def test_index_datetime_nanosecond_a(self) -> None:
index1 = IndexNanosecond(('2020-01-01', '2020-02-01'))
index2 = IndexYearMonth(index1)
self.assertEqual(
index2.values.tolist(),
[datetime.date(2020, 1, 1), datetime.date(2020, 2, 1)]
)
def from_pandas(
cls,
value: 'pandas.DataFrame',
) -> 'IndexBase':
'''
Given a Pandas index, return the appropriate IndexBase derived class.
'''
import pandas
from static_frame import Index
from static_frame import IndexGO
from static_frame import IndexHierarchy
from static_frame import IndexHierarchyGO
from static_frame import IndexNanosecond
from static_frame import IndexNanosecondGO
from static_frame.core.index_datetime import IndexDatetime
if isinstance(value, pandas.MultiIndex):
# iterating over a hierarchucal index will iterate over labels
name = tuple(value.names)
if not cls.STATIC:
return IndexHierarchyGO.from_labels(value, name=name)
return IndexHierarchy.from_labels(value, name=name)
elif isinstance(value, pandas.DatetimeIndex):
# if IndexDatetime, use cls, else use IndexNanosecond
if issubclass(cls, IndexDatetime):
return cls(value, name=value.name)
else:
if not cls.STATIC:
return IndexNanosecondGO(value, name=value.name)
return IndexNanosecond(value, name=value.name)
if not cls.STATIC:
return IndexGO(value, name=value.name)
return Index(value, name=value.name)
def test_index_nanosecond_a(self) -> None:
idx1 = IndexNanosecond(('2018-01-01T03:30', '2018-01-01T03:45', '2019-01-02T03:45'))
self.assertTrue(len(idx1.loc['2019']), 1) #type: ignore
self.assertTrue(len(idx1.loc['2018']), 2) #type: ignore
# NP reduces nanoseconds to integers
self.assertEqual(idx1.values.tolist(),
[1514777400000000000, 1514778300000000000, 1546400700000000000])
def from_pandas(
cls,
value: 'pandas.Index',
) -> 'IndexBase':
'''
Given a Pandas index, return the appropriate IndexBase derived class.
'''
import pandas
if not isinstance(value, pandas.Index):
raise ErrorInitIndex(
f'from_pandas must be called with a Pandas Index object, not: {type(value)}'
)
from static_frame import Index
from static_frame import IndexGO
from static_frame import IndexHierarchy
from static_frame import IndexHierarchyGO
from static_frame import IndexNanosecond
from static_frame import IndexNanosecondGO
from static_frame.core.index_datetime import IndexDatetime
if isinstance(value, pandas.MultiIndex):
# iterating over a hierarchical index will iterate over labels
name: tp.Optional[tp.Tuple[tp.Hashable, ...]] = tuple(value.names)
# if not assigned Pandas returns None for all components, which will raise issue if trying to unset this index.
if all(n is None for n in name): #type: ignore
name = None
depth = value.nlevels
if not cls.STATIC:
return IndexHierarchyGO.from_labels(value,
name=name,
depth_reference=depth)
return IndexHierarchy.from_labels(value,
name=name,
depth_reference=depth)
elif isinstance(value, pandas.DatetimeIndex):
# if IndexDatetime, use cls, else use IndexNanosecond
if issubclass(cls, IndexDatetime):
return cls(value, name=value.name)
else:
if not cls.STATIC:
return IndexNanosecondGO(value, name=value.name)
return IndexNanosecond(value, name=value.name)
if not cls.STATIC:
return IndexGO(value, name=value.name)
return Index(value, name=value.name)
def from_pandas(cls,
value: 'pandas.Index',
) -> 'IndexBase':
'''
Given a Pandas index, return the appropriate IndexBase derived class.
'''
import pandas
if not isinstance(value, pandas.Index):
raise ErrorInitIndex(f'from_pandas must be called with a Pandas Index object, not: {type(value)}')
from static_frame import Index
from static_frame import IndexGO
from static_frame import IndexHierarchy
from static_frame import IndexHierarchyGO
from static_frame import IndexNanosecond
from static_frame import IndexNanosecondGO
from static_frame.core.index_datetime import IndexDatetime
if isinstance(value, pandas.MultiIndex):
if value.has_duplicates:
raise ErrorInitIndex(f'cannot create IndexHierarchy from a MultiIndex with duplicates: {value}')
# iterating over a hierarchical index will iterate over labels
name: tp.Optional[tp.Tuple[tp.Hashable, ...]] = tuple(value.names)
# if not assigned Pandas returns None for all components, which will raise issue if trying to unset this index.
if all(n is None for n in name): #type: ignore
name = None
hierarchy_constructor = IndexHierarchy if cls.STATIC else IndexHierarchyGO
def build_index(pd_idx: pandas.Index) -> Index:
# NOTE: Newer versions of pandas will not require Python date objects to live inside
# a DatetimeIndex. Instead, it will be a regular Index with dtype=object.
# Only numpy datetime objects are put into a DatetimeIndex.
if isinstance(pd_idx, pandas.DatetimeIndex):
constructor: tp.Type[Index] = IndexNanosecond
else:
constructor = Index
if cls.STATIC:
return constructor(pd_idx, name=pd_idx.name)
return tp.cast(Index, constructor._MUTABLE_CONSTRUCTOR(pd_idx))
indices: tp.List[Index] = []
indexers: np.ndarray = np.empty((value.nlevels, len(value)), dtype=DTYPE_INT_DEFAULT)
for i, (levels, codes) in enumerate(zip(value.levels, value.codes)):
indexers[i] = codes
indices.append(build_index(levels))
indexers.flags.writeable = False
return hierarchy_constructor(
indices=indices,
indexers=indexers,
name=name,
)
elif isinstance(value, pandas.DatetimeIndex):
# if IndexDatetime, use cls, else use IndexNanosecond
if issubclass(cls, IndexDatetime):
return cls(value, name=value.name)
else:
if not cls.STATIC:
return IndexNanosecondGO(value, name=value.name)
return IndexNanosecond(value, name=value.name)
if not cls.STATIC:
return IndexGO(value, name=value.name)
return Index(value, name=value.name)