Skip to content

BUG: accept unicode in Timedelta constructor, #11995 #11997

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.

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 1 commit into from
Jan 8, 2016
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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: 1 addition & 1 deletion doc/source/whatsnew/v0.18.0.txt
Original file line number Diff line number Diff line change
Expand Up @@ -438,7 +438,7 @@ Bug Fixes
- Regression in ``.clip`` with tz-aware datetimes (:issue:`11838`)
- Bug in ``date_range`` when the boundaries fell on the frequency (:issue:`11804`)
- Bug in consistency of passing nested dicts to ``.groupby(...).agg(...)`` (:issue:`9052`)

- Accept unicode in ``Timedelta`` constructor (:issue:`11995`)



Expand Down
95 changes: 73 additions & 22 deletions pandas/tseries/tests/test_timedeltas.py
Original file line number Diff line number Diff line change
Expand Up @@ -161,25 +161,64 @@ def test_construction(self):
self.assertTrue(isnull(Timedelta('nat')))

# offset
self.assertEqual(to_timedelta(pd.offsets.Hour(2)),Timedelta('0 days, 02:00:00'))
self.assertEqual(Timedelta(pd.offsets.Hour(2)),Timedelta('0 days, 02:00:00'))
self.assertEqual(Timedelta(pd.offsets.Second(2)),Timedelta('0 days, 00:00:02'))
self.assertEqual(to_timedelta(pd.offsets.Hour(2)),
Timedelta('0 days, 02:00:00'))
self.assertEqual(Timedelta(pd.offsets.Hour(2)),
Timedelta('0 days, 02:00:00'))
self.assertEqual(Timedelta(pd.offsets.Second(2)),
Timedelta('0 days, 00:00:02'))

# unicode
# GH 11995
expected = Timedelta('1H')
result = pd.Timedelta(u'1H')
self.assertEqual(result, expected)
self.assertEqual(to_timedelta(pd.offsets.Hour(2)),
Timedelta(u'0 days, 02:00:00'))

self.assertRaises(ValueError, lambda: Timedelta(u'foo bar'))

def test_round(self):

t1 = Timedelta('1 days 02:34:56.789123456')
t2 = Timedelta('-1 days 02:34:56.789123456')

for (freq, s1, s2) in [('N', t1, t2),
('U', Timedelta('1 days 02:34:56.789123000'),Timedelta('-1 days 02:34:56.789123000')),
('L', Timedelta('1 days 02:34:56.789000000'),Timedelta('-1 days 02:34:56.789000000')),
('S', Timedelta('1 days 02:34:56'),Timedelta('-1 days 02:34:56')),
('2S', Timedelta('1 days 02:34:56'),Timedelta('-1 days 02:34:56')),
('5S', Timedelta('1 days 02:34:55'),Timedelta('-1 days 02:34:55')),
('T', Timedelta('1 days 02:34:00'),Timedelta('-1 days 02:34:00')),
('12T', Timedelta('1 days 02:24:00'),Timedelta('-1 days 02:24:00')),
('H', Timedelta('1 days 02:00:00'),Timedelta('-1 days 02:00:00')),
('d', Timedelta('1 days'),Timedelta('-1 days'))]:
('U',
Timedelta('1 days 02:34:56.789123000'),
Timedelta('-1 days 02:34:56.789123000')
),
('L',
Timedelta('1 days 02:34:56.789000000'),
Timedelta('-1 days 02:34:56.789000000')
),
('S',
Timedelta('1 days 02:34:56'),
Timedelta('-1 days 02:34:56')
),
('2S',
Timedelta('1 days 02:34:56'),
Timedelta('-1 days 02:34:56')
),
('5S',
Timedelta('1 days 02:34:55'),
Timedelta('-1 days 02:34:55')
),
('T',
Timedelta('1 days 02:34:00'),
Timedelta('-1 days 02:34:00')
),
('12T',
Timedelta('1 days 02:24:00'),
Timedelta('-1 days 02:24:00')),
('H',
Timedelta('1 days 02:00:00'),
Timedelta('-1 days 02:00:00')
),
('d',
Timedelta('1 days'),
Timedelta('-1 days')
)]:
r1 = t1.round(freq)
self.assertEqual(r1, s1)
r2 = t2.round(freq)
Expand Down Expand Up @@ -1104,20 +1143,32 @@ def test_components(self):
self.assertTrue(result.iloc[1].isnull().all())

def test_constructor(self):
expected = TimedeltaIndex(['1 days','1 days 00:00:05',
'2 days','2 days 00:00:02','0 days 00:00:03'])
result = TimedeltaIndex(['1 days','1 days, 00:00:05',
np.timedelta64(2,'D'),
timedelta(days=2,seconds=2),
expected = TimedeltaIndex(['1 days', '1 days 00:00:05',
'2 days', '2 days 00:00:02',
'0 days 00:00:03'])
result = TimedeltaIndex(['1 days', '1 days, 00:00:05',
np.timedelta64(2, 'D'),
timedelta(days=2, seconds=2),
pd.offsets.Second(3)])
tm.assert_index_equal(result, expected)

# unicode
result = TimedeltaIndex([u'1 days', '1 days, 00:00:05',
np.timedelta64(2, 'D'),
timedelta(days=2, seconds=2),
pd.offsets.Second(3)])
tm.assert_index_equal(result,expected)

expected = TimedeltaIndex(['0 days 00:00:00', '0 days 00:00:01', '0 days 00:00:02'])
expected = TimedeltaIndex(['0 days 00:00:00', '0 days 00:00:01',
'0 days 00:00:02'])
tm.assert_index_equal(TimedeltaIndex(range(3), unit='s'), expected)
expected = TimedeltaIndex(['0 days 00:00:00', '0 days 00:00:05', '0 days 00:00:09'])
expected = TimedeltaIndex(['0 days 00:00:00', '0 days 00:00:05',
'0 days 00:00:09'])
tm.assert_index_equal(TimedeltaIndex([0, 5, 9], unit='s'), expected)
expected = TimedeltaIndex(['0 days 00:00:00.400', '0 days 00:00:00.450', '0 days 00:00:01.200'])
tm.assert_index_equal(TimedeltaIndex([400, 450, 1200], unit='ms'), expected)
expected = TimedeltaIndex(['0 days 00:00:00.400',
'0 days 00:00:00.450',
'0 days 00:00:01.200'])
tm.assert_index_equal(TimedeltaIndex([400, 450, 1200], unit='ms'),
expected)

def test_constructor_coverage(self):
rng = timedelta_range('1 days', periods=10.5)
Expand Down
14 changes: 9 additions & 5 deletions pandas/tslib.pyx
Original file line number Diff line number Diff line change
Expand Up @@ -17,8 +17,9 @@ from cpython cimport (
PyLong_Check,
PyObject_RichCompareBool,
PyObject_RichCompare,
PyString_Check,
Py_GT, Py_GE, Py_EQ, Py_NE, Py_LT, Py_LE
Py_GT, Py_GE, Py_EQ, Py_NE, Py_LT, Py_LE,
PyUnicode_Check,
PyUnicode_AsUTF8String,
)

# Cython < 0.17 doesn't have this in cpython
Expand All @@ -31,10 +32,9 @@ cdef extern from "datetime_helper.h":

# this is our datetime.pxd
from datetime cimport cmp_pandas_datetimestruct
from util cimport is_integer_object, is_float_object, is_datetime64_object, is_timedelta64_object

from libc.stdlib cimport free

from util cimport is_integer_object, is_float_object, is_datetime64_object, is_timedelta64_object
cimport util

from datetime cimport *
Expand Down Expand Up @@ -2769,7 +2769,7 @@ cdef inline parse_timedelta_string(object ts, coerce=False):
"""

cdef:
str c
unicode c
bint neg=0, have_dot=0, have_value=0, have_hhmmss=0
object current_unit=None
int64_t result=0, m=0, r
Expand All @@ -2783,6 +2783,10 @@ cdef inline parse_timedelta_string(object ts, coerce=False):
if ts in _nat_strings or not len(ts):
return NPY_NAT

# decode ts if necessary
if not PyUnicode_Check(ts) and not PY3:
ts = str(ts).decode('utf-8')

for c in ts:

# skip whitespace / commas
Expand Down