 0], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
self.assert_index_equal(uniques, pd.PeriodIndex([v1, v2]))
# GH 5986
v1 = pd.to_timedelta('1 day 1 min')
v2 = pd.to_timedelta('1 day')
x = Series([v1, v2, v1, v1, v2, v2, v1])
labels, uniques = algos.factorize(x)
exp = np.array([0, 1, 0, 0, 1, 1, 0], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
self.assert_index_equal(uniques, pd.to_timedelta([v1, v2]))
labels, uniques = algos.factorize(x, sort=True)
exp = np.array([1, 0, 1, 1, 0, 0, 1], dtype=np.int_)
self.assert_numpy_array_equal(labels, exp)
self.assert_index_equal(uniques, pd.to_timedelta([v2, v1]))
def _codes_and_uniques(
self) -> tuple[npt.NDArray[np.signedinteger], ArrayLike]:
if self._passed_categorical:
# we make a CategoricalIndex out of the cat grouper
# preserving the categories / ordered attributes
cat = self.grouping_vector
categories = cat.categories
if self._observed:
ucodes = algorithms.unique1d(cat.codes)
ucodes = ucodes[ucodes != -1]
if self._sort or cat.ordered:
ucodes = np.sort(ucodes)
else:
ucodes = np.arange(len(categories))
uniques = Categorical.from_codes(codes=ucodes,
categories=categories,
ordered=cat.ordered)
return cat.codes, uniques
elif isinstance(self.grouping_vector, ops.BaseGrouper):
# we have a list of groupers
codes = self.grouping_vector.codes_info
# error: Incompatible types in assignment (expression has type "Union
# [ExtensionArray, ndarray[Any, Any]]", variable has type "Categorical")
uniques = (
self.grouping_vector.result_index.
_values # type: ignore[assignment]
)
else:
# GH35667, replace dropna=False with use_na_sentinel=False
# error: Incompatible types in assignment (expression has type "Union[
# ndarray[Any, Any], Index]", variable has type "Categorical")
codes, uniques = algorithms.factorize( # type: ignore[assignment]
self.grouping_vector,
sort=self._sort,
use_na_sentinel=self._dropna)
return codes, uniques
def level_styler(linestyle=None, color=None, marker=None):
"""
This function is useful for categorical plotting. Based on certain categories,
it will return styles that are persistant.
This is when you want to distinguish groups of line plots by their style
"""
vars = locals().copy()
styles = OrderedDict()
for k, SC in STYLES.items():
vals = vars.get(k, None)
if vals is None:
continue
labels, uniques = factorize(vals)
labels = labels % len(SC) # cycle back to start
style_values = np.take(SC, labels)
styles[k] = style_values
keys = styles.keys()
return [dict(zip(keys, st)) for st in itertools.izip(*styles.values())]
def level_styler(linestyle=None, color=None, marker=None):
"""
This function is useful for categorical plotting. Based on certain categories,
it will return styles that are persistant.
This is when you want to distinguish groups of line plots by their style
"""
vars = locals().copy()
styles = OrderedDict()
for k, SC in STYLES.items():
vals = vars.get(k, None)
if vals is None:
continue
labels, uniques = factorize(vals)
labels = labels % len(SC) # cycle back to start
style_values = np.take(SC, labels)
styles[k] = style_values
keys = styles.keys()
return [dict(zip(keys, st)) for st in itertools.izip(*styles.values())]
def f(vals):
labels, shape = _algorithms.factorize(vals,
size_hint=min(
len(df), SIZE_HINT_LIMIT))
return labels.astype("i8", copy=False), len(shape)
def factorize(self, sort: bool = False, na_sentinel: Optional[int] = -1):
return algorithms.factorize(self, sort=sort, na_sentinel=na_sentinel)
def __init__(self, values, categories=None, ordered=None, name=None, fastpath=False,
levels=None):
if fastpath:
# fast path
self._codes = values
self.name = name
self.categories = categories
self.ordered = ordered
return
if name is None:
name = getattr(values, 'name', None)
# TODO: Remove after deprecation period in 2017/ after 0.18
if not levels is None:
warn("Creating a 'Categorical' with 'levels' is deprecated, use 'categories' instead",
FutureWarning)
if categories is None:
categories = levels
else:
raise ValueError("Cannot pass in both 'categories' and (deprecated) 'levels', "
"use only 'categories'")
# sanitize input
if com.is_categorical_dtype(values):
# we are either a Series or a Categorical
cat = values
if isinstance(values, com.ABCSeries):
cat = values.values
if categories is None:
categories = cat.categories
if ordered is None:
ordered = cat.ordered
values = values.__array__()
elif isinstance(values, Index):
pass
else:
# on numpy < 1.6 datetimelike get inferred to all i8 by _sanitize_array
# which is fine, but since factorize does this correctly no need here
# this is an issue because _sanitize_array also coerces np.nan to a string
# under certain versions of numpy as well
values = com._possibly_infer_to_datetimelike(values, convert_dates=True)
if not isinstance(values, np.ndarray):
values = _convert_to_list_like(values)
from pandas.core.series import _sanitize_array
# On list with NaNs, int values will be converted to float. Use "object" dtype
# to prevent this. In the end objects will be casted to int/... in the category
# assignment step.
dtype = 'object' if isnull(values).any() else None
values = _sanitize_array(values, None, dtype=dtype)
if categories is None:
try:
codes, categories = factorize(values, sort=True)
# If the underlying data structure was sortable, and the user doesn't want to
# "forget" this order, the categorical also is sorted/ordered
if ordered is None:
ordered = True
except TypeError:
codes, categories = factorize(values, sort=False)
if ordered:
# raise, as we don't have a sortable data structure and so the user should
# give us one by specifying categories
raise TypeError("'values' is not ordered, please explicitly specify the "
"categories order by passing in a categories argument.")
else:
# there were two ways if categories are present
# - the old one, where each value is a int pointer to the levels array -> not anymore
# possible, but code outside of pandas could call us like that, so make some checks
# - the new one, where each value is also in the categories array (or np.nan)
# make sure that we always have the same type here, no matter what we get passed in
categories = self._validate_categories(categories)
codes = _get_codes_for_values(values, categories)
# TODO: check for old style usage. These warnings should be removes after 0.18/ in 2016
if com.is_integer_dtype(values) and not com.is_integer_dtype(categories):
warn("Values and categories have different dtypes. Did you mean to use\n"
"'Categorical.from_codes(codes, categories)'?", RuntimeWarning)
if com.is_integer_dtype(values) and (codes == -1).all():
warn("None of the categories were found in values. Did you mean to use\n"
"'Categorical.from_codes(codes, categories)'?", RuntimeWarning)
# if we got categories, we can assume that the order is intended
# if ordered is unspecified
if ordered is None:
ordered = True
self.ordered = False if ordered is None else ordered
self._codes = codes
self.categories = categories
self.name = name
def factorize(self, sort=False, na_sentinel=-1):
return algorithms.factorize(self, sort=sort, na_sentinel=na_sentinel)
def test_warn(self):
s = Series([1, 2, 3])
with tm.assert_produces_warning(FutureWarning):
algos.factorize(s, order='A')
def __init__(self, values, categories=None, ordered=None, name=None, fastpath=False,
levels=None):
if fastpath:
# fast path
self._codes = values
self.name = name
self.categories = categories
self.ordered = ordered
return
if name is None:
name = getattr(values, 'name', None)
# TODO: Remove after deprecation period in 2017/ after 0.18
if not levels is None:
warn("Creating a 'Categorical' with 'levels' is deprecated, use 'categories' instead",
FutureWarning)
if categories is None:
categories = levels
else:
raise ValueError("Cannot pass in both 'categories' and (deprecated) 'levels', "
"use only 'categories'")
# sanitize input
if com.is_categorical_dtype(values):
# we are either a Series or a Categorical
cat = values
if isinstance(values, com.ABCSeries):
cat = values.values
if categories is None:
categories = cat.categories
if ordered is None:
ordered = cat.ordered
values = values.__array__()
elif isinstance(values, Index):
pass
else:
# on numpy < 1.6 datetimelike get inferred to all i8 by _sanitize_array
# which is fine, but since factorize does this correctly no need here
# this is an issue because _sanitize_array also coerces np.nan to a string
# under certain versions of numpy as well
values = com._possibly_infer_to_datetimelike(values, convert_dates=True)
if not isinstance(values, np.ndarray):
values = _convert_to_list_like(values)
from pandas.core.series import _sanitize_array
# On list with NaNs, int values will be converted to float. Use "object" dtype
# to prevent this. In the end objects will be casted to int/... in the category
# assignment step.
dtype = 'object' if isnull(values).any() else None
values = _sanitize_array(values, None, dtype=dtype)
if categories is None:
try:
codes, categories = factorize(values, sort=True)
# If the underlying data structure was sortable, and the user doesn't want to
# "forget" this order, the categorical also is sorted/ordered
if ordered is None:
ordered = True
except TypeError:
codes, categories = factorize(values, sort=False)
if ordered:
# raise, as we don't have a sortable data structure and so the user should
# give us one by specifying categories
raise TypeError("'values' is not ordered, please explicitly specify the "
"categories order by passing in a categories argument.")
else:
# there were two ways if categories are present
# - the old one, where each value is a int pointer to the levels array -> not anymore
# possible, but code outside of pandas could call us like that, so make some checks
# - the new one, where each value is also in the categories array (or np.nan)
# make sure that we always have the same type here, no matter what we get passed in
categories = self._validate_categories(categories)
codes = _get_codes_for_values(values, categories)
# TODO: check for old style usage. These warnings should be removes after 0.18/ in 2016
if com.is_integer_dtype(values) and not com.is_integer_dtype(categories):
warn("Values and categories have different dtypes. Did you mean to use\n"
"'Categorical.from_codes(codes, categories)'?", RuntimeWarning)
if com.is_integer_dtype(values) and (codes == -1).all():
warn("None of the categories were found in values. Did you mean to use\n"
"'Categorical.from_codes(codes, categories)'?", RuntimeWarning)
# if we got categories, we can assume that the order is intended
# if ordered is unspecified
if ordered is None:
ordered = True
self.ordered = False if ordered is None else ordered
self._codes = codes
self.categories = categories
self.name = name
def factorize(self, sort: bool = False, na_sentinel: int | None = -1):
return algorithms.factorize(self, sort=sort, na_sentinel=na_sentinel)
def test_warn(self):
s = Series([1, 2, 3])
with tm.assert_produces_warning(FutureWarning):
algos.factorize(s, order='A')
def __init__(self,
values,
levels=None,
ordered=None,
name=None,
fastpath=False,
compat=False):
if fastpath:
# fast path
self._codes = values
self.name = name
self.levels = levels
self.ordered = ordered
return
if name is None:
name = getattr(values, 'name', None)
# sanitize input
if com.is_categorical_dtype(values):
# we are either a Series or a Categorical
cat = values
if isinstance(values, com.ABCSeries):
cat = values.values
if levels is None:
levels = cat.levels
if ordered is None:
ordered = cat.ordered
values = values.__array__()
elif isinstance(values, Index):
pass
else:
# on numpy < 1.6 datetimelike get inferred to all i8 by _sanitize_array
# which is fine, but since factorize does this correctly no need here
# this is an issue because _sanitize_array also coerces np.nan to a string
# under certain versions of numpy as well
values = com._possibly_infer_to_datetimelike(values,
convert_dates=True)
if not isinstance(values, np.ndarray):
values = _convert_to_list_like(values)
from pandas.core.series import _sanitize_array
# On list with NaNs, int values will be converted to float. Use "object" dtype
# to prevent this. In the end objects will be casted to int/... in the level
# assignment step.
dtype = 'object' if isnull(values).any() else None
values = _sanitize_array(values, None, dtype=dtype)
if levels is None:
try:
codes, levels = factorize(values, sort=True)
# If the underlying data structure was sortable, and the user doesn't want to
# "forget" this order, the categorical also is sorted/ordered
if ordered is None:
ordered = True
except TypeError:
codes, levels = factorize(values, sort=False)
if ordered:
# raise, as we don't have a sortable data structure and so the usershould
# give us one by specifying levels
raise TypeError(
"'values' is not ordered, please explicitly specify the level "
"order by passing in a level argument.")
else:
# there are two ways if levels are present
# the old one, where each value is a int pointer to the levels array
# the new one, where each value is also in the level array (or np.nan)
# make sure that we always have the same type here, no matter what we get passed in
levels = self._validate_levels(levels)
# There can be two ways: the old which passed in codes and levels directly
# and values have to be inferred and the new one, which passes in values and levels
# and _codes have to be inferred.
# min and max can be higher and lower if not all levels are in the values
if compat and (com.is_integer_dtype(values) and
(np.min(values) >= -1) and
(np.max(values) < len(levels))):
warn(
"Using 'values' as codes is deprecated.\n"
"'Categorical(... , compat=True)' is only there for historical reasons and "
"should not be used in new code!\n"
"See https://github.com/pydata/pandas/pull/7217",
FutureWarning)
codes = values
else:
codes = _get_codes_for_values(values, levels)
# if we got levels, we can assume that the order is intended
# if ordered is unspecified
if ordered is None:
ordered = True
self.ordered = False if ordered is None else ordered
self._codes = codes
self.levels = levels
self.name = name
def factorize(self, sort=False, na_sentinel=-1):
return algorithms.factorize(self, sort=sort, na_sentinel=na_sentinel)
def __init__(self, values, levels=None, ordered=None, name=None, fastpath=False, compat=False):
if fastpath:
# fast path
self._codes = values
self.name = name
self.levels = levels
self.ordered = ordered
return
if name is None:
name = getattr(values, 'name', None)
# sanitize input
if com.is_categorical_dtype(values):
# we are either a Series or a Categorical
cat = values
if isinstance(values, com.ABCSeries):
cat = values.values
if levels is None:
levels = cat.levels
if ordered is None:
ordered = cat.ordered
values = values.__array__()
elif isinstance(values, Index):
pass
else:
# on numpy < 1.6 datetimelike get inferred to all i8 by _sanitize_array
# which is fine, but since factorize does this correctly no need here
# this is an issue because _sanitize_array also coerces np.nan to a string
# under certain versions of numpy as well
values = com._possibly_infer_to_datetimelike(values)
if not isinstance(values, np.ndarray):
values = _convert_to_list_like(values)
from pandas.core.series import _sanitize_array
# On list with NaNs, int values will be converted to float. Use "object" dtype
# to prevent this. In the end objects will be casted to int/... in the level
# assignment step.
dtype = 'object' if com.isnull(values).any() else None
values = _sanitize_array(values, None, dtype=dtype)
if levels is None:
try:
codes, levels = factorize(values, sort=True)
# If the underlying data structure was sortable, and the user doesn't want to
# "forget" this order, the categorical also is sorted/ordered
if ordered is None:
ordered = True
except TypeError:
codes, levels = factorize(values, sort=False)
if ordered:
# raise, as we don't have a sortable data structure and so the usershould
# give us one by specifying levels
raise TypeError("'values' is not ordered, please explicitly specify the level "
"order by passing in a level argument.")
else:
# there are two ways if levels are present
# the old one, where each value is a int pointer to the levels array
# the new one, where each value is also in the level array (or np.nan)
# make sure that we always have the same type here, no matter what we get passed in
levels = self._validate_levels(levels)
# There can be two ways: the old which passed in codes and levels directly
# and values have to be inferred and the new one, which passes in values and levels
# and _codes have to be inferred.
# min and max can be higher and lower if not all levels are in the values
if compat and (com.is_integer_dtype(values) and
(np.min(values) >= -1) and (np.max(values) < len(levels))):
warn("Using 'values' as codes is deprecated.\n"
"'Categorical(... , compat=True)' is only there for historical reasons and "
"should not be used in new code!\n"
"See https://github.com/pydata/pandas/pull/7217", FutureWarning)
codes = values
else:
codes = _get_codes_for_values(values, levels)
# if we got levels, we can assume that the order is intended
# if ordered is unspecified
if ordered is None:
ordered = True
self.ordered = False if ordered is None else ordered
self._codes = codes
self.levels = levels
self.name = name
