def test_shift2(self):
ts = Series(np.random.randn(5),
index=date_range('1/1/2000', periods=5, freq='H'))
result = ts.shift(1, freq='5T')
exp_index = ts.index.shift(1, freq='5T')
tm.assert_index_equal(result.index, exp_index)
# GH #1063, multiple of same base
result = ts.shift(1, freq='4H')
exp_index = ts.index + offsets.Hour(4)
tm.assert_index_equal(result.index, exp_index)
idx = DatetimeIndex(['2000-01-01', '2000-01-02', '2000-01-04'])
msg = "Cannot shift with no freq"
with pytest.raises(NullFrequencyError, match=msg):
idx.shift(1)
def to_timestamp(self, freq=None, how='start'):
from pandas import DatetimeIndex
result = self._data.to_timestamp(freq=freq, how=how)
return DatetimeIndex._simple_new(result.asi8,
name=self.name,
freq=result.freq)
def _convert_listlike(arg, box, format, name=None, tz=tz):
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype='O')
# these are shortcutable
if is_datetime64tz_dtype(arg):
if not isinstance(arg, DatetimeIndex):
return DatetimeIndex(arg, tz=tz, name=name)
if utc:
arg = arg.tz_convert(None).tz_localize('UTC')
return arg
elif is_datetime64_ns_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg, tz=tz, name=name)
except ValueError:
pass
return arg
elif unit is not None:
if format is not None:
raise ValueError("cannot specify both format and unit")
arg = getattr(arg, 'values', arg)
result = tslib.array_with_unit_to_datetime(arg, unit,
errors=errors)
if box:
if errors == 'ignore':
from pandas import Index
return Index(result)
return DatetimeIndex(result, tz=tz, name=name)
return result
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a string, datetime, list, tuple, '
'1-d array, or Series')
arg = _ensure_object(arg)
require_iso8601 = False
if infer_datetime_format and format is None:
format = _guess_datetime_format_for_array(arg, dayfirst=dayfirst)
if format is not None:
# There is a special fast-path for iso8601 formatted
# datetime strings, so in those cases don't use the inferred
# format because this path makes process slower in this
# special case
format_is_iso8601 = _format_is_iso(format)
if format_is_iso8601:
require_iso8601 = not infer_datetime_format
format = None
try:
result = None
if format is not None:
# shortcut formatting here
if format == '%Y%m%d':
try:
result = _attempt_YYYYMMDD(arg, errors=errors)
except:
raise ValueError("cannot convert the input to "
"'%Y%m%d' date format")
# fallback
if result is None:
try:
result = array_strptime(arg, format, exact=exact,
errors=errors)
except tslib.OutOfBoundsDatetime:
if errors == 'raise':
raise
result = arg
except ValueError:
# if format was inferred, try falling back
# to array_to_datetime - terminate here
# for specified formats
if not infer_datetime_format:
if errors == 'raise':
raise
result = arg
if result is None and (format is None or infer_datetime_format):
result = tslib.array_to_datetime(
arg,
errors=errors,
utc=utc,
dayfirst=dayfirst,
yearfirst=yearfirst,
require_iso8601=require_iso8601
)
if is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz=tz, name=name)
return result
except ValueError as e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, name=name, tz=tz)
except (ValueError, TypeError):
raise e
def test_to_datetime_unit(self):
epoch = 1370745748
s = Series([epoch + t for t in range(20)])
result = to_datetime(s, unit='s')
expected = Series([
Timestamp('2013-06-09 02:42:28') + timedelta(seconds=t)
for t in range(20)
])
assert_series_equal(result, expected)
s = Series([epoch + t for t in range(20)]).astype(float)
result = to_datetime(s, unit='s')
expected = Series([
Timestamp('2013-06-09 02:42:28') + timedelta(seconds=t)
for t in range(20)
])
assert_series_equal(result, expected)
s = Series([epoch + t for t in range(20)] + [iNaT])
result = to_datetime(s, unit='s')
expected = Series([
Timestamp('2013-06-09 02:42:28') + timedelta(seconds=t)
for t in range(20)
] + [NaT])
assert_series_equal(result, expected)
s = Series([epoch + t for t in range(20)] + [iNaT]).astype(float)
result = to_datetime(s, unit='s')
expected = Series([
Timestamp('2013-06-09 02:42:28') + timedelta(seconds=t)
for t in range(20)
] + [NaT])
assert_series_equal(result, expected)
# GH13834
s = Series([epoch + t
for t in np.arange(0, 2, .25)] + [iNaT]).astype(float)
result = to_datetime(s, unit='s')
expected = Series([
Timestamp('2013-06-09 02:42:28') + timedelta(seconds=t)
for t in np.arange(0, 2, .25)
] + [NaT])
assert_series_equal(result, expected)
s = concat([
Series([epoch + t for t in range(20)]).astype(float),
Series([np.nan])
],
ignore_index=True)
result = to_datetime(s, unit='s')
expected = Series([
Timestamp('2013-06-09 02:42:28') + timedelta(seconds=t)
for t in range(20)
] + [NaT])
assert_series_equal(result, expected)
result = to_datetime([1, 2, 'NaT', pd.NaT, np.nan], unit='D')
expected = DatetimeIndex(
[Timestamp('1970-01-02'),
Timestamp('1970-01-03')] + ['NaT'] * 3)
tm.assert_index_equal(result, expected)
with pytest.raises(ValueError):
to_datetime([1, 2, 'foo'], unit='D')
with pytest.raises(ValueError):
to_datetime([1, 2, 111111111], unit='D')
# coerce we can process
expected = DatetimeIndex(
[Timestamp('1970-01-02'),
Timestamp('1970-01-03')] + ['NaT'] * 1)
result = to_datetime([1, 2, 'foo'], unit='D', errors='coerce')
tm.assert_index_equal(result, expected)
result = to_datetime([1, 2, 111111111], unit='D', errors='coerce')
tm.assert_index_equal(result, expected)
def _convert_listlike(arg, box, format, name=None, tz=tz):
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype='O')
# these are shortcutable
if is_datetime64tz_dtype(arg):
if not isinstance(arg, DatetimeIndex):
return DatetimeIndex(arg, tz=tz, name=name)
if utc:
arg = arg.tz_convert(None).tz_localize('UTC')
return arg
elif is_datetime64_ns_dtype(arg):
if box and not isinstance(arg, DatetimeIndex):
try:
return DatetimeIndex(arg, tz=tz, name=name)
except ValueError:
pass
return arg
elif unit is not None:
if format is not None:
raise ValueError("cannot specify both format and unit")
arg = getattr(arg, 'values', arg)
result = tslib.array_with_unit_to_datetime(arg,
unit,
errors=errors)
if box:
if errors == 'ignore':
from pandas import Index
return Index(result)
return DatetimeIndex(result, tz=tz, name=name)
return result
elif getattr(arg, 'ndim', 1) > 1:
raise TypeError('arg must be a string, datetime, list, tuple, '
'1-d array, or Series')
arg = _ensure_object(arg)
require_iso8601 = False
if infer_datetime_format and format is None:
format = _guess_datetime_format_for_array(arg, dayfirst=dayfirst)
if format is not None:
# There is a special fast-path for iso8601 formatted
# datetime strings, so in those cases don't use the inferred
# format because this path makes process slower in this
# special case
format_is_iso8601 = _format_is_iso(format)
if format_is_iso8601:
require_iso8601 = not infer_datetime_format
format = None
try:
result = None
if format is not None:
# shortcut formatting here
if format == '%Y%m%d':
try:
result = _attempt_YYYYMMDD(arg, errors=errors)
except:
raise ValueError("cannot convert the input to "
"'%Y%m%d' date format")
# fallback
if result is None:
try:
result = tslib.array_strptime(arg,
format,
exact=exact,
errors=errors)
except tslib.OutOfBoundsDatetime:
if errors == 'raise':
raise
result = arg
except ValueError:
# if format was inferred, try falling back
# to array_to_datetime - terminate here
# for specified formats
if not infer_datetime_format:
if errors == 'raise':
raise
result = arg
if result is None and (format is None or infer_datetime_format):
result = tslib.array_to_datetime(
arg,
errors=errors,
utc=utc,
dayfirst=dayfirst,
yearfirst=yearfirst,
require_iso8601=require_iso8601)
if is_datetime64_dtype(result) and box:
result = DatetimeIndex(result, tz=tz, name=name)
return result
except ValueError as e:
try:
values, tz = tslib.datetime_to_datetime64(arg)
return DatetimeIndex._simple_new(values, name=name, tz=tz)
except (ValueError, TypeError):
raise e
def to_timestamp(self, freq=None, how="start") -> DatetimeIndex:
arr = self._data.to_timestamp(freq, how)
return DatetimeIndex._simple_new(arr, name=self.name)
def test_constructor_with_datetime_tz(self):
# 8260
# support datetime64 with tz
dr = date_range('20130101', periods=3, tz='US/Eastern')
s = Series(dr)
self.assertTrue(s.dtype.name == 'datetime64[ns, US/Eastern]')
self.assertTrue(s.dtype == 'datetime64[ns, US/Eastern]')
self.assertTrue(is_datetime64tz_dtype(s.dtype))
self.assertTrue('datetime64[ns, US/Eastern]' in str(s))
# export
result = s.values
assert isinstance(result, np.ndarray)
self.assertTrue(result.dtype == 'datetime64[ns]')
exp = pd.DatetimeIndex(result)
exp = exp.tz_localize('UTC').tz_convert(tz=s.dt.tz)
tm.assert_index_equal(dr, exp)
# indexing
result = s.iloc[0]
self.assertEqual(
result,
Timestamp('2013-01-01 00:00:00-0500', tz='US/Eastern', freq='D'))
result = s[0]
self.assertEqual(
result,
Timestamp('2013-01-01 00:00:00-0500', tz='US/Eastern', freq='D'))
result = s[Series([True, True, False], index=s.index)]
assert_series_equal(result, s[0:2])
result = s.iloc[0:1]
assert_series_equal(result, Series(dr[0:1]))
# concat
result = pd.concat([s.iloc[0:1], s.iloc[1:]])
assert_series_equal(result, s)
# astype
result = s.astype(object)
expected = Series(DatetimeIndex(s._values).asobject)
assert_series_equal(result, expected)
result = Series(s.values).dt.tz_localize('UTC').dt.tz_convert(s.dt.tz)
assert_series_equal(result, s)
# astype - datetime64[ns, tz]
result = Series(s.values).astype('datetime64[ns, US/Eastern]')
assert_series_equal(result, s)
result = Series(s.values).astype(s.dtype)
assert_series_equal(result, s)
result = s.astype('datetime64[ns, CET]')
expected = Series(date_range('20130101 06:00:00', periods=3, tz='CET'))
assert_series_equal(result, expected)
# short str
self.assertTrue('datetime64[ns, US/Eastern]' in str(s))
# formatting with NaT
result = s.shift()
self.assertTrue('datetime64[ns, US/Eastern]' in str(result))
self.assertTrue('NaT' in str(result))
# long str
t = Series(date_range('20130101', periods=1000, tz='US/Eastern'))
self.assertTrue('datetime64[ns, US/Eastern]' in str(t))
result = pd.DatetimeIndex(s, freq='infer')
tm.assert_index_equal(result, dr)
# inference
s = Series([
pd.Timestamp('2013-01-01 13:00:00-0800', tz='US/Pacific'),
pd.Timestamp('2013-01-02 14:00:00-0800', tz='US/Pacific')
])
self.assertTrue(s.dtype == 'datetime64[ns, US/Pacific]')
self.assertTrue(lib.infer_dtype(s) == 'datetime64')
s = Series([
pd.Timestamp('2013-01-01 13:00:00-0800', tz='US/Pacific'),
pd.Timestamp('2013-01-02 14:00:00-0800', tz='US/Eastern')
])
self.assertTrue(s.dtype == 'object')
self.assertTrue(lib.infer_dtype(s) == 'datetime')
# with all NaT
s = Series(pd.NaT, index=[0, 1], dtype='datetime64[ns, US/Eastern]')
expected = Series(pd.DatetimeIndex(['NaT', 'NaT'], tz='US/Eastern'))
assert_series_equal(s, expected)
def _convert_listlike_datetimes(
arg,
format: Optional[str],
name: Hashable = None,
tz: Optional[Timezone] = None,
unit: Optional[str] = None,
errors: Optional[str] = None,
infer_datetime_format: bool = False,
dayfirst: Optional[bool] = None,
yearfirst: Optional[bool] = None,
exact: bool = True,
):
"""
Helper function for to_datetime. Performs the conversions of 1D listlike
of dates
Parameters
----------
arg : list, tuple, ndarray, Series, Index
date to be parsed
name : object
None or string for the Index name
tz : object
None or 'utc'
unit : string
None or string of the frequency of the passed data
errors : string
error handing behaviors from to_datetime, 'raise', 'coerce', 'ignore'
infer_datetime_format : bool, default False
inferring format behavior from to_datetime
dayfirst : boolean
dayfirst parsing behavior from to_datetime
yearfirst : boolean
yearfirst parsing behavior from to_datetime
exact : bool, default True
exact format matching behavior from to_datetime
Returns
-------
Index-like of parsed dates
"""
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype="O")
arg_dtype = getattr(arg, "dtype", None)
# these are shortcutable
if is_datetime64tz_dtype(arg_dtype):
if not isinstance(arg, (DatetimeArray, DatetimeIndex)):
return DatetimeIndex(arg, tz=tz, name=name)
if tz == "utc":
arg = arg.tz_convert(None).tz_localize(tz)
return arg
elif is_datetime64_ns_dtype(arg_dtype):
if not isinstance(arg, (DatetimeArray, DatetimeIndex)):
try:
return DatetimeIndex(arg, tz=tz, name=name)
except ValueError:
pass
elif tz:
# DatetimeArray, DatetimeIndex
return arg.tz_localize(tz)
return arg
elif unit is not None:
if format is not None:
raise ValueError("cannot specify both format and unit")
return _to_datetime_with_unit(arg, unit, name, tz, errors)
elif getattr(arg, "ndim", 1) > 1:
raise TypeError(
"arg must be a string, datetime, list, tuple, 1-d array, or Series"
)
# warn if passing timedelta64, raise for PeriodDtype
# NB: this must come after unit transformation
orig_arg = arg
try:
arg, _ = maybe_convert_dtype(arg, copy=False)
except TypeError:
if errors == "coerce":
result = np.array(["NaT"], dtype="datetime64[ns]").repeat(len(arg))
return DatetimeIndex(result, name=name)
elif errors == "ignore":
# error: Incompatible types in assignment (expression has type
# "Index", variable has type "ExtensionArray")
result = Index(arg, name=name) # type: ignore[assignment]
return result
raise
arg = ensure_object(arg)
require_iso8601 = False
if infer_datetime_format and format is None:
format = _guess_datetime_format_for_array(arg, dayfirst=dayfirst)
if format is not None:
# There is a special fast-path for iso8601 formatted
# datetime strings, so in those cases don't use the inferred
# format because this path makes process slower in this
# special case
format_is_iso8601 = format_is_iso(format)
if format_is_iso8601:
require_iso8601 = not infer_datetime_format
format = None
# error: Incompatible types in assignment (expression has type "None", variable has
# type "ExtensionArray")
result = None # type: ignore[assignment]
if format is not None:
# error: Incompatible types in assignment (expression has type
# "Optional[Index]", variable has type "ndarray")
result = _to_datetime_with_format( # type: ignore[assignment]
arg, orig_arg, name, tz, format, exact, errors, infer_datetime_format
)
if result is not None:
return result
if result is None:
assert format is None or infer_datetime_format
utc = tz == "utc"
result, tz_parsed = objects_to_datetime64ns(
arg,
dayfirst=dayfirst,
yearfirst=yearfirst,
utc=utc,
errors=errors,
require_iso8601=require_iso8601,
allow_object=True,
)
if tz_parsed is not None:
# We can take a shortcut since the datetime64 numpy array
# is in UTC
dta = DatetimeArray(result, dtype=tz_to_dtype(tz_parsed))
return DatetimeIndex._simple_new(dta, name=name)
utc = tz == "utc"
return _box_as_indexlike(result, utc=utc, name=name)
def _convert_listlike_datetimes(
arg,
format: Optional[str],
name: Hashable = None,
tz: Optional[Timezone] = None,
unit: Optional[str] = None,
errors: Optional[str] = None,
infer_datetime_format: Optional[bool] = None,
dayfirst: Optional[bool] = None,
yearfirst: Optional[bool] = None,
exact: Optional[bool] = None,
):
"""
Helper function for to_datetime. Performs the conversions of 1D listlike
of dates
Parameters
----------
arg : list, tuple, ndarray, Series, Index
date to be parsed
name : object
None or string for the Index name
tz : object
None or 'utc'
unit : string
None or string of the frequency of the passed data
errors : string
error handing behaviors from to_datetime, 'raise', 'coerce', 'ignore'
infer_datetime_format : boolean
inferring format behavior from to_datetime
dayfirst : boolean
dayfirst parsing behavior from to_datetime
yearfirst : boolean
yearfirst parsing behavior from to_datetime
exact : boolean
exact format matching behavior from to_datetime
Returns
-------
Index-like of parsed dates
"""
if isinstance(arg, (list, tuple)):
arg = np.array(arg, dtype="O")
arg_dtype = getattr(arg, "dtype", None)
# these are shortcutable
if is_datetime64tz_dtype(arg_dtype):
if not isinstance(arg, (DatetimeArray, DatetimeIndex)):
return DatetimeIndex(arg, tz=tz, name=name)
if tz == "utc":
arg = arg.tz_convert(None).tz_localize(tz)
return arg
elif is_datetime64_ns_dtype(arg_dtype):
if not isinstance(arg, (DatetimeArray, DatetimeIndex)):
try:
return DatetimeIndex(arg, tz=tz, name=name)
except ValueError:
pass
elif tz:
# DatetimeArray, DatetimeIndex
return arg.tz_localize(tz)
return arg
elif unit is not None:
if format is not None:
raise ValueError("cannot specify both format and unit")
arg = getattr(arg, "_values", arg)
# GH 30050 pass an ndarray to tslib.array_with_unit_to_datetime
# because it expects an ndarray argument
if isinstance(arg, IntegerArray):
result = arg.astype(f"datetime64[{unit}]")
tz_parsed = None
else:
result, tz_parsed = tslib.array_with_unit_to_datetime(
arg, unit, errors=errors)
if errors == "ignore":
result = Index(result, name=name)
else:
result = DatetimeIndex(result, name=name)
# GH 23758: We may still need to localize the result with tz
# GH 25546: Apply tz_parsed first (from arg), then tz (from caller)
# result will be naive but in UTC
try:
result = result.tz_localize("UTC").tz_convert(tz_parsed)
except AttributeError:
# Regular Index from 'ignore' path
return result
if tz is not None:
if result.tz is None:
result = result.tz_localize(tz)
else:
result = result.tz_convert(tz)
return result
elif getattr(arg, "ndim", 1) > 1:
raise TypeError(
"arg must be a string, datetime, list, tuple, 1-d array, or Series"
)
# warn if passing timedelta64, raise for PeriodDtype
# NB: this must come after unit transformation
orig_arg = arg
try:
arg, _ = maybe_convert_dtype(arg, copy=False)
except TypeError:
if errors == "coerce":
result = np.array(["NaT"], dtype="datetime64[ns]").repeat(len(arg))
return DatetimeIndex(result, name=name)
elif errors == "ignore":
result = Index(arg, name=name)
return result
raise
arg = ensure_object(arg)
require_iso8601 = False
if infer_datetime_format and format is None:
format = _guess_datetime_format_for_array(arg, dayfirst=dayfirst)
if format is not None:
# There is a special fast-path for iso8601 formatted
# datetime strings, so in those cases don't use the inferred
# format because this path makes process slower in this
# special case
format_is_iso8601 = format_is_iso(format)
if format_is_iso8601:
require_iso8601 = not infer_datetime_format
format = None
tz_parsed = None
result = None
if format is not None:
try:
# shortcut formatting here
if format == "%Y%m%d":
try:
# pass orig_arg as float-dtype may have been converted to
# datetime64[ns]
orig_arg = ensure_object(orig_arg)
result = _attempt_YYYYMMDD(orig_arg, errors=errors)
except (ValueError, TypeError, OutOfBoundsDatetime) as err:
raise ValueError(
"cannot convert the input to '%Y%m%d' date format"
) from err
# fallback
if result is None:
try:
result, timezones = array_strptime(arg,
format,
exact=exact,
errors=errors)
if "%Z" in format or "%z" in format:
return _return_parsed_timezone_results(
result, timezones, tz, name)
except OutOfBoundsDatetime:
if errors == "raise":
raise
elif errors == "coerce":
result = np.empty(arg.shape, dtype="M8[ns]")
iresult = result.view("i8")
iresult.fill(iNaT)
else:
result = arg
except ValueError:
# if format was inferred, try falling back
# to array_to_datetime - terminate here
# for specified formats
if not infer_datetime_format:
if errors == "raise":
raise
elif errors == "coerce":
result = np.empty(arg.shape, dtype="M8[ns]")
iresult = result.view("i8")
iresult.fill(iNaT)
else:
result = arg
except ValueError as e:
# Fallback to try to convert datetime objects if timezone-aware
# datetime objects are found without passing `utc=True`
try:
values, tz = conversion.datetime_to_datetime64(arg)
dta = DatetimeArray(values, dtype=tz_to_dtype(tz))
return DatetimeIndex._simple_new(dta, name=name)
except (ValueError, TypeError):
raise e
if result is None:
assert format is None or infer_datetime_format
utc = tz == "utc"
result, tz_parsed = objects_to_datetime64ns(
arg,
dayfirst=dayfirst,
yearfirst=yearfirst,
utc=utc,
errors=errors,
require_iso8601=require_iso8601,
allow_object=True,
)
if tz_parsed is not None:
# We can take a shortcut since the datetime64 numpy array
# is in UTC
dta = DatetimeArray(result, dtype=tz_to_dtype(tz_parsed))
return DatetimeIndex._simple_new(dta, name=name)
utc = tz == "utc"
return _box_as_indexlike(result, utc=utc, name=name)
def test_to_datetime_unit(self):
epoch = 1370745748
s = Series([epoch + t for t in range(20)])
result = to_datetime(s, unit="s")
expected = Series([
Timestamp("2013-06-09 02:42:28") + timedelta(seconds=t)
for t in range(20)
])
tm.assert_series_equal(result, expected)
s = Series([epoch + t for t in range(20)]).astype(float)
result = to_datetime(s, unit="s")
expected = Series([
Timestamp("2013-06-09 02:42:28") + timedelta(seconds=t)
for t in range(20)
])
tm.assert_series_equal(result, expected)
s = Series([epoch + t for t in range(20)] + [iNaT])
result = to_datetime(s, unit="s")
expected = Series([
Timestamp("2013-06-09 02:42:28") + timedelta(seconds=t)
for t in range(20)
] + [NaT])
tm.assert_series_equal(result, expected)
s = Series([epoch + t for t in range(20)] + [iNaT]).astype(float)
result = to_datetime(s, unit="s")
expected = Series([
Timestamp("2013-06-09 02:42:28") + timedelta(seconds=t)
for t in range(20)
] + [NaT])
tm.assert_series_equal(result, expected)
# GH13834
s = Series([epoch + t
for t in np.arange(0, 2, 0.25)] + [iNaT]).astype(float)
result = to_datetime(s, unit="s")
expected = Series([
Timestamp("2013-06-09 02:42:28") + timedelta(seconds=t)
for t in np.arange(0, 2, 0.25)
] + [NaT])
tm.assert_series_equal(result, expected)
s = concat(
[
Series([epoch + t for t in range(20)]).astype(float),
Series([np.nan])
],
ignore_index=True,
)
result = to_datetime(s, unit="s")
expected = Series([
Timestamp("2013-06-09 02:42:28") + timedelta(seconds=t)
for t in range(20)
] + [NaT])
tm.assert_series_equal(result, expected)
result = to_datetime([1, 2, "NaT", pd.NaT, np.nan], unit="D")
expected = DatetimeIndex(
[Timestamp("1970-01-02"),
Timestamp("1970-01-03")] + ["NaT"] * 3)
tm.assert_index_equal(result, expected)
msg = "non convertible value foo with the unit 'D'"
with pytest.raises(ValueError, match=msg):
to_datetime([1, 2, "foo"], unit="D")
msg = "cannot convert input 111111111 with the unit 'D'"
with pytest.raises(OutOfBoundsDatetime, match=msg):
to_datetime([1, 2, 111111111], unit="D")
# coerce we can process
expected = DatetimeIndex(
[Timestamp("1970-01-02"),
Timestamp("1970-01-03")] + ["NaT"] * 1)
result = to_datetime([1, 2, "foo"], unit="D", errors="coerce")
tm.assert_index_equal(result, expected)
result = to_datetime([1, 2, 111111111], unit="D", errors="coerce")
tm.assert_index_equal(result, expected)
def to_timestamp(self, freq=None, how='start'):
from pandas import DatetimeIndex
result = self._data.to_timestamp(freq=freq, how=how)
return DatetimeIndex._simple_new(result.asi8,
name=self.name,
freq=result.freq)
def _get_time_bins(self, ax):
if not isinstance(ax, DatetimeIndex):
raise TypeError('axis must be a DatetimeIndex, but got '
'an instance of %r' % type(ax).__name__)
if len(ax) == 0:
binner = labels = DatetimeIndex(data=[],
freq=self.freq,
name=ax.name)
return binner, [], labels
first, last = ax.min(), ax.max()
first, last = _get_range_edges(first,
last,
self.freq,
closed=self.closed,
base=self.base)
tz = ax.tz
# GH #12037
# use first/last directly instead of call replace() on them
# because replace() will swallow the nanosecond part
# thus last bin maybe slightly before the end if the end contains
# nanosecond part and lead to `Values falls after last bin` error
binner = labels = DatetimeIndex(freq=self.freq,
start=first,
end=last,
tz=tz,
name=ax.name)
# a little hack
trimmed = False
if (len(binner) > 2 and binner[-2] == last and self.closed == 'right'):
binner = binner[:-1]
trimmed = True
ax_values = ax.asi8
binner, bin_edges = self._adjust_bin_edges(binner, ax_values)
# general version, knowing nothing about relative frequencies
bins = lib.generate_bins_dt64(ax_values,
bin_edges,
self.closed,
hasnans=ax.hasnans)
if self.closed == 'right':
labels = binner
if self.label == 'right':
labels = labels[1:]
elif not trimmed:
labels = labels[:-1]
else:
if self.label == 'right':
labels = labels[1:]
elif not trimmed:
labels = labels[:-1]
if ax.hasnans:
binner = binner.insert(0, tslib.NaT)
labels = labels.insert(0, tslib.NaT)
# if we end up with more labels than bins
# adjust the labels
# GH4076
if len(bins) < len(labels):
labels = labels[:len(bins)]
return binner, bins, labels
