def test_union_categoricals_ordered(self):
c1 = Categorical([1, 2, 3], ordered=True)
c2 = Categorical([1, 2, 3], ordered=False)
msg = 'Categorical.ordered must be the same'
with tm.assertRaisesRegexp(TypeError, msg):
union_categoricals([c1, c2])
res = union_categoricals([c1, c1])
exp = Categorical([1, 2, 3, 1, 2, 3], ordered=True)
tm.assert_categorical_equal(res, exp)
c1 = Categorical([1, 2, 3, np.nan], ordered=True)
c2 = Categorical([3, 2], categories=[1, 2, 3], ordered=True)
res = union_categoricals([c1, c2])
exp = Categorical([1, 2, 3, np.nan, 3, 2], ordered=True)
tm.assert_categorical_equal(res, exp)
c1 = Categorical([1, 2, 3], ordered=True)
c2 = Categorical([1, 2, 3], categories=[3, 2, 1], ordered=True)
msg = "to union ordered Categoricals, all categories must be the same"
with tm.assertRaisesRegexp(TypeError, msg):
union_categoricals([c1, c2])
def test_tz(self):
t = '2014-02-01 09:00'
ts = Timestamp(t)
local = ts.tz_localize('Asia/Tokyo')
self.assertEqual(local.hour, 9)
self.assertEqual(local, Timestamp(t, tz='Asia/Tokyo'))
conv = local.tz_convert('US/Eastern')
self.assertEqual(conv,
Timestamp('2014-01-31 19:00', tz='US/Eastern'))
self.assertEqual(conv.hour, 19)
# preserves nanosecond
ts = Timestamp(t) + offsets.Nano(5)
local = ts.tz_localize('Asia/Tokyo')
self.assertEqual(local.hour, 9)
self.assertEqual(local.nanosecond, 5)
conv = local.tz_convert('US/Eastern')
self.assertEqual(conv.nanosecond, 5)
self.assertEqual(conv.hour, 19)
# GH 8025
with tm.assertRaisesRegexp(TypeError, 'Cannot localize tz-aware Timestamp, use '
'tz_convert for conversions'):
Timestamp('2011-01-01' ,tz='US/Eastern').tz_localize('Asia/Tokyo')
with tm.assertRaisesRegexp(TypeError, 'Cannot convert tz-naive Timestamp, use '
'tz_localize to localize'):
Timestamp('2011-01-01').tz_convert('Asia/Tokyo')
def test_tz(self):
t = "2014-02-01 09:00"
ts = Timestamp(t)
local = ts.tz_localize("Asia/Tokyo")
self.assertEqual(local.hour, 9)
self.assertEqual(local, Timestamp(t, tz="Asia/Tokyo"))
conv = local.tz_convert("US/Eastern")
self.assertEqual(conv, Timestamp("2014-01-31 19:00", tz="US/Eastern"))
self.assertEqual(conv.hour, 19)
# preserves nanosecond
ts = Timestamp(t) + offsets.Nano(5)
local = ts.tz_localize("Asia/Tokyo")
self.assertEqual(local.hour, 9)
self.assertEqual(local.nanosecond, 5)
conv = local.tz_convert("US/Eastern")
self.assertEqual(conv.nanosecond, 5)
self.assertEqual(conv.hour, 19)
# GH 8025
with tm.assertRaisesRegexp(TypeError, "Cannot localize tz-aware Timestamp, use " "tz_convert for conversions"):
Timestamp("2011-01-01", tz="US/Eastern").tz_localize("Asia/Tokyo")
with tm.assertRaisesRegexp(TypeError, "Cannot convert tz-naive Timestamp, use " "tz_localize to localize"):
Timestamp("2011-01-01").tz_convert("Asia/Tokyo")
def test_index_equal_metadata_message(self):
expected = """Index are different
Attribute "names" are different
\\[left\\]: \\[None\\]
\\[right\\]: \\[u?'x'\\]"""
idx1 = pd.Index([1, 2, 3])
idx2 = pd.Index([1, 2, 3], name='x')
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2)
# same name, should pass
assert_index_equal(pd.Index([1, 2, 3], name=np.nan),
pd.Index([1, 2, 3], name=np.nan))
assert_index_equal(pd.Index([1, 2, 3], name=pd.NaT),
pd.Index([1, 2, 3], name=pd.NaT))
expected = """Index are different
Attribute "names" are different
\\[left\\]: \\[nan\\]
\\[right\\]: \\[NaT\\]"""
idx1 = pd.Index([1, 2, 3], name=np.nan)
idx2 = pd.Index([1, 2, 3], name=pd.NaT)
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2)
def test_categorical_equal_message(self):
expected = """Categorical\\.categories are different
Categorical\\.categories values are different \\(25\\.0 %\\)
\\[left\\]: Int64Index\\(\\[1, 2, 3, 4\\], dtype='int64'\\)
\\[right\\]: Int64Index\\(\\[1, 2, 3, 5\\], dtype='int64'\\)"""
a = pd.Categorical([1, 2, 3, 4])
b = pd.Categorical([1, 2, 3, 5])
with assertRaisesRegexp(AssertionError, expected):
tm.assert_categorical_equal(a, b)
expected = """Categorical\\.codes are different
Categorical\\.codes values are different \\(50\\.0 %\\)
\\[left\\]: \\[0, 1, 3, 2\\]
\\[right\\]: \\[0, 1, 2, 3\\]"""
a = pd.Categorical([1, 2, 4, 3], categories=[1, 2, 3, 4])
b = pd.Categorical([1, 2, 3, 4], categories=[1, 2, 3, 4])
with assertRaisesRegexp(AssertionError, expected):
tm.assert_categorical_equal(a, b)
expected = """Categorical are different
Attribute "ordered" are different
\\[left\\]: False
\\[right\\]: True"""
a = pd.Categorical([1, 2, 3, 4], ordered=False)
b = pd.Categorical([1, 2, 3, 4], ordered=True)
with assertRaisesRegexp(AssertionError, expected):
tm.assert_categorical_equal(a, b)
def test_take_fill_value(self):
# see gh-12631
idx = self._holder([1, 2, 3], name='xxx')
result = idx.take(np.array([1, 0, -1]))
expected = self._holder([2, 1, 3], name='xxx')
tm.assert_index_equal(result, expected)
name = self._holder.__name__
msg = ("Unable to fill values because "
"{name} cannot contain NA").format(name=name)
# fill_value=True
with tm.assertRaisesRegexp(ValueError, msg):
idx.take(np.array([1, 0, -1]), fill_value=True)
# allow_fill=False
result = idx.take(np.array([1, 0, -1]), allow_fill=False,
fill_value=True)
expected = self._holder([2, 1, 3], name='xxx')
tm.assert_index_equal(result, expected)
with tm.assertRaisesRegexp(ValueError, msg):
idx.take(np.array([1, 0, -2]), fill_value=True)
with tm.assertRaisesRegexp(ValueError, msg):
idx.take(np.array([1, 0, -5]), fill_value=True)
with tm.assertRaises(IndexError):
idx.take(np.array([1, -5]))
def test_tshift(self):
# PeriodIndex
ps = tm.makePeriodFrame()
shifted = ps.tshift(1)
unshifted = shifted.tshift(-1)
assert_frame_equal(unshifted, ps)
shifted2 = ps.tshift(freq='B')
assert_frame_equal(shifted, shifted2)
shifted3 = ps.tshift(freq=offsets.BDay())
assert_frame_equal(shifted, shifted3)
assertRaisesRegexp(ValueError, 'does not match', ps.tshift, freq='M')
# DatetimeIndex
shifted = self.tsframe.tshift(1)
unshifted = shifted.tshift(-1)
assert_frame_equal(self.tsframe, unshifted)
shifted2 = self.tsframe.tshift(freq=self.tsframe.index.freq)
assert_frame_equal(shifted, shifted2)
inferred_ts = DataFrame(self.tsframe.values,
Index(np.asarray(self.tsframe.index)),
columns=self.tsframe.columns)
shifted = inferred_ts.tshift(1)
unshifted = shifted.tshift(-1)
assert_frame_equal(shifted, self.tsframe.tshift(1))
assert_frame_equal(unshifted, inferred_ts)
no_freq = self.tsframe.iloc[[0, 5, 7], :]
self.assertRaises(ValueError, no_freq.tshift)
def test_get_loc(self):
idx = pd.period_range('2000-01-01', periods=3)
for method in [None, 'pad', 'backfill', 'nearest']:
self.assertEqual(idx.get_loc(idx[1], method), 1)
self.assertEqual(
idx.get_loc(idx[1].asfreq('H', how='start'), method), 1)
self.assertEqual(idx.get_loc(idx[1].to_timestamp(), method), 1)
self.assertEqual(
idx.get_loc(idx[1].to_timestamp().to_pydatetime(), method), 1)
self.assertEqual(idx.get_loc(str(idx[1]), method), 1)
idx = pd.period_range('2000-01-01', periods=5)[::2]
self.assertEqual(idx.get_loc('2000-01-02T12', method='nearest',
tolerance='1 day'), 1)
self.assertEqual(idx.get_loc('2000-01-02T12', method='nearest',
tolerance=pd.Timedelta('1D')), 1)
self.assertEqual(idx.get_loc('2000-01-02T12', method='nearest',
tolerance=np.timedelta64(1, 'D')), 1)
self.assertEqual(idx.get_loc('2000-01-02T12', method='nearest',
tolerance=timedelta(1)), 1)
with tm.assertRaisesRegexp(ValueError, 'must be convertible'):
idx.get_loc('2000-01-10', method='nearest', tolerance='foo')
msg = 'Input has different freq from PeriodIndex\\(freq=D\\)'
with tm.assertRaisesRegexp(ValueError, msg):
idx.get_loc('2000-01-10', method='nearest', tolerance='1 hour')
with tm.assertRaises(KeyError):
idx.get_loc('2000-01-10', method='nearest', tolerance='1 day')
def test_take_fill_value(self):
# GH 12631
idx = pd.Float64Index([1., 2., 3.], name='xxx')
result = idx.take(np.array([1, 0, -1]))
expected = pd.Float64Index([2., 1., 3.], name='xxx')
tm.assert_index_equal(result, expected)
# fill_value
result = idx.take(np.array([1, 0, -1]), fill_value=True)
expected = pd.Float64Index([2., 1., np.nan], name='xxx')
tm.assert_index_equal(result, expected)
# allow_fill=False
result = idx.take(np.array([1, 0, -1]), allow_fill=False,
fill_value=True)
expected = pd.Float64Index([2., 1., 3.], name='xxx')
tm.assert_index_equal(result, expected)
msg = ('When allow_fill=True and fill_value is not None, '
'all indices must be >= -1')
with tm.assertRaisesRegexp(ValueError, msg):
idx.take(np.array([1, 0, -2]), fill_value=True)
with tm.assertRaisesRegexp(ValueError, msg):
idx.take(np.array([1, 0, -5]), fill_value=True)
with tm.assertRaises(IndexError):
idx.take(np.array([1, -5]))
def test_difference_base(self):
for name, idx in compat.iteritems(self.indices):
first = idx[2:]
second = idx[:4]
answer = idx[4:]
result = first.difference(second)
if isinstance(idx, CategoricalIndex):
pass
else:
self.assertTrue(tm.equalContents(result, answer))
# GH 10149
cases = [klass(second.values)
for klass in [np.array, Series, list]]
for case in cases:
if isinstance(idx, PeriodIndex):
msg = "can only call with other PeriodIndex-ed objects"
with tm.assertRaisesRegexp(ValueError, msg):
result = first.difference(case)
elif isinstance(idx, CategoricalIndex):
pass
elif isinstance(idx, (DatetimeIndex, TimedeltaIndex)):
self.assertEqual(result.__class__, answer.__class__)
tm.assert_numpy_array_equal(result.asi8, answer.asi8)
else:
result = first.difference(case)
self.assertTrue(tm.equalContents(result, answer))
if isinstance(idx, MultiIndex):
msg = "other must be a MultiIndex or a list of tuples"
with tm.assertRaisesRegexp(TypeError, msg):
result = first.difference([1, 2, 3])
def test_symmetric_difference(self):
for name, idx in compat.iteritems(self.indices):
first = idx[1:]
second = idx[:-1]
if isinstance(idx, CategoricalIndex):
pass
else:
answer = idx[[0, -1]]
result = first.symmetric_difference(second)
self.assertTrue(tm.equalContents(result, answer))
# GH 10149
cases = [klass(second.values)
for klass in [np.array, Series, list]]
for case in cases:
if isinstance(idx, PeriodIndex):
msg = "can only call with other PeriodIndex-ed objects"
with tm.assertRaisesRegexp(ValueError, msg):
result = first.symmetric_difference(case)
elif isinstance(idx, CategoricalIndex):
pass
else:
result = first.symmetric_difference(case)
self.assertTrue(tm.equalContents(result, answer))
if isinstance(idx, MultiIndex):
msg = "other must be a MultiIndex or a list of tuples"
with tm.assertRaisesRegexp(TypeError, msg):
result = first.symmetric_difference([1, 2, 3])
# 12591 deprecated
with tm.assert_produces_warning(FutureWarning):
first.sym_diff(second)
def test_take_filling_fill_value(self):
# same tests as GH 12631
sparse = SparseArray([np.nan, 0, 1, 0, 4], fill_value=0)
result = sparse.take(np.array([1, 0, -1]))
expected = SparseArray([0, np.nan, 4], fill_value=0)
tm.assert_sp_array_equal(result, expected)
# fill_value
result = sparse.take(np.array([1, 0, -1]), fill_value=True)
expected = SparseArray([0, np.nan, 0], fill_value=0)
tm.assert_sp_array_equal(result, expected)
# allow_fill=False
result = sparse.take(np.array([1, 0, -1]),
allow_fill=False, fill_value=True)
expected = SparseArray([0, np.nan, 4], fill_value=0)
tm.assert_sp_array_equal(result, expected)
msg = ('When allow_fill=True and fill_value is not None, '
'all indices must be >= -1')
with tm.assertRaisesRegexp(ValueError, msg):
sparse.take(np.array([1, 0, -2]), fill_value=True)
with tm.assertRaisesRegexp(ValueError, msg):
sparse.take(np.array([1, 0, -5]), fill_value=True)
with tm.assertRaises(IndexError):
sparse.take(np.array([1, -6]))
with tm.assertRaises(IndexError):
sparse.take(np.array([1, 5]))
with tm.assertRaises(IndexError):
sparse.take(np.array([1, 5]), fill_value=True)
def test_union_base(self):
for name, idx in compat.iteritems(self.indices):
first = idx[3:]
second = idx[:5]
everything = idx
union = first.union(second)
self.assertTrue(tm.equalContents(union, everything))
# GH 10149
cases = [klass(second.values)
for klass in [np.array, Series, list]]
for case in cases:
if isinstance(idx, PeriodIndex):
msg = "can only call with other PeriodIndex-ed objects"
with tm.assertRaisesRegexp(ValueError, msg):
result = first.union(case)
elif isinstance(idx, CategoricalIndex):
pass
else:
result = first.union(case)
self.assertTrue(tm.equalContents(result, everything))
if isinstance(idx, MultiIndex):
msg = "other must be a MultiIndex or a list of tuples"
with tm.assertRaisesRegexp(TypeError, msg):
result = first.union([1, 2, 3])
def test_append_series_dict(self):
df = DataFrame(np.random.randn(5, 4),
columns=['foo', 'bar', 'baz', 'qux'])
series = df.loc[4]
with assertRaisesRegexp(ValueError, 'Indexes have overlapping values'):
df.append(series, verify_integrity=True)
series.name = None
with assertRaisesRegexp(TypeError, 'Can only append a Series if '
'ignore_index=True'):
df.append(series, verify_integrity=True)
result = df.append(series[::-1], ignore_index=True)
expected = df.append(DataFrame({0: series[::-1]}, index=df.columns).T,
ignore_index=True)
assert_frame_equal(result, expected)
# dict
result = df.append(series.to_dict(), ignore_index=True)
assert_frame_equal(result, expected)
result = df.append(series[::-1][:3], ignore_index=True)
expected = df.append(DataFrame({0: series[::-1][:3]}).T,
ignore_index=True)
assert_frame_equal(result, expected.loc[:, result.columns])
# can append when name set
row = df.loc[4]
row.name = 5
result = df.append(row)
expected = df.append(df[-1:], ignore_index=True)
assert_frame_equal(result, expected)
def test_insert_index_datetime64tz(self):
obj = pd.DatetimeIndex(['2011-01-01', '2011-01-02', '2011-01-03',
'2011-01-04'], tz='US/Eastern')
self.assertEqual(obj.dtype, 'datetime64[ns, US/Eastern]')
# datetime64tz + datetime64tz => datetime64
exp = pd.DatetimeIndex(['2011-01-01', '2012-01-01', '2011-01-02',
'2011-01-03', '2011-01-04'], tz='US/Eastern')
val = pd.Timestamp('2012-01-01', tz='US/Eastern')
self._assert_insert_conversion(obj, val, exp,
'datetime64[ns, US/Eastern]')
# ToDo: must coerce to object
msg = "Passed item and index have different timezone"
with tm.assertRaisesRegexp(ValueError, msg):
obj.insert(1, pd.Timestamp('2012-01-01'))
# ToDo: must coerce to object
msg = "Passed item and index have different timezone"
with tm.assertRaisesRegexp(ValueError, msg):
obj.insert(1, pd.Timestamp('2012-01-01', tz='Asia/Tokyo'))
# ToDo: must coerce to object
msg = "cannot insert DatetimeIndex with incompatible label"
with tm.assertRaisesRegexp(TypeError, msg):
obj.insert(1, 1)
def test_take_fill_value(self):
# GH 12631
idx = pd.PeriodIndex(['2011-01-01', '2011-02-01', '2011-03-01'],
name='xxx', freq='D')
result = idx.take(np.array([1, 0, -1]))
expected = pd.PeriodIndex(['2011-02-01', '2011-01-01', '2011-03-01'],
name='xxx', freq='D')
tm.assert_index_equal(result, expected)
# fill_value
result = idx.take(np.array([1, 0, -1]), fill_value=True)
expected = pd.PeriodIndex(['2011-02-01', '2011-01-01', 'NaT'],
name='xxx', freq='D')
tm.assert_index_equal(result, expected)
# allow_fill=False
result = idx.take(np.array([1, 0, -1]), allow_fill=False,
fill_value=True)
expected = pd.PeriodIndex(['2011-02-01', '2011-01-01', '2011-03-01'],
name='xxx', freq='D')
tm.assert_index_equal(result, expected)
msg = ('When allow_fill=True and fill_value is not None, '
'all indices must be >= -1')
with tm.assertRaisesRegexp(ValueError, msg):
idx.take(np.array([1, 0, -2]), fill_value=True)
with tm.assertRaisesRegexp(ValueError, msg):
idx.take(np.array([1, 0, -5]), fill_value=True)
with tm.assertRaises(IndexError):
idx.take(np.array([1, -5]))
def test_round(self):
td = pd.timedelta_range(start='16801 days', periods=5, freq='30Min')
elt = td[1]
expected_rng = TimedeltaIndex([
Timedelta('16801 days 00:00:00'),
Timedelta('16801 days 00:00:00'),
Timedelta('16801 days 01:00:00'),
Timedelta('16801 days 02:00:00'),
Timedelta('16801 days 02:00:00'),
])
expected_elt = expected_rng[1]
tm.assert_index_equal(td.round(freq='H'), expected_rng)
self.assertEqual(elt.round(freq='H'), expected_elt)
msg = pd.tseries.frequencies._INVALID_FREQ_ERROR
with self.assertRaisesRegexp(ValueError, msg):
td.round(freq='foo')
with tm.assertRaisesRegexp(ValueError, msg):
elt.round(freq='foo')
msg = "<MonthEnd> is a non-fixed frequency"
tm.assertRaisesRegexp(ValueError, msg, td.round, freq='M')
tm.assertRaisesRegexp(ValueError, msg, elt.round, freq='M')
def test_take_fill_value(self):
# GH 12631
idx = pd.Int64Index([1, 2, 3], name='xxx')
result = idx.take(np.array([1, 0, -1]))
expected = pd.Int64Index([2, 1, 3], name='xxx')
tm.assert_index_equal(result, expected)
# fill_value
msg = "Unable to fill values because Int64Index cannot contain NA"
with tm.assertRaisesRegexp(ValueError, msg):
idx.take(np.array([1, 0, -1]), fill_value=True)
# allow_fill=False
result = idx.take(np.array([1, 0, -1]), allow_fill=False,
fill_value=True)
expected = pd.Int64Index([2, 1, 3], name='xxx')
tm.assert_index_equal(result, expected)
msg = "Unable to fill values because Int64Index cannot contain NA"
with tm.assertRaisesRegexp(ValueError, msg):
idx.take(np.array([1, 0, -2]), fill_value=True)
with tm.assertRaisesRegexp(ValueError, msg):
idx.take(np.array([1, 0, -5]), fill_value=True)
with tm.assertRaises(IndexError):
idx.take(np.array([1, -5]))
def test_numpy_cumsum(self):
non_null_data = np.array([1, 2, 3, 4, 5], dtype=float)
non_null_expected = SparseArray(non_null_data.cumsum())
null_data = np.array([1, 2, np.nan, 4, 5], dtype=float)
null_expected = SparseArray(np.array([1.0, 3.0, np.nan, 7.0, 12.0]))
for data, expected in [
(null_data, null_expected),
(non_null_data, non_null_expected)
]:
out = np.cumsum(SparseArray(data))
tm.assert_sp_array_equal(out, expected)
out = np.cumsum(SparseArray(data, fill_value=np.nan))
tm.assert_sp_array_equal(out, expected)
out = np.cumsum(SparseArray(data, fill_value=2))
tm.assert_sp_array_equal(out, expected)
msg = "the 'dtype' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.cumsum,
SparseArray(data), dtype=np.int64)
msg = "the 'out' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.cumsum,
SparseArray(data), out=out)
def test_constructor_freq_mult(self):
# GH #7811
for func in [PeriodIndex, period_range]:
# must be the same, but for sure...
pidx = func(start='2014-01', freq='2M', periods=4)
expected = PeriodIndex(['2014-01', '2014-03',
'2014-05', '2014-07'], freq='2M')
tm.assert_index_equal(pidx, expected)
pidx = func(start='2014-01-02', end='2014-01-15', freq='3D')
expected = PeriodIndex(['2014-01-02', '2014-01-05',
'2014-01-08', '2014-01-11',
'2014-01-14'], freq='3D')
tm.assert_index_equal(pidx, expected)
pidx = func(end='2014-01-01 17:00', freq='4H', periods=3)
expected = PeriodIndex(['2014-01-01 09:00', '2014-01-01 13:00',
'2014-01-01 17:00'], freq='4H')
tm.assert_index_equal(pidx, expected)
msg = ('Frequency must be positive, because it'
' represents span: -1M')
with tm.assertRaisesRegexp(ValueError, msg):
PeriodIndex(['2011-01'], freq='-1M')
msg = ('Frequency must be positive, because it' ' represents span: 0M')
with tm.assertRaisesRegexp(ValueError, msg):
PeriodIndex(['2011-01'], freq='0M')
msg = ('Frequency must be positive, because it' ' represents span: 0M')
with tm.assertRaisesRegexp(ValueError, msg):
period_range('2011-01', periods=3, freq='0M')
def test_numpy_transpose(self):
sdf = SparseDataFrame([1, 2, 3], index=[1, 2, 3], columns=['a'])
result = np.transpose(np.transpose(sdf))
tm.assert_sp_frame_equal(result, sdf)
msg = "the 'axes' parameter is not supported"
tm.assertRaisesRegexp(ValueError, msg, np.transpose, sdf, axes=1)
def test_constructor_cant_cast_datetime64(self):
msg = "Cannot cast datetime64 to "
with tm.assertRaisesRegexp(TypeError, msg):
Series(date_range('1/1/2000', periods=10), dtype=float)
with tm.assertRaisesRegexp(TypeError, msg):
Series(date_range('1/1/2000', periods=10), dtype=int)
def test_constructor_generic_timestamp_deprecated(self):
# see gh-15524
with tm.assert_produces_warning(FutureWarning):
dtype = np.timedelta64
s = Series([], dtype=dtype)
assert s.empty
assert s.dtype == 'm8[ns]'
with tm.assert_produces_warning(FutureWarning):
dtype = np.datetime64
s = Series([], dtype=dtype)
assert s.empty
assert s.dtype == 'M8[ns]'
# These timestamps have the wrong frequencies,
# so an Exception should be raised now.
msg = "cannot convert timedeltalike"
with tm.assertRaisesRegexp(TypeError, msg):
Series([], dtype='m8[ps]')
msg = "cannot convert datetimelike"
with tm.assertRaisesRegexp(TypeError, msg):
Series([], dtype='M8[ps]')
def test_concat4_interleave_partitions():
pdf1 = pd.DataFrame(np.random.randn(10, 5), columns=list("ABCDE"), index=list("abcdefghij"))
pdf2 = pd.DataFrame(np.random.randn(13, 5), columns=list("ABCDE"), index=list("fghijklmnopqr"))
pdf3 = pd.DataFrame(np.random.randn(13, 6), columns=list("CDEXYZ"), index=list("fghijklmnopqr"))
ddf1 = dd.from_pandas(pdf1, 2)
ddf2 = dd.from_pandas(pdf2, 3)
ddf3 = dd.from_pandas(pdf3, 2)
msg = (
"All inputs have known divisions which cannnot be "
"concatenated in order. Specify "
"interleave_partitions=True to ignore order"
)
cases = [[ddf1, ddf1], [ddf1, ddf2], [ddf1, ddf3], [ddf2, ddf1], [ddf2, ddf3], [ddf3, ddf1], [ddf3, ddf2]]
for case in cases:
pdcase = [c.compute() for c in case]
with tm.assertRaisesRegexp(ValueError, msg):
dd.concat(case)
assert eq(dd.concat(case, interleave_partitions=True), pd.concat(pdcase))
assert eq(dd.concat(case, join="inner", interleave_partitions=True), pd.concat(pdcase, join="inner"))
msg = "'join' must be 'inner' or 'outer'"
with tm.assertRaisesRegexp(ValueError, msg):
dd.concat([ddf1, ddf1], join="invalid", interleave_partitions=True)
def test_no_args_with_kwargs(self):
bad_arg = 'bar'
min_fname_arg_count = 2
compat_args = OrderedDict()
compat_args['foo'] = -5
compat_args[bad_arg] = 1
msg = (r"the '{arg}' parameter is not supported "
r"in the pandas implementation of {func}\(\)".
format(arg=bad_arg, func=self.fname))
args = ()
kwargs = {'foo': -5, bad_arg: 2}
tm.assertRaisesRegexp(ValueError, msg,
validate_args_and_kwargs,
self.fname, args, kwargs,
min_fname_arg_count, compat_args)
args = (-5, 2)
kwargs = {}
tm.assertRaisesRegexp(ValueError, msg,
validate_args_and_kwargs,
self.fname, args, kwargs,
min_fname_arg_count, compat_args)
def test_null_quote_char(self):
data = 'a,b,c\n1,2,3'
# sanity checks
msg = 'quotechar must be set if quoting enabled'
tm.assertRaisesRegexp(TypeError, msg, self.read_csv,
StringIO(data), quotechar=None,
quoting=csv.QUOTE_MINIMAL)
tm.assertRaisesRegexp(TypeError, msg, self.read_csv,
StringIO(data), quotechar='',
quoting=csv.QUOTE_MINIMAL)
# no errors should be raised if quoting is None
expected = DataFrame([[1, 2, 3]],
columns=['a', 'b', 'c'])
result = self.read_csv(StringIO(data), quotechar=None,
quoting=csv.QUOTE_NONE)
tm.assert_frame_equal(result, expected)
result = self.read_csv(StringIO(data), quotechar='',
quoting=csv.QUOTE_NONE)
tm.assert_frame_equal(result, expected)
def test_wdi_download_error_handling(self):
cntry_codes = ['USA', 'XX']
inds = 'NY.GDP.PCAP.CD'
with tm.assertRaisesRegexp(ValueError, "Invalid Country Code\\(s\\): XX"):
result = download(country=cntry_codes, indicator=inds,
start=2003, end=2004, errors='raise')
if PANDAS_0160:
# assert_produces_warning doesn't exists in prior versions
with self.assert_produces_warning():
result = download(country=cntry_codes, indicator=inds,
start=2003, end=2004, errors='warn')
self.assertTrue(isinstance(result, pd.DataFrame))
self.assertEqual(len(result), 2)
cntry_codes = ['USA']
inds = ['NY.GDP.PCAP.CD', 'BAD_INDICATOR']
with tm.assertRaisesRegexp(ValueError, "The provided parameter value is not valid\\. Indicator: BAD_INDICATOR"):
result = download(country=cntry_codes, indicator=inds,
start=2003, end=2004, errors='raise')
if PANDAS_0160:
with self.assert_produces_warning():
result = download(country=cntry_codes, indicator=inds,
start=2003, end=2004, errors='warn')
self.assertTrue(isinstance(result, pd.DataFrame))
self.assertEqual(len(result), 2)
def test_constructor_pi_nat(self):
idx = PeriodIndex([Period('2011-01', freq='M'), pd.NaT,
Period('2011-01', freq='M')])
exp = PeriodIndex(['2011-01', 'NaT', '2011-01'], freq='M')
tm.assert_index_equal(idx, exp)
idx = PeriodIndex(np.array([Period('2011-01', freq='M'), pd.NaT,
Period('2011-01', freq='M')]))
tm.assert_index_equal(idx, exp)
idx = PeriodIndex([pd.NaT, pd.NaT, Period('2011-01', freq='M'),
Period('2011-01', freq='M')])
exp = PeriodIndex(['NaT', 'NaT', '2011-01', '2011-01'], freq='M')
tm.assert_index_equal(idx, exp)
idx = PeriodIndex(np.array([pd.NaT, pd.NaT,
Period('2011-01', freq='M'),
Period('2011-01', freq='M')]))
tm.assert_index_equal(idx, exp)
idx = PeriodIndex([pd.NaT, pd.NaT, '2011-01', '2011-01'], freq='M')
tm.assert_index_equal(idx, exp)
with tm.assertRaisesRegexp(ValueError, 'freq not specified'):
PeriodIndex([pd.NaT, pd.NaT])
with tm.assertRaisesRegexp(ValueError, 'freq not specified'):
PeriodIndex(np.array([pd.NaT, pd.NaT]))
with tm.assertRaisesRegexp(ValueError, 'freq not specified'):
PeriodIndex(['NaT', 'NaT'])
with tm.assertRaisesRegexp(ValueError, 'freq not specified'):
PeriodIndex(np.array(['NaT', 'NaT']))
def test_set_item(self):
def setitem():
self.arr[5] = 3
def setslice():
self.arr[1:5] = 2
assertRaisesRegexp(TypeError, "item assignment", setitem)
assertRaisesRegexp(TypeError, "item assignment", setslice)
def test_type_check(self):
# GH 11776
df = pd.DataFrame({'a': [1, -3.14, 7], 'b': ['4', '5', '6']})
with tm.assertRaisesRegexp(TypeError, "1-d array"):
to_numeric(df)
for errors in ['ignore', 'raise', 'coerce']:
with tm.assertRaisesRegexp(TypeError, "1-d array"):
to_numeric(df, errors=errors)
def test_invalid_table_attrs(self):
url = self.banklist_data
with tm.assertRaisesRegexp(ValueError, 'No tables found'):
self.read_html(url, 'First Federal Bank of Florida',
attrs={'id': 'tasdfable'})
def check_mutable_error(self, *args, **kwargs):
# pass whatever functions you normally would to assertRaises (after the Exception kind)
assertRaisesRegexp(TypeError, self.mutable_regex, *args, **kwargs)
def test_numeric_compat(self):
idx = self.create_index()
tm.assertRaisesRegexp(TypeError, "cannot perform __mul__",
lambda: idx * 1)
tm.assertRaisesRegexp(TypeError, "cannot perform __mul__",
lambda: 1 * idx)
div_err = "cannot perform __truediv__" if PY3 \
else "cannot perform __div__"
tm.assertRaisesRegexp(TypeError, div_err, lambda: idx / 1)
tm.assertRaisesRegexp(TypeError, div_err, lambda: 1 / idx)
tm.assertRaisesRegexp(TypeError, "cannot perform __floordiv__",
lambda: idx // 1)
tm.assertRaisesRegexp(TypeError, "cannot perform __floordiv__",
lambda: 1 // idx)
def test_hash_error(self):
for ind in self.indices.values():
with tm.assertRaisesRegexp(
TypeError, "unhashable type: %r" % type(ind).__name__):
hash(ind)
def test_wrong_number_names(self):
def testit(ind):
ind.names = ["apple", "banana", "carrot"]
for ind in self.indices.values():
assertRaisesRegexp(ValueError, "^Length", testit, ind)
def test_logical_compat(self):
idx = self.create_index()
tm.assertRaisesRegexp(TypeError, 'cannot perform all',
lambda: idx.all())
tm.assertRaisesRegexp(TypeError, 'cannot perform any',
lambda: idx.any())
def test_negative_skiprows(self):
with tm.assertRaisesRegexp(ValueError,
'\(you passed a negative value\)'):
self.read_html(self.spam_data, 'Water', skiprows=-1)
def test_set_index2(self):
df = DataFrame({'A': ['foo', 'foo', 'foo', 'bar', 'bar'],
'B': ['one', 'two', 'three', 'one', 'two'],
'C': ['a', 'b', 'c', 'd', 'e'],
'D': np.random.randn(5),
'E': np.random.randn(5)})
# new object, single-column
result = df.set_index('C')
result_nodrop = df.set_index('C', drop=False)
index = Index(df['C'], name='C')
expected = df.loc[:, ['A', 'B', 'D', 'E']]
expected.index = index
expected_nodrop = df.copy()
expected_nodrop.index = index
assert_frame_equal(result, expected)
assert_frame_equal(result_nodrop, expected_nodrop)
self.assertEqual(result.index.name, index.name)
# inplace, single
df2 = df.copy()
df2.set_index('C', inplace=True)
assert_frame_equal(df2, expected)
df3 = df.copy()
df3.set_index('C', drop=False, inplace=True)
assert_frame_equal(df3, expected_nodrop)
# create new object, multi-column
result = df.set_index(['A', 'B'])
result_nodrop = df.set_index(['A', 'B'], drop=False)
index = MultiIndex.from_arrays([df['A'], df['B']], names=['A', 'B'])
expected = df.loc[:, ['C', 'D', 'E']]
expected.index = index
expected_nodrop = df.copy()
expected_nodrop.index = index
assert_frame_equal(result, expected)
assert_frame_equal(result_nodrop, expected_nodrop)
self.assertEqual(result.index.names, index.names)
# inplace
df2 = df.copy()
df2.set_index(['A', 'B'], inplace=True)
assert_frame_equal(df2, expected)
df3 = df.copy()
df3.set_index(['A', 'B'], drop=False, inplace=True)
assert_frame_equal(df3, expected_nodrop)
# corner case
with assertRaisesRegexp(ValueError, 'Index has duplicate keys'):
df.set_index('A', verify_integrity=True)
# append
result = df.set_index(['A', 'B'], append=True)
xp = df.reset_index().set_index(['index', 'A', 'B'])
xp.index.names = [None, 'A', 'B']
assert_frame_equal(result, xp)
# append to existing multiindex
rdf = df.set_index(['A'], append=True)
rdf = rdf.set_index(['B', 'C'], append=True)
expected = df.set_index(['A', 'B', 'C'], append=True)
assert_frame_equal(rdf, expected)
# Series
result = df.set_index(df.C)
self.assertEqual(result.index.name, 'C')
def test_frame_to_time_stamp(self):
K = 5
index = PeriodIndex(freq='A', start='1/1/2001', end='12/1/2009')
df = DataFrame(randn(len(index), K), index=index)
df['mix'] = 'a'
exp_index = date_range('1/1/2001', end='12/31/2009', freq='A-DEC')
result = df.to_timestamp('D', 'end')
tm.assert_index_equal(result.index, exp_index)
tm.assert_numpy_array_equal(result.values, df.values)
exp_index = date_range('1/1/2001', end='1/1/2009', freq='AS-JAN')
result = df.to_timestamp('D', 'start')
tm.assert_index_equal(result.index, exp_index)
def _get_with_delta(delta, freq='A-DEC'):
return date_range(to_datetime('1/1/2001') + delta,
to_datetime('12/31/2009') + delta, freq=freq)
delta = timedelta(hours=23)
result = df.to_timestamp('H', 'end')
exp_index = _get_with_delta(delta)
tm.assert_index_equal(result.index, exp_index)
delta = timedelta(hours=23, minutes=59)
result = df.to_timestamp('T', 'end')
exp_index = _get_with_delta(delta)
tm.assert_index_equal(result.index, exp_index)
result = df.to_timestamp('S', 'end')
delta = timedelta(hours=23, minutes=59, seconds=59)
exp_index = _get_with_delta(delta)
tm.assert_index_equal(result.index, exp_index)
# columns
df = df.T
exp_index = date_range('1/1/2001', end='12/31/2009', freq='A-DEC')
result = df.to_timestamp('D', 'end', axis=1)
tm.assert_index_equal(result.columns, exp_index)
tm.assert_numpy_array_equal(result.values, df.values)
exp_index = date_range('1/1/2001', end='1/1/2009', freq='AS-JAN')
result = df.to_timestamp('D', 'start', axis=1)
tm.assert_index_equal(result.columns, exp_index)
delta = timedelta(hours=23)
result = df.to_timestamp('H', 'end', axis=1)
exp_index = _get_with_delta(delta)
tm.assert_index_equal(result.columns, exp_index)
delta = timedelta(hours=23, minutes=59)
result = df.to_timestamp('T', 'end', axis=1)
exp_index = _get_with_delta(delta)
tm.assert_index_equal(result.columns, exp_index)
result = df.to_timestamp('S', 'end', axis=1)
delta = timedelta(hours=23, minutes=59, seconds=59)
exp_index = _get_with_delta(delta)
tm.assert_index_equal(result.columns, exp_index)
# invalid axis
tm.assertRaisesRegexp(ValueError, 'axis', df.to_timestamp, axis=2)
result1 = df.to_timestamp('5t', axis=1)
result2 = df.to_timestamp('t', axis=1)
expected = pd.date_range('2001-01-01', '2009-01-01', freq='AS')
self.assertTrue(isinstance(result1.columns, DatetimeIndex))
self.assertTrue(isinstance(result2.columns, DatetimeIndex))
self.assert_numpy_array_equal(result1.columns.asi8, expected.asi8)
self.assert_numpy_array_equal(result2.columns.asi8, expected.asi8)
# PeriodIndex.to_timestamp always use 'infer'
self.assertEqual(result1.columns.freqstr, 'AS-JAN')
self.assertEqual(result2.columns.freqstr, 'AS-JAN')
def test_skiprows_invalid(self):
with tm.assertRaisesRegexp(TypeError,
'is not a valid type for skipping rows'):
self.read_html(self.spam_data, '.*Water.*', skiprows='asdf')
def test_converters_type_must_be_dict(self):
data = """index,A,B,C,D
foo,2,3,4,5
"""
with tm.assertRaisesRegexp(TypeError, 'Type converters.+'):
self.read_csv(StringIO(data), converters=0)
def test_set_columns(self):
cols = Index(np.arange(len(self.mixed_frame.columns)))
self.mixed_frame.columns = cols
with assertRaisesRegexp(ValueError, 'Length mismatch'):
self.mixed_frame.columns = cols[::2]
def test_take_fill_value(self):
# GH 12631
# numeric category
idx = pd.CategoricalIndex([1, 2, 3], name='xxx')
result = idx.take(np.array([1, 0, -1]))
expected = pd.CategoricalIndex([2, 1, 3], name='xxx')
tm.assert_index_equal(result, expected)
tm.assert_categorical_equal(result.values, expected.values)
# fill_value
result = idx.take(np.array([1, 0, -1]), fill_value=True)
expected = pd.CategoricalIndex([2, 1, np.nan],
categories=[1, 2, 3],
name='xxx')
tm.assert_index_equal(result, expected)
tm.assert_categorical_equal(result.values, expected.values)
# allow_fill=False
result = idx.take(np.array([1, 0, -1]),
allow_fill=False,
fill_value=True)
expected = pd.CategoricalIndex([2, 1, 3], name='xxx')
tm.assert_index_equal(result, expected)
tm.assert_categorical_equal(result.values, expected.values)
# object category
idx = pd.CategoricalIndex(list('CBA'),
categories=list('ABC'),
ordered=True,
name='xxx')
result = idx.take(np.array([1, 0, -1]))
expected = pd.CategoricalIndex(list('BCA'),
categories=list('ABC'),
ordered=True,
name='xxx')
tm.assert_index_equal(result, expected)
tm.assert_categorical_equal(result.values, expected.values)
# fill_value
result = idx.take(np.array([1, 0, -1]), fill_value=True)
expected = pd.CategoricalIndex(['B', 'C', np.nan],
categories=list('ABC'),
ordered=True,
name='xxx')
tm.assert_index_equal(result, expected)
tm.assert_categorical_equal(result.values, expected.values)
# allow_fill=False
result = idx.take(np.array([1, 0, -1]),
allow_fill=False,
fill_value=True)
expected = pd.CategoricalIndex(list('BCA'),
categories=list('ABC'),
ordered=True,
name='xxx')
tm.assert_index_equal(result, expected)
tm.assert_categorical_equal(result.values, expected.values)
msg = ('When allow_fill=True and fill_value is not None, '
'all indices must be >= -1')
with tm.assertRaisesRegexp(ValueError, msg):
idx.take(np.array([1, 0, -2]), fill_value=True)
with tm.assertRaisesRegexp(ValueError, msg):
idx.take(np.array([1, 0, -5]), fill_value=True)
with tm.assertRaises(IndexError):
idx.take(np.array([1, -5]))
def test_construction_dti_with_mixed_timezones(self):
# GH 11488 (not changed, added explicit tests)
# no tz results in DatetimeIndex
result = DatetimeIndex(
[Timestamp('2011-01-01'), Timestamp('2011-01-02')], name='idx')
exp = DatetimeIndex(
[Timestamp('2011-01-01'), Timestamp('2011-01-02')], name='idx')
self.assert_index_equal(result, exp, exact=True)
self.assertTrue(isinstance(result, DatetimeIndex))
# same tz results in DatetimeIndex
result = DatetimeIndex([Timestamp('2011-01-01 10:00', tz='Asia/Tokyo'),
Timestamp('2011-01-02 10:00',
tz='Asia/Tokyo')],
name='idx')
exp = DatetimeIndex([Timestamp('2011-01-01 10:00'),
Timestamp('2011-01-02 10:00')],
tz='Asia/Tokyo', name='idx')
self.assert_index_equal(result, exp, exact=True)
self.assertTrue(isinstance(result, DatetimeIndex))
# same tz results in DatetimeIndex (DST)
result = DatetimeIndex([Timestamp('2011-01-01 10:00', tz='US/Eastern'),
Timestamp('2011-08-01 10:00',
tz='US/Eastern')],
name='idx')
exp = DatetimeIndex([Timestamp('2011-01-01 10:00'),
Timestamp('2011-08-01 10:00')],
tz='US/Eastern', name='idx')
self.assert_index_equal(result, exp, exact=True)
self.assertTrue(isinstance(result, DatetimeIndex))
# different tz coerces tz-naive to tz-awareIndex(dtype=object)
result = DatetimeIndex([Timestamp('2011-01-01 10:00'),
Timestamp('2011-01-02 10:00',
tz='US/Eastern')], name='idx')
exp = DatetimeIndex([Timestamp('2011-01-01 05:00'),
Timestamp('2011-01-02 10:00')],
tz='US/Eastern', name='idx')
self.assert_index_equal(result, exp, exact=True)
self.assertTrue(isinstance(result, DatetimeIndex))
# tz mismatch affecting to tz-aware raises TypeError/ValueError
with tm.assertRaises(ValueError):
DatetimeIndex([Timestamp('2011-01-01 10:00', tz='Asia/Tokyo'),
Timestamp('2011-01-02 10:00', tz='US/Eastern')],
name='idx')
with tm.assertRaisesRegexp(TypeError, 'data is already tz-aware'):
DatetimeIndex([Timestamp('2011-01-01 10:00'),
Timestamp('2011-01-02 10:00', tz='US/Eastern')],
tz='Asia/Tokyo', name='idx')
with tm.assertRaises(ValueError):
DatetimeIndex([Timestamp('2011-01-01 10:00', tz='Asia/Tokyo'),
Timestamp('2011-01-02 10:00', tz='US/Eastern')],
tz='US/Eastern', name='idx')
with tm.assertRaisesRegexp(TypeError, 'data is already tz-aware'):
# passing tz should results in DatetimeIndex, then mismatch raises
# TypeError
Index([pd.NaT, Timestamp('2011-01-01 10:00'),
pd.NaT, Timestamp('2011-01-02 10:00', tz='US/Eastern')],
tz='Asia/Tokyo', name='idx')
def test_isinstance(self):
expected = "Expected type "
with assertRaisesRegexp(AssertionError, expected):
tm.assertIsInstance(1, pd.Series)
def test_get_loc(self):
idx = pd.date_range('2000-01-01', periods=3)
for method in [None, 'pad', 'backfill', 'nearest']:
self.assertEqual(idx.get_loc(idx[1], method), 1)
self.assertEqual(idx.get_loc(idx[1].to_pydatetime(), method), 1)
self.assertEqual(idx.get_loc(str(idx[1]), method), 1)
if method is not None:
self.assertEqual(
idx.get_loc(idx[1],
method,
tolerance=pd.Timedelta('0 days')), 1)
self.assertEqual(idx.get_loc('2000-01-01', method='nearest'), 0)
self.assertEqual(idx.get_loc('2000-01-01T12', method='nearest'), 1)
self.assertEqual(
idx.get_loc('2000-01-01T12', method='nearest', tolerance='1 day'),
1)
self.assertEqual(
idx.get_loc('2000-01-01T12',
method='nearest',
tolerance=pd.Timedelta('1D')), 1)
self.assertEqual(
idx.get_loc('2000-01-01T12',
method='nearest',
tolerance=np.timedelta64(1, 'D')), 1)
self.assertEqual(
idx.get_loc('2000-01-01T12',
method='nearest',
tolerance=timedelta(1)), 1)
with tm.assertRaisesRegexp(ValueError, 'must be convertible'):
idx.get_loc('2000-01-01T12', method='nearest', tolerance='foo')
with tm.assertRaises(KeyError):
idx.get_loc('2000-01-01T03', method='nearest', tolerance='2 hours')
self.assertEqual(idx.get_loc('2000', method='nearest'), slice(0, 3))
self.assertEqual(idx.get_loc('2000-01', method='nearest'), slice(0, 3))
self.assertEqual(idx.get_loc('1999', method='nearest'), 0)
self.assertEqual(idx.get_loc('2001', method='nearest'), 2)
with tm.assertRaises(KeyError):
idx.get_loc('1999', method='pad')
with tm.assertRaises(KeyError):
idx.get_loc('2001', method='backfill')
with tm.assertRaises(KeyError):
idx.get_loc('foobar')
with tm.assertRaises(TypeError):
idx.get_loc(slice(2))
idx = pd.to_datetime(['2000-01-01', '2000-01-04'])
self.assertEqual(idx.get_loc('2000-01-02', method='nearest'), 0)
self.assertEqual(idx.get_loc('2000-01-03', method='nearest'), 1)
self.assertEqual(idx.get_loc('2000-01', method='nearest'), slice(0, 2))
# time indexing
idx = pd.date_range('2000-01-01', periods=24, freq='H')
tm.assert_numpy_array_equal(idx.get_loc(time(12)),
np.array([12]),
check_dtype=False)
tm.assert_numpy_array_equal(idx.get_loc(time(12, 30)),
np.array([]),
check_dtype=False)
with tm.assertRaises(NotImplementedError):
idx.get_loc(time(12, 30), method='pad')
def test_index_equal_message(self):
expected = """Index are different
Index levels are different
\\[left\\]: 1, Int64Index\\(\\[1, 2, 3\\], dtype='int64'\\)
\\[right\\]: 2, MultiIndex\\(levels=\\[\\[u?'A', u?'B'\\], \\[1, 2, 3, 4\\]\\],
labels=\\[\\[0, 0, 1, 1\\], \\[0, 1, 2, 3\\]\\]\\)"""
idx1 = pd.Index([1, 2, 3])
idx2 = pd.MultiIndex.from_tuples([('A', 1), ('A', 2), ('B', 3),
('B', 4)])
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2, exact=False)
expected = """MultiIndex level \\[1\\] are different
MultiIndex level \\[1\\] values are different \\(25\\.0 %\\)
\\[left\\]: Int64Index\\(\\[2, 2, 3, 4\\], dtype='int64'\\)
\\[right\\]: Int64Index\\(\\[1, 2, 3, 4\\], dtype='int64'\\)"""
idx1 = pd.MultiIndex.from_tuples([('A', 2), ('A', 2), ('B', 3),
('B', 4)])
idx2 = pd.MultiIndex.from_tuples([('A', 1), ('A', 2), ('B', 3),
('B', 4)])
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2)
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2, check_exact=False)
expected = """Index are different
Index length are different
\\[left\\]: 3, Int64Index\\(\\[1, 2, 3\\], dtype='int64'\\)
\\[right\\]: 4, Int64Index\\(\\[1, 2, 3, 4\\], dtype='int64'\\)"""
idx1 = pd.Index([1, 2, 3])
idx2 = pd.Index([1, 2, 3, 4])
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2)
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2, check_exact=False)
expected = """Index are different
Index classes are different
\\[left\\]: Int64Index\\(\\[1, 2, 3\\], dtype='int64'\\)
\\[right\\]: Float64Index\\(\\[1\\.0, 2\\.0, 3\\.0\\], dtype='float64'\\)"""
idx1 = pd.Index([1, 2, 3])
idx2 = pd.Index([1, 2, 3.0])
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2, exact=True)
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2, exact=True, check_exact=False)
expected = """Index are different
Index values are different \\(33\\.33333 %\\)
\\[left\\]: Float64Index\\(\\[1.0, 2.0, 3.0], dtype='float64'\\)
\\[right\\]: Float64Index\\(\\[1.0, 2.0, 3.0000000001\\], dtype='float64'\\)"""
idx1 = pd.Index([1, 2, 3.])
idx2 = pd.Index([1, 2, 3.0000000001])
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2)
# must success
assert_index_equal(idx1, idx2, check_exact=False)
expected = """Index are different
Index values are different \\(33\\.33333 %\\)
\\[left\\]: Float64Index\\(\\[1.0, 2.0, 3.0], dtype='float64'\\)
\\[right\\]: Float64Index\\(\\[1.0, 2.0, 3.0001\\], dtype='float64'\\)"""
idx1 = pd.Index([1, 2, 3.])
idx2 = pd.Index([1, 2, 3.0001])
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2)
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2, check_exact=False)
# must success
assert_index_equal(idx1,
idx2,
check_exact=False,
check_less_precise=True)
expected = """Index are different
Index values are different \\(33\\.33333 %\\)
\\[left\\]: Int64Index\\(\\[1, 2, 3\\], dtype='int64'\\)
\\[right\\]: Int64Index\\(\\[1, 2, 4\\], dtype='int64'\\)"""
idx1 = pd.Index([1, 2, 3])
idx2 = pd.Index([1, 2, 4])
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2)
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2, check_less_precise=True)
expected = """MultiIndex level \\[1\\] are different
MultiIndex level \\[1\\] values are different \\(25\\.0 %\\)
\\[left\\]: Int64Index\\(\\[2, 2, 3, 4\\], dtype='int64'\\)
\\[right\\]: Int64Index\\(\\[1, 2, 3, 4\\], dtype='int64'\\)"""
idx1 = pd.MultiIndex.from_tuples([('A', 2), ('A', 2), ('B', 3),
('B', 4)])
idx2 = pd.MultiIndex.from_tuples([('A', 1), ('A', 2), ('B', 3),
('B', 4)])
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2)
with assertRaisesRegexp(AssertionError, expected):
assert_index_equal(idx1, idx2, check_exact=False)
def test_notisinstance(self):
expected = "Input must not be type "
with assertRaisesRegexp(AssertionError, expected):
tm.assertNotIsInstance(pd.Series([1]), pd.Series)
def test_hash_error(self):
index = date_range('20010101', periods=10)
with tm.assertRaisesRegexp(
TypeError, "unhashable type: %r" % type(index).__name__):
hash(index)
def test_frame_equal_message(self):
expected = """DataFrame are different
DataFrame shape \\(number of rows\\) are different
\\[left\\]: 3, RangeIndex\\(start=0, stop=3, step=1\\)
\\[right\\]: 4, RangeIndex\\(start=0, stop=4, step=1\\)"""
with assertRaisesRegexp(AssertionError, expected):
assert_frame_equal(pd.DataFrame({'A': [1, 2, 3]}),
pd.DataFrame({'A': [1, 2, 3, 4]}))
expected = """DataFrame are different
DataFrame shape \\(number of columns\\) are different
\\[left\\]: 2, Index\\(\\[u?'A', u?'B'\\], dtype='object'\\)
\\[right\\]: 1, Index\\(\\[u?'A'\\], dtype='object'\\)"""
with assertRaisesRegexp(AssertionError, expected):
assert_frame_equal(pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6]
}), pd.DataFrame({'A': [1, 2, 3]}))
expected = """DataFrame\\.index are different
DataFrame\\.index values are different \\(33\\.33333 %\\)
\\[left\\]: Index\\(\\[u?'a', u?'b', u?'c'\\], dtype='object'\\)
\\[right\\]: Index\\(\\[u?'a', u?'b', u?'d'\\], dtype='object'\\)"""
with assertRaisesRegexp(AssertionError, expected):
assert_frame_equal(
pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6]
},
index=['a', 'b', 'c']),
pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6]
},
index=['a', 'b', 'd']))
expected = """DataFrame\\.columns are different
DataFrame\\.columns values are different \\(50\\.0 %\\)
\\[left\\]: Index\\(\\[u?'A', u?'B'\\], dtype='object'\\)
\\[right\\]: Index\\(\\[u?'A', u?'b'\\], dtype='object'\\)"""
with assertRaisesRegexp(AssertionError, expected):
assert_frame_equal(
pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6]
},
index=['a', 'b', 'c']),
pd.DataFrame({
'A': [1, 2, 3],
'b': [4, 5, 6]
},
index=['a', 'b', 'c']))
expected = """DataFrame\\.iloc\\[:, 1\\] are different
DataFrame\\.iloc\\[:, 1\\] values are different \\(33\\.33333 %\\)
\\[left\\]: \\[4, 5, 6\\]
\\[right\\]: \\[4, 5, 7\\]"""
with assertRaisesRegexp(AssertionError, expected):
assert_frame_equal(pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6]
}), pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 7]
}))
with assertRaisesRegexp(AssertionError, expected):
assert_frame_equal(pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 6]
}),
pd.DataFrame({
'A': [1, 2, 3],
'B': [4, 5, 7]
}),
by_blocks=True)
def test_add_iadd(self):
# union
rng1 = pd.period_range('1/1/2000', freq='D', periods=5)
other1 = pd.period_range('1/6/2000', freq='D', periods=5)
expected1 = pd.period_range('1/1/2000', freq='D', periods=10)
rng2 = pd.period_range('1/1/2000', freq='D', periods=5)
other2 = pd.period_range('1/4/2000', freq='D', periods=5)
expected2 = pd.period_range('1/1/2000', freq='D', periods=8)
rng3 = pd.period_range('1/1/2000', freq='D', periods=5)
other3 = pd.PeriodIndex([], freq='D')
expected3 = pd.period_range('1/1/2000', freq='D', periods=5)
rng4 = pd.period_range('2000-01-01 09:00', freq='H', periods=5)
other4 = pd.period_range('2000-01-02 09:00', freq='H', periods=5)
expected4 = pd.PeriodIndex([
'2000-01-01 09:00', '2000-01-01 10:00', '2000-01-01 11:00',
'2000-01-01 12:00', '2000-01-01 13:00', '2000-01-02 09:00',
'2000-01-02 10:00', '2000-01-02 11:00', '2000-01-02 12:00',
'2000-01-02 13:00'
],
freq='H')
rng5 = pd.PeriodIndex(
['2000-01-01 09:01', '2000-01-01 09:03', '2000-01-01 09:05'],
freq='T')
other5 = pd.PeriodIndex(
['2000-01-01 09:01', '2000-01-01 09:05'
'2000-01-01 09:08'],
freq='T')
expected5 = pd.PeriodIndex([
'2000-01-01 09:01', '2000-01-01 09:03', '2000-01-01 09:05',
'2000-01-01 09:08'
],
freq='T')
rng6 = pd.period_range('2000-01-01', freq='M', periods=7)
other6 = pd.period_range('2000-04-01', freq='M', periods=7)
expected6 = pd.period_range('2000-01-01', freq='M', periods=10)
rng7 = pd.period_range('2003-01-01', freq='A', periods=5)
other7 = pd.period_range('1998-01-01', freq='A', periods=8)
expected7 = pd.period_range('1998-01-01', freq='A', periods=10)
for rng, other, expected in [(rng1, other1, expected1),
(rng2, other2, expected2),
(rng3, other3, expected3),
(rng4, other4, expected4),
(rng5, other5, expected5),
(rng6, other6, expected6),
(rng7, other7, expected7)]:
result_add = rng + other
result_union = rng.union(other)
tm.assert_index_equal(result_add, expected)
tm.assert_index_equal(result_union, expected)
# GH 6527
rng += other
tm.assert_index_equal(rng, expected)
# offset
for delta in [pd.offsets.Hour(2), timedelta(hours=2)]:
rng = pd.period_range('2000-01-01', '2000-02-01')
with tm.assertRaisesRegexp(TypeError,
'unsupported operand type\(s\)'):
result = rng + delta
with tm.assertRaisesRegexp(TypeError,
'unsupported operand type\(s\)'):
rng += delta
# int
rng = pd.period_range('2000-01-01 09:00', freq='H', periods=10)
result = rng + 1
expected = pd.period_range('2000-01-01 10:00', freq='H', periods=10)
tm.assert_index_equal(result, expected)
rng += 1
tm.assert_index_equal(rng, expected)
def test_numpy_array_equal_message(self):
if is_platform_windows():
raise nose.SkipTest("windows has incomparable line-endings "
"and uses L on the shape")
expected = """numpy array are different
numpy array shapes are different
\\[left\\]: \\(2,\\)
\\[right\\]: \\(3,\\)"""
with assertRaisesRegexp(AssertionError, expected):
assert_numpy_array_equal(np.array([1, 2]), np.array([3, 4, 5]))
with assertRaisesRegexp(AssertionError, expected):
assert_almost_equal(np.array([1, 2]), np.array([3, 4, 5]))
# scalar comparison
expected = """Expected type """
with assertRaisesRegexp(AssertionError, expected):
assert_numpy_array_equal(1, 2)
expected = """expected 2\\.00000 but got 1\\.00000, with decimal 5"""
with assertRaisesRegexp(AssertionError, expected):
assert_almost_equal(1, 2)
# array / scalar array comparison
expected = """numpy array are different
numpy array classes are different
\\[left\\]: ndarray
\\[right\\]: int"""
with assertRaisesRegexp(AssertionError, expected):
# numpy_array_equal only accepts np.ndarray
assert_numpy_array_equal(np.array([1]), 1)
with assertRaisesRegexp(AssertionError, expected):
assert_almost_equal(np.array([1]), 1)
# scalar / array comparison
expected = """numpy array are different
numpy array classes are different
\\[left\\]: int
\\[right\\]: ndarray"""
with assertRaisesRegexp(AssertionError, expected):
assert_numpy_array_equal(1, np.array([1]))
with assertRaisesRegexp(AssertionError, expected):
assert_almost_equal(1, np.array([1]))
expected = """numpy array are different
numpy array values are different \\(66\\.66667 %\\)
\\[left\\]: \\[nan, 2\\.0, 3\\.0\\]
\\[right\\]: \\[1\\.0, nan, 3\\.0\\]"""
with assertRaisesRegexp(AssertionError, expected):
assert_numpy_array_equal(np.array([np.nan, 2, 3]),
np.array([1, np.nan, 3]))
with assertRaisesRegexp(AssertionError, expected):
assert_almost_equal(np.array([np.nan, 2, 3]),
np.array([1, np.nan, 3]))
expected = """numpy array are different
numpy array values are different \\(50\\.0 %\\)
\\[left\\]: \\[1, 2\\]
\\[right\\]: \\[1, 3\\]"""
with assertRaisesRegexp(AssertionError, expected):
assert_numpy_array_equal(np.array([1, 2]), np.array([1, 3]))
with assertRaisesRegexp(AssertionError, expected):
assert_almost_equal(np.array([1, 2]), np.array([1, 3]))
expected = """numpy array are different
numpy array values are different \\(50\\.0 %\\)
\\[left\\]: \\[1\\.1, 2\\.000001\\]
\\[right\\]: \\[1\\.1, 2.0\\]"""
with assertRaisesRegexp(AssertionError, expected):
assert_numpy_array_equal(np.array([1.1, 2.000001]),
np.array([1.1, 2.0]))
# must pass
assert_almost_equal(np.array([1.1, 2.000001]), np.array([1.1, 2.0]))
expected = """numpy array are different
numpy array values are different \\(16\\.66667 %\\)
\\[left\\]: \\[\\[1, 2\\], \\[3, 4\\], \\[5, 6\\]\\]
\\[right\\]: \\[\\[1, 3\\], \\[3, 4\\], \\[5, 6\\]\\]"""
with assertRaisesRegexp(AssertionError, expected):
assert_numpy_array_equal(np.array([[1, 2], [3, 4], [5, 6]]),
np.array([[1, 3], [3, 4], [5, 6]]))
with assertRaisesRegexp(AssertionError, expected):
assert_almost_equal(np.array([[1, 2], [3, 4], [5, 6]]),
np.array([[1, 3], [3, 4], [5, 6]]))
expected = """numpy array are different
numpy array values are different \\(25\\.0 %\\)
\\[left\\]: \\[\\[1, 2\\], \\[3, 4\\]\\]
\\[right\\]: \\[\\[1, 3\\], \\[3, 4\\]\\]"""
with assertRaisesRegexp(AssertionError, expected):
assert_numpy_array_equal(np.array([[1, 2], [3, 4]]),
np.array([[1, 3], [3, 4]]))
with assertRaisesRegexp(AssertionError, expected):
assert_almost_equal(np.array([[1, 2], [3, 4]]),
np.array([[1, 3], [3, 4]]))
# allow to overwrite message
expected = """Index are different
Index shapes are different
\\[left\\]: \\(2,\\)
\\[right\\]: \\(3,\\)"""
with assertRaisesRegexp(AssertionError, expected):
assert_numpy_array_equal(np.array([1, 2]),
np.array([3, 4, 5]),
obj='Index')
with assertRaisesRegexp(AssertionError, expected):
assert_almost_equal(np.array([1, 2]),
np.array([3, 4, 5]),
obj='Index')
def test_dt_accessor_no_new_attributes(self):
# https://github.com/pydata/pandas/issues/10673
s = Series(date_range('20130101', periods=5, freq='D'))
with tm.assertRaisesRegexp(AttributeError,
"You cannot add any new attribute"):
s.dt.xlabel = "a"
def test_mut_exclusive():
msg = "mutually exclusive arguments: '[ab]' and '[ab]'"
with tm.assertRaisesRegexp(TypeError, msg):
com._mut_exclusive(a=1, b=2)
assert com._mut_exclusive(a=1, b=None) == 1
assert com._mut_exclusive(major=None, major_axis=None) is None
def test_per_axis_per_level_getitem(self):
# GH6134
# example test case
ix = MultiIndex.from_product(
[_mklbl('A', 5),
_mklbl('B', 7),
_mklbl('C', 4),
_mklbl('D', 2)])
df = DataFrame(np.arange(len(ix.get_values())), index=ix)
result = df.loc[(slice('A1', 'A3'), slice(None), ['C1', 'C3']), :]
expected = df.loc[[
tuple([a, b, c, d]) for a, b, c, d in df.index.values
if (a == 'A1' or a == 'A2' or a == 'A3') and (
c == 'C1' or c == 'C3')
]]
tm.assert_frame_equal(result, expected)
expected = df.loc[[
tuple([a, b, c, d]) for a, b, c, d in df.index.values
if (a == 'A1' or a == 'A2' or a == 'A3') and (
c == 'C1' or c == 'C2' or c == 'C3')
]]
result = df.loc[(slice('A1', 'A3'), slice(None), slice('C1', 'C3')), :]
tm.assert_frame_equal(result, expected)
# test multi-index slicing with per axis and per index controls
index = MultiIndex.from_tuples([('A', 1), ('A', 2), ('A', 3),
('B', 1)],
names=['one', 'two'])
columns = MultiIndex.from_tuples([('a', 'foo'), ('a', 'bar'),
('b', 'foo'), ('b', 'bah')],
names=['lvl0', 'lvl1'])
df = DataFrame(np.arange(16, dtype='int64').reshape(4, 4),
index=index,
columns=columns)
df = df.sort_index(axis=0).sort_index(axis=1)
# identity
result = df.loc[(slice(None), slice(None)), :]
tm.assert_frame_equal(result, df)
result = df.loc[(slice(None), slice(None)), (slice(None), slice(None))]
tm.assert_frame_equal(result, df)
result = df.loc[:, (slice(None), slice(None))]
tm.assert_frame_equal(result, df)
# index
result = df.loc[(slice(None), [1]), :]
expected = df.iloc[[0, 3]]
tm.assert_frame_equal(result, expected)
result = df.loc[(slice(None), 1), :]
expected = df.iloc[[0, 3]]
tm.assert_frame_equal(result, expected)
# columns
result = df.loc[:, (slice(None), ['foo'])]
expected = df.iloc[:, [1, 3]]
tm.assert_frame_equal(result, expected)
# both
result = df.loc[(slice(None), 1), (slice(None), ['foo'])]
expected = df.iloc[[0, 3], [1, 3]]
tm.assert_frame_equal(result, expected)
result = df.loc['A', 'a']
expected = DataFrame(dict(bar=[1, 5, 9], foo=[0, 4, 8]),
index=Index([1, 2, 3], name='two'),
columns=Index(['bar', 'foo'], name='lvl1'))
tm.assert_frame_equal(result, expected)
result = df.loc[(slice(None), [1, 2]), :]
expected = df.iloc[[0, 1, 3]]
tm.assert_frame_equal(result, expected)
# multi-level series
s = Series(np.arange(len(ix.get_values())), index=ix)
result = s.loc['A1':'A3', :, ['C1', 'C3']]
expected = s.loc[[
tuple([a, b, c, d]) for a, b, c, d in s.index.values
if (a == 'A1' or a == 'A2' or a == 'A3') and (
c == 'C1' or c == 'C3')
]]
tm.assert_series_equal(result, expected)
# boolean indexers
result = df.loc[(slice(None), df.loc[:, ('a', 'bar')] > 5), :]
expected = df.iloc[[2, 3]]
tm.assert_frame_equal(result, expected)
def f():
df.loc[(slice(None), np.array([True, False])), :]
self.assertRaises(ValueError, f)
# ambiguous cases
# these can be multiply interpreted (e.g. in this case
# as df.loc[slice(None),[1]] as well
self.assertRaises(KeyError, lambda: df.loc[slice(None), [1]])
result = df.loc[(slice(None), [1]), :]
expected = df.iloc[[0, 3]]
tm.assert_frame_equal(result, expected)
# not lexsorted
self.assertEqual(df.index.lexsort_depth, 2)
df = df.sort_index(level=1, axis=0)
self.assertEqual(df.index.lexsort_depth, 0)
with tm.assertRaisesRegexp(
UnsortedIndexError,
'MultiIndex Slicing requires the index to be fully '
r'lexsorted tuple len \(2\), lexsort depth \(0\)'):
df.loc[(slice(None), df.loc[:, ('a', 'bar')] > 5), :]
def test_write_explicit_bad(self, compression, get_random_path):
with tm.assertRaisesRegexp(ValueError,
"Unrecognized compression type"):
with tm.ensure_clean(get_random_path) as path:
df = tm.makeDataFrame()
df.to_pickle(path, compression=compression)
def assert_unbounded_slice_error(slc):
tm.assertRaisesRegexp(ValueError, "unbounded slice",
lambda: BlockPlacement(slc))
def test_dt_namespace_accessor(self):
# GH 7207, 11128
# test .dt namespace accessor
ok_for_base = ['year', 'month', 'day', 'hour', 'minute', 'second',
'weekofyear', 'week', 'dayofweek', 'weekday',
'dayofyear', 'quarter', 'freq', 'days_in_month',
'daysinmonth', 'is_leap_year']
ok_for_period = ok_for_base + ['qyear', 'start_time', 'end_time']
ok_for_period_methods = ['strftime', 'to_timestamp', 'asfreq']
ok_for_dt = ok_for_base + ['date', 'time', 'microsecond', 'nanosecond',
'is_month_start', 'is_month_end',
'is_quarter_start', 'is_quarter_end',
'is_year_start', 'is_year_end', 'tz',
'weekday_name']
ok_for_dt_methods = ['to_period', 'to_pydatetime', 'tz_localize',
'tz_convert', 'normalize', 'strftime', 'round',
'floor', 'ceil', 'weekday_name']
ok_for_td = ['days', 'seconds', 'microseconds', 'nanoseconds']
ok_for_td_methods = ['components', 'to_pytimedelta', 'total_seconds',
'round', 'floor', 'ceil']
def get_expected(s, name):
result = getattr(Index(s._values), prop)
if isinstance(result, np.ndarray):
if is_integer_dtype(result):
result = result.astype('int64')
elif not is_list_like(result):
return result
return Series(result, index=s.index, name=s.name)
def compare(s, name):
a = getattr(s.dt, prop)
b = get_expected(s, prop)
if not (is_list_like(a) and is_list_like(b)):
self.assertEqual(a, b)
else:
tm.assert_series_equal(a, b)
# datetimeindex
cases = [Series(date_range('20130101', periods=5), name='xxx'),
Series(date_range('20130101', periods=5, freq='s'),
name='xxx'),
Series(date_range('20130101 00:00:00', periods=5, freq='ms'),
name='xxx')]
for s in cases:
for prop in ok_for_dt:
# we test freq below
if prop != 'freq':
compare(s, prop)
for prop in ok_for_dt_methods:
getattr(s.dt, prop)
result = s.dt.to_pydatetime()
self.assertIsInstance(result, np.ndarray)
self.assertTrue(result.dtype == object)
result = s.dt.tz_localize('US/Eastern')
exp_values = DatetimeIndex(s.values).tz_localize('US/Eastern')
expected = Series(exp_values, index=s.index, name='xxx')
tm.assert_series_equal(result, expected)
tz_result = result.dt.tz
self.assertEqual(str(tz_result), 'US/Eastern')
freq_result = s.dt.freq
self.assertEqual(freq_result, DatetimeIndex(s.values,
freq='infer').freq)
# let's localize, then convert
result = s.dt.tz_localize('UTC').dt.tz_convert('US/Eastern')
exp_values = (DatetimeIndex(s.values).tz_localize('UTC')
.tz_convert('US/Eastern'))
expected = Series(exp_values, index=s.index, name='xxx')
tm.assert_series_equal(result, expected)
# round
s = Series(pd.to_datetime(['2012-01-01 13:00:00',
'2012-01-01 12:01:00',
'2012-01-01 08:00:00']), name='xxx')
result = s.dt.round('D')
expected = Series(pd.to_datetime(['2012-01-02', '2012-01-02',
'2012-01-01']), name='xxx')
tm.assert_series_equal(result, expected)
# round with tz
result = (s.dt.tz_localize('UTC')
.dt.tz_convert('US/Eastern')
.dt.round('D'))
exp_values = pd.to_datetime(['2012-01-01', '2012-01-01',
'2012-01-01']).tz_localize('US/Eastern')
expected = Series(exp_values, name='xxx')
tm.assert_series_equal(result, expected)
# floor
s = Series(pd.to_datetime(['2012-01-01 13:00:00',
'2012-01-01 12:01:00',
'2012-01-01 08:00:00']), name='xxx')
result = s.dt.floor('D')
expected = Series(pd.to_datetime(['2012-01-01', '2012-01-01',
'2012-01-01']), name='xxx')
tm.assert_series_equal(result, expected)
# ceil
s = Series(pd.to_datetime(['2012-01-01 13:00:00',
'2012-01-01 12:01:00',
'2012-01-01 08:00:00']), name='xxx')
result = s.dt.ceil('D')
expected = Series(pd.to_datetime(['2012-01-02', '2012-01-02',
'2012-01-02']), name='xxx')
tm.assert_series_equal(result, expected)
# datetimeindex with tz
s = Series(date_range('20130101', periods=5, tz='US/Eastern'),
name='xxx')
for prop in ok_for_dt:
# we test freq below
if prop != 'freq':
compare(s, prop)
for prop in ok_for_dt_methods:
getattr(s.dt, prop)
result = s.dt.to_pydatetime()
self.assertIsInstance(result, np.ndarray)
self.assertTrue(result.dtype == object)
result = s.dt.tz_convert('CET')
expected = Series(s._values.tz_convert('CET'),
index=s.index, name='xxx')
tm.assert_series_equal(result, expected)
tz_result = result.dt.tz
self.assertEqual(str(tz_result), 'CET')
freq_result = s.dt.freq
self.assertEqual(freq_result, DatetimeIndex(s.values,
freq='infer').freq)
# timedeltaindex
cases = [Series(timedelta_range('1 day', periods=5),
index=list('abcde'), name='xxx'),
Series(timedelta_range('1 day 01:23:45', periods=5,
freq='s'), name='xxx'),
Series(timedelta_range('2 days 01:23:45.012345', periods=5,
freq='ms'), name='xxx')]
for s in cases:
for prop in ok_for_td:
# we test freq below
if prop != 'freq':
compare(s, prop)
for prop in ok_for_td_methods:
getattr(s.dt, prop)
result = s.dt.components
self.assertIsInstance(result, DataFrame)
tm.assert_index_equal(result.index, s.index)
result = s.dt.to_pytimedelta()
self.assertIsInstance(result, np.ndarray)
self.assertTrue(result.dtype == object)
result = s.dt.total_seconds()
self.assertIsInstance(result, pd.Series)
self.assertTrue(result.dtype == 'float64')
freq_result = s.dt.freq
self.assertEqual(freq_result, TimedeltaIndex(s.values,
freq='infer').freq)
# both
index = date_range('20130101', periods=3, freq='D')
s = Series(date_range('20140204', periods=3, freq='s'),
index=index, name='xxx')
exp = Series(np.array([2014, 2014, 2014], dtype='int64'),
index=index, name='xxx')
tm.assert_series_equal(s.dt.year, exp)
exp = Series(np.array([2, 2, 2], dtype='int64'),
index=index, name='xxx')
tm.assert_series_equal(s.dt.month, exp)
exp = Series(np.array([0, 1, 2], dtype='int64'),
index=index, name='xxx')
tm.assert_series_equal(s.dt.second, exp)
exp = pd.Series([s[0]] * 3, index=index, name='xxx')
tm.assert_series_equal(s.dt.normalize(), exp)
# periodindex
cases = [Series(period_range('20130101', periods=5, freq='D'),
name='xxx')]
for s in cases:
for prop in ok_for_period:
# we test freq below
if prop != 'freq':
compare(s, prop)
for prop in ok_for_period_methods:
getattr(s.dt, prop)
freq_result = s.dt.freq
self.assertEqual(freq_result, PeriodIndex(s.values).freq)
# test limited display api
def get_dir(s):
results = [r for r in s.dt.__dir__() if not r.startswith('_')]
return list(sorted(set(results)))
s = Series(date_range('20130101', periods=5, freq='D'), name='xxx')
results = get_dir(s)
tm.assert_almost_equal(
results, list(sorted(set(ok_for_dt + ok_for_dt_methods))))
s = Series(period_range('20130101', periods=5,
freq='D', name='xxx').asobject)
results = get_dir(s)
tm.assert_almost_equal(
results, list(sorted(set(ok_for_period + ok_for_period_methods))))
# 11295
# ambiguous time error on the conversions
s = Series(pd.date_range('2015-01-01', '2016-01-01',
freq='T'), name='xxx')
s = s.dt.tz_localize('UTC').dt.tz_convert('America/Chicago')
results = get_dir(s)
tm.assert_almost_equal(
results, list(sorted(set(ok_for_dt + ok_for_dt_methods))))
exp_values = pd.date_range('2015-01-01', '2016-01-01', freq='T',
tz='UTC').tz_convert('America/Chicago')
expected = Series(exp_values, name='xxx')
tm.assert_series_equal(s, expected)
# no setting allowed
s = Series(date_range('20130101', periods=5, freq='D'), name='xxx')
with tm.assertRaisesRegexp(ValueError, "modifications"):
s.dt.hour = 5
# trying to set a copy
with pd.option_context('chained_assignment', 'raise'):
def f():
s.dt.hour[0] = 5
self.assertRaises(com.SettingWithCopyError, f)
def test_hash_error(self):
index = timedelta_range('1 days', periods=10)
with tm.assertRaisesRegexp(TypeError, "unhashable type: %r" %
type(index).__name__):
hash(index)
def test_shift(self):
# naive shift
shiftedFrame = self.tsframe.shift(5)
self.assert_index_equal(shiftedFrame.index, self.tsframe.index)
shiftedSeries = self.tsframe['A'].shift(5)
assert_series_equal(shiftedFrame['A'], shiftedSeries)
shiftedFrame = self.tsframe.shift(-5)
self.assert_index_equal(shiftedFrame.index, self.tsframe.index)
shiftedSeries = self.tsframe['A'].shift(-5)
assert_series_equal(shiftedFrame['A'], shiftedSeries)
# shift by 0
unshifted = self.tsframe.shift(0)
assert_frame_equal(unshifted, self.tsframe)
# shift by DateOffset
shiftedFrame = self.tsframe.shift(5, freq=offsets.BDay())
self.assertEqual(len(shiftedFrame), len(self.tsframe))
shiftedFrame2 = self.tsframe.shift(5, freq='B')
assert_frame_equal(shiftedFrame, shiftedFrame2)
d = self.tsframe.index[0]
shifted_d = d + offsets.BDay(5)
assert_series_equal(self.tsframe.xs(d),
shiftedFrame.xs(shifted_d),
check_names=False)
# shift int frame
int_shifted = self.intframe.shift(1) # noqa
# Shifting with PeriodIndex
ps = tm.makePeriodFrame()
shifted = ps.shift(1)
unshifted = shifted.shift(-1)
self.assert_index_equal(shifted.index, ps.index)
self.assert_index_equal(unshifted.index, ps.index)
tm.assert_numpy_array_equal(unshifted.ix[:, 0].valid().values,
ps.ix[:-1, 0].values)
shifted2 = ps.shift(1, 'B')
shifted3 = ps.shift(1, offsets.BDay())
assert_frame_equal(shifted2, shifted3)
assert_frame_equal(ps, shifted2.shift(-1, 'B'))
assertRaisesRegexp(ValueError,
'does not match PeriodIndex freq',
ps.shift,
freq='D')
# shift other axis
# GH 6371
df = DataFrame(np.random.rand(10, 5))
expected = pd.concat(
[DataFrame(np.nan, index=df.index, columns=[0]), df.iloc[:, 0:-1]],
ignore_index=True,
axis=1)
result = df.shift(1, axis=1)
assert_frame_equal(result, expected)
# shift named axis
df = DataFrame(np.random.rand(10, 5))
expected = pd.concat(
[DataFrame(np.nan, index=df.index, columns=[0]), df.iloc[:, 0:-1]],
ignore_index=True,
axis=1)
result = df.shift(1, axis='columns')
assert_frame_equal(result, expected)
