def _infer_dtype_from_scalar(val):
""" interpret the dtype from a scalar """
dtype = np.object_
# a 1-element ndarray
if isinstance(val, np.ndarray):
if val.ndim != 0:
raise ValueError(
"invalid ndarray passed to _infer_dtype_from_scalar")
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)) and getattr(val, 'tzinfo', None) is None:
val = lib.Timestamp(val).value
dtype = np.dtype('M8[ns]')
elif isinstance(val, (np.timedelta64, timedelta)):
val = lib.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_
return dtype, val
def _wrap_results(result, dtype):
""" wrap our results if needed """
if is_datetime64_dtype(dtype):
if not isinstance(result, np.ndarray):
result = lib.Timestamp(result)
else:
result = result.view(dtype)
elif is_timedelta64_dtype(dtype):
if not isinstance(result, np.ndarray):
# raise if we have a timedelta64[ns] which is too large
if np.fabs(result) > _int64_max:
raise ValueError("overflow in timedelta operation")
result = lib.Timedelta(result, unit='ns')
else:
result = result.astype('i8').view(dtype)
return result
def conv(r, dtype):
try:
if isnull(r):
pass
elif dtype == _NS_DTYPE:
r = lib.Timestamp(r)
elif dtype == _TD_DTYPE:
r = _coerce_scalar_to_timedelta_type(r)
elif dtype == np.bool_:
# messy. non 0/1 integers do not get converted.
if is_integer(r) and r not in [0, 1]:
return int(r)
r = bool(r)
elif dtype.kind == 'f':
r = float(r)
elif dtype.kind == 'i':
r = int(r)
except:
pass
return r
def _convert_1d(values, unit, axis):
def try_parse(values):
try:
return _dt_to_float_ordinal(tools.to_datetime(values))
except Exception:
return values
if isinstance(values, (datetime, pydt.date)):
return _dt_to_float_ordinal(values)
elif isinstance(values, np.datetime64):
return _dt_to_float_ordinal(lib.Timestamp(values))
elif isinstance(values, pydt.time):
return dates.date2num(values)
elif (is_integer(values) or is_float(values)):
return values
elif isinstance(values, compat.string_types):
return try_parse(values)
elif isinstance(values, (list, tuple, np.ndarray, Index)):
if isinstance(values, Index):
values = values.values
if not isinstance(values, np.ndarray):
values = com._asarray_tuplesafe(values)
if is_integer_dtype(values) or is_float_dtype(values):
return values
try:
values = tools.to_datetime(values)
if isinstance(values, Index):
values = _dt_to_float_ordinal(values)
else:
values = [_dt_to_float_ordinal(x) for x in values]
except Exception:
values = _dt_to_float_ordinal(values)
return values
def rep_stamp(self):
return lib.Timestamp(self.values[0])
def maybe_promote(dtype, fill_value=np.nan):
# if we passed an array here, determine the fill value by dtype
if isinstance(fill_value, np.ndarray):
if issubclass(fill_value.dtype.type, (np.datetime64, np.timedelta64)):
fill_value = iNaT
else:
# we need to change to object type as our
# fill_value is of object type
if fill_value.dtype == np.object_:
dtype = np.dtype(np.object_)
fill_value = np.nan
# returns tuple of (dtype, fill_value)
if issubclass(dtype.type, (np.datetime64, np.timedelta64)):
# for now: refuse to upcast datetime64
# (this is because datetime64 will not implicitly upconvert
# to object correctly as of numpy 1.6.1)
if isnull(fill_value):
fill_value = iNaT
else:
if issubclass(dtype.type, np.datetime64):
try:
fill_value = lib.Timestamp(fill_value).value
except:
# the proper thing to do here would probably be to upcast
# to object (but numpy 1.6.1 doesn't do this properly)
fill_value = iNaT
elif issubclass(dtype.type, np.timedelta64):
try:
fill_value = lib.Timedelta(fill_value).value
except:
# as for datetimes, cannot upcast to object
fill_value = iNaT
else:
fill_value = iNaT
elif is_datetimetz(dtype):
if isnull(fill_value):
fill_value = iNaT
elif is_float(fill_value):
if issubclass(dtype.type, np.bool_):
dtype = np.object_
elif issubclass(dtype.type, np.integer):
dtype = np.float64
elif is_bool(fill_value):
if not issubclass(dtype.type, np.bool_):
dtype = np.object_
elif is_integer(fill_value):
if issubclass(dtype.type, np.bool_):
dtype = np.object_
elif issubclass(dtype.type, np.integer):
# upcast to prevent overflow
arr = np.asarray(fill_value)
if arr != arr.astype(dtype):
dtype = arr.dtype
elif is_complex(fill_value):
if issubclass(dtype.type, np.bool_):
dtype = np.object_
elif issubclass(dtype.type, (np.integer, np.floating)):
dtype = np.complex128
elif fill_value is None:
if is_float_dtype(dtype) or is_complex_dtype(dtype):
fill_value = np.nan
elif is_integer_dtype(dtype):
dtype = np.float64
fill_value = np.nan
elif is_datetime_or_timedelta_dtype(dtype):
fill_value = iNaT
else:
dtype = np.object_
else:
dtype = np.object_
# in case we have a string that looked like a number
if is_categorical_dtype(dtype):
pass
elif is_datetimetz(dtype):
pass
elif issubclass(np.dtype(dtype).type, string_types):
dtype = np.object_
return dtype, fill_value
def test_datetimeindex_constructor_misc(self):
arr = ['1/1/2005', '1/2/2005', 'Jn 3, 2005', '2005-01-04']
self.assertRaises(Exception, DatetimeIndex, arr)
arr = ['1/1/2005', '1/2/2005', '1/3/2005', '2005-01-04']
idx1 = DatetimeIndex(arr)
arr = [datetime(2005, 1, 1), '1/2/2005', '1/3/2005', '2005-01-04']
idx2 = DatetimeIndex(arr)
arr = [
lib.Timestamp(datetime(2005, 1, 1)), '1/2/2005', '1/3/2005',
'2005-01-04'
]
idx3 = DatetimeIndex(arr)
arr = np.array(['1/1/2005', '1/2/2005', '1/3/2005', '2005-01-04'],
dtype='O')
idx4 = DatetimeIndex(arr)
arr = to_datetime(['1/1/2005', '1/2/2005', '1/3/2005', '2005-01-04'])
idx5 = DatetimeIndex(arr)
arr = to_datetime(
['1/1/2005', '1/2/2005', 'Jan 3, 2005', '2005-01-04'])
idx6 = DatetimeIndex(arr)
idx7 = DatetimeIndex(['12/05/2007', '25/01/2008'], dayfirst=True)
idx8 = DatetimeIndex(['2007/05/12', '2008/01/25'],
dayfirst=False,
yearfirst=True)
tm.assert_index_equal(idx7, idx8)
for other in [idx2, idx3, idx4, idx5, idx6]:
self.assertTrue((idx1.values == other.values).all())
sdate = datetime(1999, 12, 25)
edate = datetime(2000, 1, 1)
idx = DatetimeIndex(start=sdate, freq='1B', periods=20)
self.assertEqual(len(idx), 20)
self.assertEqual(idx[0], sdate + 0 * offsets.BDay())
self.assertEqual(idx.freq, 'B')
idx = DatetimeIndex(end=edate, freq=('D', 5), periods=20)
self.assertEqual(len(idx), 20)
self.assertEqual(idx[-1], edate)
self.assertEqual(idx.freq, '5D')
idx1 = DatetimeIndex(start=sdate, end=edate, freq='W-SUN')
idx2 = DatetimeIndex(start=sdate,
end=edate,
freq=offsets.Week(weekday=6))
self.assertEqual(len(idx1), len(idx2))
self.assertEqual(idx1.offset, idx2.offset)
idx1 = DatetimeIndex(start=sdate, end=edate, freq='QS')
idx2 = DatetimeIndex(start=sdate,
end=edate,
freq=offsets.QuarterBegin(startingMonth=1))
self.assertEqual(len(idx1), len(idx2))
self.assertEqual(idx1.offset, idx2.offset)
idx1 = DatetimeIndex(start=sdate, end=edate, freq='BQ')
idx2 = DatetimeIndex(start=sdate,
end=edate,
freq=offsets.BQuarterEnd(startingMonth=12))
self.assertEqual(len(idx1), len(idx2))
self.assertEqual(idx1.offset, idx2.offset)
