class Indexing(object):
def setup(self):
self.index = PeriodIndex(start='1985', periods=1000, freq='D')
self.series = Series(range(1000), index=self.index)
self.period = self.index[500]
def time_get_loc(self):
self.index.get_loc(self.period)
def time_shape(self):
self.index.shape
def time_shallow_copy(self):
self.index._shallow_copy()
def time_series_loc(self):
self.series.loc[self.period]
def time_align(self):
DataFrame({'a': self.series, 'b': self.series[:500]})
def time_intersection(self):
self.index[:750].intersection(self.index[250:])
def time_unique(self):
self.index.unique()
class Indexing(object):
goal_time = 0.2
def setup(self):
self.index = PeriodIndex(start='1985', periods=1000, freq='D')
self.series = Series(range(1000), index=self.index)
self.period = self.index[500]
def time_get_loc(self):
self.index.get_loc(self.period)
def time_shape(self):
self.index.shape
def time_shallow_copy(self):
self.index._shallow_copy()
def time_series_loc(self):
self.series.loc[self.period]
def time_align(self):
pd.DataFrame({'a': self.series, 'b': self.series[:500]})
def time_intersection(self):
self.index[:750].intersection(self.index[250:])
def test_shallow_copy_empty(self):
# GH13067
idx = PeriodIndex([], freq="M")
result = idx._shallow_copy()
expected = idx
tm.assert_index_equal(result, expected)
def test_shallow_copy_empty(self):
# GH13067
idx = PeriodIndex([], freq='M')
result = idx._shallow_copy()
expected = idx
tm.assert_index_equal(result, expected)
def factorize(values, sort=False, order=None, na_sentinel=-1, size_hint=None):
"""
Encode input values as an enumerated type or categorical variable
Parameters
----------
values : ndarray (1-d)
Sequence
sort : boolean, default False
Sort by values
na_sentinel : int, default -1
Value to mark "not found"
size_hint : hint to the hashtable sizer
Returns
-------
labels : the indexer to the original array
uniques : ndarray (1-d) or Index
the unique values. Index is returned when passed values is Index or
Series
note: an array of Periods will ignore sort as it returns an always sorted
PeriodIndex
"""
from pandas import Index, Series, DatetimeIndex, PeriodIndex
# handling two possibilities here
# - for a numpy datetimelike simply view as i8 then cast back
# - for an extension datetimelike view as i8 then
# reconstruct from boxed values to transfer metadata
dtype = None
if needs_i8_conversion(values):
if is_period_dtype(values):
values = PeriodIndex(values)
vals = values.asi8
elif is_datetimetz(values):
values = DatetimeIndex(values)
vals = values.asi8
else:
# numpy dtype
dtype = values.dtype
vals = values.view(np.int64)
else:
vals = np.asarray(values)
(hash_klass, vec_klass), vals = _get_data_algo(vals, _hashtables)
table = hash_klass(size_hint or len(vals))
uniques = vec_klass()
labels = table.get_labels(vals, uniques, 0, na_sentinel, True)
labels = _ensure_platform_int(labels)
uniques = uniques.to_array()
if sort and len(uniques) > 0:
uniques, labels = safe_sort(uniques,
labels,
na_sentinel=na_sentinel,
assume_unique=True)
if dtype is not None:
uniques = uniques.astype(dtype)
if isinstance(values, Index):
uniques = values._shallow_copy(uniques, name=None)
elif isinstance(values, Series):
uniques = Index(uniques)
return labels, uniques
def factorize(values, sort=False, order=None, na_sentinel=-1, size_hint=None):
"""
Encode input values as an enumerated type or categorical variable
Parameters
----------
values : ndarray (1-d)
Sequence
sort : boolean, default False
Sort by values
na_sentinel : int, default -1
Value to mark "not found"
size_hint : hint to the hashtable sizer
Returns
-------
labels : the indexer to the original array
uniques : ndarray (1-d) or Index
the unique values. Index is returned when passed values is Index or
Series
note: an array of Periods will ignore sort as it returns an always sorted
PeriodIndex
"""
from pandas import Index, Series, DatetimeIndex, PeriodIndex
# handling two possibilities here
# - for a numpy datetimelike simply view as i8 then cast back
# - for an extension datetimelike view as i8 then
# reconstruct from boxed values to transfer metadata
dtype = None
if needs_i8_conversion(values):
if is_period_dtype(values):
values = PeriodIndex(values)
vals = values.asi8
elif is_datetimetz(values):
values = DatetimeIndex(values)
vals = values.asi8
else:
# numpy dtype
dtype = values.dtype
vals = values.view(np.int64)
else:
vals = np.asarray(values)
(hash_klass, vec_klass), vals = _get_data_algo(vals, _hashtables)
table = hash_klass(size_hint or len(vals))
uniques = vec_klass()
check_nulls = not is_integer_dtype(values)
labels = table.get_labels(vals, uniques, 0, na_sentinel, check_nulls)
labels = _ensure_platform_int(labels)
uniques = uniques.to_array()
if sort and len(uniques) > 0:
uniques, labels = safe_sort(uniques, labels, na_sentinel=na_sentinel,
assume_unique=True)
if dtype is not None:
uniques = uniques.astype(dtype)
if isinstance(values, Index):
uniques = values._shallow_copy(uniques, name=None)
elif isinstance(values, Series):
uniques = Index(uniques)
return labels, uniques