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_isnull():
assert not isnull(1.)
assert isnull(None)
assert isnull(np.NaN)
assert not isnull(np.inf)
assert not isnull(-np.inf)
# series
for s in [tm.makeFloatSeries(),tm.makeStringSeries(),
tm.makeObjectSeries(),tm.makeTimeSeries(),tm.makePeriodSeries()]:
assert(isinstance(isnull(s), Series))
# frame
for df in [tm.makeTimeDataFrame(),tm.makePeriodFrame(),tm.makeMixedDataFrame()]:
result = isnull(df)
expected = df.apply(isnull)
tm.assert_frame_equal(result, expected)
# panel
for p in [ tm.makePanel(), tm.makePeriodPanel(), tm.add_nans(tm.makePanel()) ]:
result = isnull(p)
expected = p.apply(isnull)
tm.assert_panel_equal(result, expected)
# panel 4d
for p in [ tm.makePanel4D(), tm.add_nans_panel4d(tm.makePanel4D()) ]:
result = isnull(p)
expected = p.apply(isnull)
tm.assert_panel4d_equal(result, expected)
def test_isna_isnull(self, isna_f):
assert not isna_f(1.0)
assert isna_f(None)
assert isna_f(np.NaN)
assert float("nan")
assert not isna_f(np.inf)
assert not isna_f(-np.inf)
# type
assert not isna_f(type(pd.Series()))
assert not isna_f(type(pd.DataFrame()))
# series
for s in [
tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries(),
tm.makeTimeSeries(),
tm.makePeriodSeries(),
]:
assert isinstance(isna_f(s), Series)
# frame
for df in [
tm.makeTimeDataFrame(),
tm.makePeriodFrame(),
tm.makeMixedDataFrame(),
]:
result = isna_f(df)
expected = df.apply(isna_f)
tm.assert_frame_equal(result, expected)
def test_isnull(self):
assert not isnull(1.)
assert isnull(None)
assert isnull(np.NaN)
assert float('nan')
assert not isnull(np.inf)
assert not isnull(-np.inf)
# series
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries(), tm.makeTimeSeries(),
tm.makePeriodSeries()]:
assert isinstance(isnull(s), Series)
# frame
for df in [tm.makeTimeDataFrame(), tm.makePeriodFrame(),
tm.makeMixedDataFrame()]:
result = isnull(df)
expected = df.apply(isnull)
tm.assert_frame_equal(result, expected)
# panel
with catch_warnings(record=True):
for p in [tm.makePanel(), tm.makePeriodPanel(),
tm.add_nans(tm.makePanel())]:
result = isnull(p)
expected = p.apply(isnull)
tm.assert_panel_equal(result, expected)
# panel 4d
with catch_warnings(record=True):
for p in [tm.makePanel4D(), tm.add_nans_panel4d(tm.makePanel4D())]:
result = isnull(p)
expected = p.apply(isnull)
tm.assert_panel4d_equal(result, expected)
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_isnull(self):
self.assertFalse(isnull(1.))
self.assertTrue(isnull(None))
self.assertTrue(isnull(np.NaN))
self.assertTrue(float('nan'))
self.assertFalse(isnull(np.inf))
self.assertFalse(isnull(-np.inf))
# series
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries(), tm.makeTimeSeries(),
tm.makePeriodSeries()]:
assert isinstance(isnull(s), Series)
# frame
for df in [tm.makeTimeDataFrame(), tm.makePeriodFrame(),
tm.makeMixedDataFrame()]:
result = isnull(df)
expected = df.apply(isnull)
tm.assert_frame_equal(result, expected)
# panel
with catch_warnings(record=True):
for p in [tm.makePanel(), tm.makePeriodPanel(),
tm.add_nans(tm.makePanel())]:
result = isnull(p)
expected = p.apply(isnull)
tm.assert_panel_equal(result, expected)
# panel 4d
with catch_warnings(record=True):
for p in [tm.makePanel4D(), tm.add_nans_panel4d(tm.makePanel4D())]:
result = isnull(p)
expected = p.apply(isnull)
tm.assert_panel4d_equal(result, expected)
def test_isna_isnull(self, isna_f):
assert not isna_f(1.)
assert isna_f(None)
assert isna_f(np.NaN)
assert float('nan')
assert not isna_f(np.inf)
assert not isna_f(-np.inf)
# series
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries(), tm.makeTimeSeries(),
tm.makePeriodSeries()]:
assert isinstance(isna_f(s), Series)
# frame
for df in [tm.makeTimeDataFrame(), tm.makePeriodFrame(),
tm.makeMixedDataFrame()]:
result = isna_f(df)
expected = df.apply(isna_f)
tm.assert_frame_equal(result, expected)
# panel
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
for p in [tm.makePanel(), tm.makePeriodPanel(),
tm.add_nans(tm.makePanel())]:
result = isna_f(p)
expected = p.apply(isna_f)
tm.assert_panel_equal(result, expected)
def test_isnull(self):
self.assertFalse(isnull(1.))
self.assertTrue(isnull(None))
self.assertTrue(isnull(np.NaN))
self.assertTrue(float('nan'))
self.assertFalse(isnull(np.inf))
self.assertFalse(isnull(-np.inf))
# series
for s in [
tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries(),
tm.makeTimeSeries(),
tm.makePeriodSeries()
]:
self.assertIsInstance(isnull(s), Series)
# frame
for df in [
tm.makeTimeDataFrame(),
tm.makePeriodFrame(),
tm.makeMixedDataFrame()
]:
result = isnull(df)
expected = df.apply(isnull)
tm.assert_frame_equal(result, expected)
# panel
for p in [
tm.makePanel(),
tm.makePeriodPanel(),
tm.add_nans(tm.makePanel())
]:
result = isnull(p)
expected = p.apply(isnull)
tm.assert_panel_equal(result, expected)
# panel 4d
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
for p in [tm.makePanel4D(), tm.add_nans_panel4d(tm.makePanel4D())]:
result = isnull(p)
expected = p.apply(isnull)
tm.assert_panel4d_equal(result, expected)
def test_isna_isnull(self, isna_f):
assert not isna_f(1.)
assert isna_f(None)
assert isna_f(np.NaN)
assert float('nan')
assert not isna_f(np.inf)
assert not isna_f(-np.inf)
# series
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries(), tm.makeTimeSeries(),
tm.makePeriodSeries()]:
assert isinstance(isna_f(s), Series)
# frame
for df in [tm.makeTimeDataFrame(), tm.makePeriodFrame(),
tm.makeMixedDataFrame()]:
result = isna_f(df)
expected = df.apply(isna_f)
tm.assert_frame_equal(result, expected)
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)
with pytest.raises(ValueError, match="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], :]
msg = "Freq was not given and was not set in the index"
with pytest.raises(ValueError, match=msg):
no_freq.tshift()
def test_isna_isnull(self, isna_f):
assert not isna_f(1.)
assert isna_f(None)
assert isna_f(np.NaN)
assert float('nan')
assert not isna_f(np.inf)
assert not isna_f(-np.inf)
# series
for s in [
tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries(),
tm.makeTimeSeries(),
tm.makePeriodSeries()
]:
assert isinstance(isna_f(s), Series)
# frame
for df in [
tm.makeTimeDataFrame(),
tm.makePeriodFrame(),
tm.makeMixedDataFrame()
]:
result = isna_f(df)
expected = df.apply(isna_f)
tm.assert_frame_equal(result, expected)
# panel
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
for p in [
tm.makePanel(),
tm.makePeriodPanel(),
tm.add_nans(tm.makePanel())
]:
result = isna_f(p)
expected = p.apply(isna_f)
tm.assert_panel_equal(result, expected)
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)
with pytest.raises(ValueError, match='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], :]
msg = "Freq was not given and was not set in the index"
with pytest.raises(ValueError, match=msg):
no_freq.tshift()
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.iloc[:, 0].valid().values,
ps.iloc[:-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)
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.iloc[:, 0].valid().values,
ps.iloc[:-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)
pd.Series([1.0, 2.0, 3.0]),
pd.Series([1.0, 2.0, 3.0], name="foo"),
pd.Series([1.0, 2.0, 3.0], name="foo", index=[4, 5, 6]),
pd.Series([1.0, 2.0, 3.0], name="foo", index=pd.Index([4, 5, 6], name="bar")),
pd.DataFrame({"x": ["a", "b", "c"]}),
pd.DataFrame({"x": [b"a", b"b", b"c"]}),
pd.DataFrame({"x": pd.Categorical(["a", "b", "a"], ordered=True)}),
pd.DataFrame({"x": pd.Categorical(["a", "b", "a"], ordered=False)}),
tm.makeCategoricalIndex(),
tm.makeCustomDataframe(5, 3),
tm.makeDataFrame(),
tm.makeDateIndex(),
tm.makeMissingDataframe(),
tm.makeMixedDataFrame(),
tm.makeObjectSeries(),
tm.makePeriodFrame(),
tm.makeRangeIndex(),
tm.makeTimeDataFrame(),
tm.makeTimeSeries(),
tm.makeUnicodeIndex(),
]
@pytest.mark.parametrize("df", dfs)
def test_dumps_serialize_numpy(df):
header, frames = serialize(df)
if "compression" in header:
frames = decompress(header, frames)
df2 = deserialize(header, frames)
assert_eq(df, df2)
def test_shift(self):
# naive shift
shiftedFrame = self.tsframe.shift(5)
tm.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)
tm.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())
assert 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)
tm.assert_index_equal(shifted.index, ps.index)
tm.assert_index_equal(unshifted.index, ps.index)
tm.assert_numpy_array_equal(unshifted.iloc[:, 0].dropna().values,
ps.iloc[:-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"))
msg = "does not match PeriodIndex freq"
with pytest.raises(ValueError, match=msg):
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)
pd.Series([1., 2., 3.], name='foo',
index=[4, 5, 6]),
pd.Series([1., 2., 3.], name='foo',
index=pd.Index([4, 5, 6], name='bar')),
pd.DataFrame({'x': ['a', 'b', 'c']}),
pd.DataFrame({'x': [b'a', b'b', b'c']}),
pd.DataFrame({'x': pd.Categorical(['a', 'b', 'a'], ordered=True)}),
pd.DataFrame({'x': pd.Categorical(['a', 'b', 'a'], ordered=False)}),
tm.makeCategoricalIndex(),
tm.makeCustomDataframe(5, 3),
tm.makeDataFrame(),
tm.makeDateIndex(),
tm.makeMissingDataframe(),
tm.makeMixedDataFrame(),
tm.makeObjectSeries(),
tm.makePeriodFrame(),
tm.makeRangeIndex(),
tm.makeTimeDataFrame(),
tm.makeTimeSeries(),
tm.makeUnicodeIndex(),
]
@pytest.mark.parametrize('df', dfs)
def test_dumps_serialize_numpy(df):
header, frames = serialize(df)
if 'compression' in header:
frames = decompress(header, frames)
df2 = deserialize(header, frames)
assert_eq(df, df2)