def _maybe_convert_i8(self, key):
"""
Maybe convert a given key to its equivalent i8 value(s). Used as a
preprocessing step prior to IntervalTree queries (self._engine), which
expects numeric data.
Parameters
----------
key : scalar or list-like
The key that should maybe be converted to i8.
Returns
-------
scalar or list-like
The original key if no conversion occurred, int if converted scalar,
Int64Index if converted list-like.
"""
original = key
if is_list_like(key):
key = ensure_index(key)
if not self._needs_i8_conversion(key):
return original
scalar = is_scalar(key)
if is_interval_dtype(key) or isinstance(key, Interval):
# convert left/right and reconstruct
left = self._maybe_convert_i8(key.left)
right = self._maybe_convert_i8(key.right)
constructor = Interval if scalar else IntervalIndex.from_arrays
return constructor(left, right, closed=self.closed)
if scalar:
# Timestamp/Timedelta
key_dtype, key_i8 = infer_dtype_from_scalar(key, pandas_dtype=True)
if lib.is_period(key):
key_i8 = key.ordinal
elif isinstance(key_i8, Timestamp):
key_i8 = key_i8.value
elif isinstance(key_i8, (np.datetime64, np.timedelta64)):
key_i8 = key_i8.view("i8")
else:
# DatetimeIndex/TimedeltaIndex
key_dtype, key_i8 = key.dtype, Index(key.asi8)
if key.hasnans:
# convert NaT from its i8 value to np.nan so it's not viewed
# as a valid value, maybe causing errors (e.g. is_overlapping)
key_i8 = key_i8.where(~key._isnan)
# ensure consistency with IntervalIndex subtype
# error: Item "ExtensionDtype"/"dtype[Any]" of "Union[dtype[Any],
# ExtensionDtype]" has no attribute "subtype"
subtype = self.dtype.subtype # type: ignore[union-attr]
if not is_dtype_equal(subtype, key_dtype):
raise ValueError(
f"Cannot index an IntervalIndex of subtype {subtype} with "
f"values of dtype {key_dtype}")
return key_i8
def infer_dtype_from_scalar(val, pandas_dtype=False):
"""
interpret the dtype from a scalar
Parameters
----------
pandas_dtype : bool, default False
whether to infer dtype including pandas extension types.
If False, scalar belongs to pandas extension types is inferred as
object
"""
dtype = np.object_
# a 1-element ndarray
if isinstance(val, np.ndarray):
msg = "invalid ndarray passed to infer_dtype_from_scalar"
if val.ndim != 0:
raise ValueError(msg)
dtype = val.dtype
val = val.item()
elif isinstance(val, str):
# If we create an empty array using a string to infer
# the dtype, NumPy will only allocate one character per entry
# so this is kind of bad. Alternately we could use np.repeat
# instead of np.empty (but then you still don't want things
# coming out as np.str_!
dtype = np.object_
elif isinstance(val, (np.datetime64, datetime)):
val = tslibs.Timestamp(val)
if val is tslibs.NaT or val.tz is None:
dtype = np.dtype("M8[ns]")
else:
if pandas_dtype:
dtype = DatetimeTZDtype(unit="ns", tz=val.tz)
else:
# return datetimetz as object
return np.object_, val
val = val.value
elif isinstance(val, (np.timedelta64, timedelta)):
val = tslibs.Timedelta(val).value
dtype = np.dtype("m8[ns]")
elif is_bool(val):
dtype = np.bool_
elif is_integer(val):
if isinstance(val, np.integer):
dtype = type(val)
else:
dtype = np.int64
elif is_float(val):
if isinstance(val, np.floating):
dtype = type(val)
else:
dtype = np.float64
elif is_complex(val):
dtype = np.complex_
elif pandas_dtype:
if lib.is_period(val):
dtype = PeriodDtype(freq=val.freq)
val = val.ordinal
return dtype, val
def test_is_period(self):
assert lib.is_period(pd.Period('2011-01', freq='M'))
assert not lib.is_period(pd.PeriodIndex(['2011-01'], freq='M'))
assert not lib.is_period(pd.Timestamp('2011-01'))
assert not lib.is_period(1)
assert not lib.is_period(np.nan)
def test_is_period(self):
assert lib.is_period(pd.Period('2011-01', freq='M'))
assert not lib.is_period(pd.PeriodIndex(['2011-01'], freq='M'))
assert not lib.is_period(pd.Timestamp('2011-01'))
assert not lib.is_period(1)
assert not lib.is_period(np.nan)
def infer_dtype_from_scalar(val, pandas_dtype=False):
"""
interpret the dtype from a scalar
Parameters
----------
pandas_dtype : bool, default False
whether to infer dtype including pandas extension types.
If False, scalar belongs to pandas extension types is inferred as
object
"""
dtype = np.object_
# a 1-element ndarray
if isinstance(val, np.ndarray):
msg = "invalid ndarray passed to _infer_dtype_from_scalar"
if val.ndim != 0:
raise ValueError(msg)
dtype = val.dtype
val = val.item()
elif isinstance(val, string_types):
# If we create an empty array using a string to infer
# the dtype, NumPy will only allocate one character per entry
# so this is kind of bad. Alternately we could use np.repeat
# instead of np.empty (but then you still don't want things
# coming out as np.str_!
dtype = np.object_
elif isinstance(val, (np.datetime64, datetime)):
val = tslib.Timestamp(val)
if val is tslib.NaT or val.tz is None:
dtype = np.dtype('M8[ns]')
else:
if pandas_dtype:
dtype = DatetimeTZDtype(unit='ns', tz=val.tz)
else:
# return datetimetz as object
return np.object_, val
val = val.value
elif isinstance(val, (np.timedelta64, timedelta)):
val = tslib.Timedelta(val).value
dtype = np.dtype('m8[ns]')
elif is_bool(val):
dtype = np.bool_
elif is_integer(val):
if isinstance(val, np.integer):
dtype = type(val)
else:
dtype = np.int64
elif is_float(val):
if isinstance(val, np.floating):
dtype = type(val)
else:
dtype = np.float64
elif is_complex(val):
dtype = np.complex_
elif pandas_dtype:
if lib.is_period(val):
dtype = PeriodDtype(freq=val.freq)
val = val.ordinal
return dtype, val
def test_is_period(self):
assert lib.is_period(pd.Period("2011-01", freq="M"))
assert not lib.is_period(pd.PeriodIndex(["2011-01"], freq="M"))
assert not lib.is_period(pd.Timestamp("2011-01"))
assert not lib.is_period(1)
assert not lib.is_period(np.nan)
def test_is_period(self):
self.assertTrue(lib.is_period(pd.Period('2011-01', freq='M')))
self.assertFalse(lib.is_period(pd.PeriodIndex(['2011-01'], freq='M')))
self.assertFalse(lib.is_period(pd.Timestamp('2011-01')))
self.assertFalse(lib.is_period(1))
self.assertFalse(lib.is_period(np.nan))
def test_is_period(self):
self.assertTrue(lib.is_period(pd.Period('2011-01', freq='M')))
self.assertFalse(lib.is_period(pd.PeriodIndex(['2011-01'], freq='M')))
self.assertFalse(lib.is_period(pd.Timestamp('2011-01')))
self.assertFalse(lib.is_period(1))
self.assertFalse(lib.is_period(np.nan))
