Skip to content

BUG: Cleanup timedelta offset #23439

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Nov 6, 2018
Merged

BUG: Cleanup timedelta offset #23439

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
789e9aa
BUG: Cleanup timedelta offset
sinhrks Oct 30, 2018
04f3ceb
fix tests
sinhrks Nov 5, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions doc/source/whatsnew/v0.24.0.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1127,6 +1127,8 @@ Timedelta
- Fixed bug in adding a :class:`DataFrame` with all-`timedelta64[ns]` dtypes to a :class:`DataFrame` with all-integer dtypes returning incorrect results instead of raising ``TypeError`` (:issue:`22696`)
- Bug in :class:`TimedeltaIndex` where adding a timezone-aware datetime scalar incorrectly returned a timezone-naive :class:`DatetimeIndex` (:issue:`23215`)
- Bug in :class:`TimedeltaIndex` where adding ``np.timedelta64('NaT')`` incorrectly returned an all-`NaT` :class:`DatetimeIndex` instead of an all-`NaT` :class:`TimedeltaIndex` (:issue:`23215`)
- Bug in :class:`Timedelta` and :func:`to_timedelta()` have inconsistencies in supported unit string (:issue:`21762`)


Timezones
^^^^^^^^^
Expand Down
66 changes: 57 additions & 9 deletions pandas/_libs/tslibs/timedeltas.pyx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,10 +45,16 @@ Components = collections.namedtuple('Components', [
'days', 'hours', 'minutes', 'seconds',
'milliseconds', 'microseconds', 'nanoseconds'])

cdef dict timedelta_abbrevs = { 'D': 'd',
'd': 'd',
'days': 'd',
'day': 'd',

cdef dict timedelta_abbrevs = { 'Y': 'Y',
'y': 'Y',
'M': 'M',
'W': 'W',
'w': 'W',
'D': 'D',
'd': 'D',
'days': 'D',
'day': 'D',
'hours': 'h',
'hour': 'h',
'hr': 'h',
Expand All @@ -57,6 +63,7 @@ cdef dict timedelta_abbrevs = { 'D': 'd',
'minute': 'm',
'min': 'm',
'minutes': 'm',
't': 'm',
's': 's',
'seconds': 's',
'sec': 's',
Expand All @@ -66,16 +73,19 @@ cdef dict timedelta_abbrevs = { 'D': 'd',
'millisecond': 'ms',
'milli': 'ms',
'millis': 'ms',
'l': 'ms',
'us': 'us',
'microseconds': 'us',
'microsecond': 'us',
'micro': 'us',
'micros': 'us',
'u': 'us',
'ns': 'ns',
'nanoseconds': 'ns',
'nano': 'ns',
'nanos': 'ns',
'nanosecond': 'ns'}
'nanosecond': 'ns',
'n': 'ns'}

_no_input = object()

Expand Down Expand Up @@ -140,7 +150,8 @@ cpdef int64_t delta_to_nanoseconds(delta) except? -1:

cpdef convert_to_timedelta64(object ts, object unit):
"""
Convert an incoming object to a timedelta64 if possible
Convert an incoming object to a timedelta64 if possible.
Before calling, unit must be standardized to avoid repeated unit conversion

Handle these types of objects:
- timedelta/Timedelta
Expand Down Expand Up @@ -228,6 +239,7 @@ def array_to_timedelta64(object[:] values, unit='ns', errors='raise'):
for i in range(n):
result[i] = parse_timedelta_string(values[i])
except:
unit = parse_timedelta_unit(unit)
for i in range(n):
try:
result[i] = convert_to_timedelta64(values[i], unit)
Expand All @@ -247,7 +259,16 @@ cdef inline int64_t cast_from_unit(object ts, object unit) except? -1:
int64_t m
int p

if unit == 'D' or unit == 'd':
if unit == 'Y':
m = 1000000000L * 31556952
p = 9
elif unit == 'M':
m = 1000000000L * 2629746
p = 9
elif unit == 'W':
m = 1000000000L * 86400 * 7
p = 9
elif unit == 'D' or unit == 'd':
m = 1000000000L * 86400
p = 9
elif unit == 'h':
Expand Down Expand Up @@ -485,14 +506,34 @@ cdef inline timedelta_from_spec(object number, object frac, object unit):

try:
unit = ''.join(unit)
unit = timedelta_abbrevs[unit.lower()]
if unit == 'M':
# To parse ISO 8601 string, 'M' should be treated as minute,
# not month
unit = 'm'
unit = parse_timedelta_unit(unit)
except KeyError:
raise ValueError("invalid abbreviation: {unit}".format(unit=unit))

n = ''.join(number) + '.' + ''.join(frac)
return cast_from_unit(float(n), unit)


cpdef inline object parse_timedelta_unit(object unit):
"""
Parameters
----------
unit : an unit string
"""
if unit is None:
return 'ns'
elif unit == 'M':
return unit
try:
return timedelta_abbrevs[unit.lower()]
except (KeyError, AttributeError):
raise ValueError("invalid unit abbreviation: {unit}"
.format(unit=unit))

# ----------------------------------------------------------------------
# Timedelta ops utilities

Expand Down Expand Up @@ -1070,7 +1111,13 @@ class Timedelta(_Timedelta):
Parameters
----------
value : Timedelta, timedelta, np.timedelta64, string, or integer
unit : string, {'ns', 'us', 'ms', 's', 'm', 'h', 'D'}, optional
unit : string, {'Y', 'M', 'W', 'D', 'days', 'day',
'hours', hour', 'hr', 'h', 'm', 'minute', 'min', 'minutes',
'T', 'S', 'seconds', 'sec', 'second', 'ms',
'milliseconds', 'millisecond', 'milli', 'millis', 'L',
'us', 'microseconds', 'microsecond', 'micro', 'micros',
'U', 'ns', 'nanoseconds', 'nano', 'nanos', 'nanosecond'
'N'}, optional
Denote the unit of the input, if input is an integer. Default 'ns'.
days, seconds, microseconds,
milliseconds, minutes, hours, weeks : numeric, optional
Expand Down Expand Up @@ -1121,6 +1168,7 @@ class Timedelta(_Timedelta):
value = np.timedelta64(delta_to_nanoseconds(value.delta), 'ns')
elif is_integer_object(value) or is_float_object(value):
# unit=None is de-facto 'ns'
unit = parse_timedelta_unit(unit)
value = convert_to_timedelta64(value, unit)
elif checknull_with_nat(value):
return NaT
Expand Down
54 changes: 11 additions & 43 deletions pandas/core/tools/timedeltas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,8 @@
import pandas as pd
from pandas._libs import tslibs
from pandas._libs.tslibs.timedeltas import (convert_to_timedelta64,
array_to_timedelta64)
array_to_timedelta64,
parse_timedelta_unit)

from pandas.core.dtypes.common import (
ensure_object,
Expand All @@ -23,8 +24,14 @@ def to_timedelta(arg, unit='ns', box=True, errors='raise'):
Parameters
----------
arg : string, timedelta, list, tuple, 1-d array, or Series
unit : unit of the arg (D,h,m,s,ms,us,ns) denote the unit, which is an
integer/float number
unit : string, {'Y', 'M', 'W', 'D', 'days', 'day',
'hours', hour', 'hr', 'h', 'm', 'minute', 'min', 'minutes',
'T', 'S', 'seconds', 'sec', 'second', 'ms',
'milliseconds', 'millisecond', 'milli', 'millis', 'L',
'us', 'microseconds', 'microsecond', 'micro', 'micros',
'U', 'ns', 'nanoseconds', 'nano', 'nanos', 'nanosecond'
'N'}, optional
Denote the unit of the input, if input is an integer. Default 'ns'.
box : boolean, default True
- If True returns a Timedelta/TimedeltaIndex of the results
- if False returns a np.timedelta64 or ndarray of values of dtype
Expand Down Expand Up @@ -69,7 +76,7 @@ def to_timedelta(arg, unit='ns', box=True, errors='raise'):
pandas.DataFrame.astype : Cast argument to a specified dtype.
pandas.to_datetime : Convert argument to datetime.
"""
unit = _validate_timedelta_unit(unit)
unit = parse_timedelta_unit(unit)

if errors not in ('ignore', 'raise', 'coerce'):
raise ValueError("errors must be one of 'ignore', "
Expand Down Expand Up @@ -99,45 +106,6 @@ def to_timedelta(arg, unit='ns', box=True, errors='raise'):
box=box, errors=errors)


_unit_map = {
'Y': 'Y',
'y': 'Y',
'W': 'W',
'w': 'W',
'D': 'D',
'd': 'D',
'days': 'D',
'Days': 'D',
'day': 'D',
'Day': 'D',
'M': 'M',
'H': 'h',
'h': 'h',
'm': 'm',
'T': 'm',
'S': 's',
's': 's',
'L': 'ms',
'MS': 'ms',
'ms': 'ms',
'US': 'us',
'us': 'us',
'NS': 'ns',
'ns': 'ns',
}


def _validate_timedelta_unit(arg):
""" provide validation / translation for timedelta short units """
try:
return _unit_map[arg]
except (KeyError, TypeError):
if arg is None:
return 'ns'
raise ValueError("invalid timedelta unit {arg} provided"
.format(arg=arg))


def _coerce_scalar_to_timedelta_type(r, unit='ns', box=True, errors='raise'):
"""Convert string 'r' to a timedelta object."""

Expand Down
73 changes: 50 additions & 23 deletions pandas/tests/scalar/timedelta/test_timedelta.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -293,37 +293,64 @@ def test_nat_converters(self):
assert to_timedelta('nat', box=False).astype('int64') == iNaT
assert to_timedelta('nan', box=False).astype('int64') == iNaT

def testit(unit, transform):

# array
result = to_timedelta(np.arange(5), unit=unit)
expected = TimedeltaIndex([np.timedelta64(i, transform(unit))
@pytest.mark.parametrize('units, np_unit',
[(['Y', 'y'], 'Y'),
(['M'], 'M'),
(['W', 'w'], 'W'),
(['D', 'd', 'days', 'day', 'Days', 'Day'], 'D'),
(['m', 'minute', 'min', 'minutes', 't',
'Minute', 'Min', 'Minutes', 'T'], 'm'),
(['s', 'seconds', 'sec', 'second',
'S', 'Seconds', 'Sec', 'Second'], 's'),
(['ms', 'milliseconds', 'millisecond', 'milli',
'millis', 'l', 'MS', 'Milliseconds',
'Millisecond', 'Milli', 'Millis', 'L'], 'ms'),
(['us', 'microseconds', 'microsecond', 'micro',
'micros', 'u', 'US', 'Microseconds',
'Microsecond', 'Micro', 'Micros', 'U'], 'us'),
(['ns', 'nanoseconds', 'nanosecond', 'nano',
'nanos', 'n', 'NS', 'Nanoseconds',
'Nanosecond', 'Nano', 'Nanos', 'N'], 'ns')])
@pytest.mark.parametrize('wrapper', [np.array, list, pd.Index])
def test_unit_parser(self, units, np_unit, wrapper):
# validate all units, GH 6855, GH 21762
for unit in units:
# array-likes
expected = TimedeltaIndex([np.timedelta64(i, np_unit)
for i in np.arange(5).tolist()])
result = to_timedelta(wrapper(range(5)), unit=unit)
tm.assert_index_equal(result, expected)
result = TimedeltaIndex(wrapper(range(5)), unit=unit)
tm.assert_index_equal(result, expected)

if unit == 'M':
# M is treated as minutes in string repr
expected = TimedeltaIndex([np.timedelta64(i, 'm')
for i in np.arange(5).tolist()])

str_repr = ['{}{}'.format(x, unit) for x in np.arange(5)]
result = to_timedelta(wrapper(str_repr))
tm.assert_index_equal(result, expected)
result = TimedeltaIndex(wrapper(str_repr))
tm.assert_index_equal(result, expected)

# scalar
result = to_timedelta(2, unit=unit)
expected = Timedelta(np.timedelta64(2, transform(unit)).astype(
expected = Timedelta(np.timedelta64(2, np_unit).astype(
'timedelta64[ns]'))
assert result == expected

# validate all units
# GH 6855
for unit in ['Y', 'M', 'W', 'D', 'y', 'w', 'd']:
testit(unit, lambda x: x.upper())
for unit in ['days', 'day', 'Day', 'Days']:
testit(unit, lambda x: 'D')
for unit in ['h', 'm', 's', 'ms', 'us', 'ns', 'H', 'S', 'MS', 'US',
'NS']:
testit(unit, lambda x: x.lower())

# offsets
result = to_timedelta(2, unit=unit)
assert result == expected
result = Timedelta(2, unit=unit)
assert result == expected

# m
testit('T', lambda x: 'm')
if unit == 'M':
expected = Timedelta(np.timedelta64(2, 'm').astype(
'timedelta64[ns]'))

# ms
testit('L', lambda x: 'ms')
result = to_timedelta('2{}'.format(unit))
assert result == expected
result = Timedelta('2{}'.format(unit))
assert result == expected

def test_numeric_conversions(self):
assert ct(0) == np.timedelta64(0, 'ns')
Expand Down