class TestSeriesFlexArithmetic:
@pytest.mark.parametrize(
"ts",
[
(lambda x: x, lambda x: x * 2, False),
(lambda x: x, lambda x: x[::2], False),
(lambda x: x, lambda x: 5, True),
(lambda x: tm.makeFloatSeries(), lambda x: tm.makeFloatSeries(),
True),
],
)
@pytest.mark.parametrize(
"opname", ["add", "sub", "mul", "floordiv", "truediv", "pow"])
def test_flex_method_equivalence(self, opname, ts):
# check that Series.{opname} behaves like Series.__{opname}__,
tser = tm.makeTimeSeries().rename("ts")
series = ts[0](tser)
other = ts[1](tser)
check_reverse = ts[2]
op = getattr(Series, opname)
alt = getattr(operator, opname)
result = op(series, other)
expected = alt(series, other)
tm.assert_almost_equal(result, expected)
if check_reverse:
rop = getattr(Series, "r" + opname)
result = rop(series, other)
expected = alt(other, series)
tm.assert_almost_equal(result, expected)
def test_op_method(self):
def check(series, other, check_reverse=False):
simple_ops = ['add', 'sub', 'mul', 'floordiv', 'truediv', 'pow']
if not compat.PY3:
simple_ops.append('div')
for opname in simple_ops:
op = getattr(Series, opname)
if op == 'div':
alt = operator.truediv
else:
alt = getattr(operator, opname)
result = op(series, other)
expected = alt(series, other)
tm.assert_almost_equal(result, expected)
if check_reverse:
rop = getattr(Series, "r" + opname)
result = rop(series, other)
expected = alt(other, series)
tm.assert_almost_equal(result, expected)
check(self.ts, self.ts * 2)
check(self.ts, self.ts[::2])
check(self.ts, 5, check_reverse=True)
check(tm.makeFloatSeries(), tm.makeFloatSeries(), check_reverse=True)
def test_op_method(self):
def check(series, other, check_reverse=False):
simple_ops = ['add', 'sub', 'mul', 'floordiv', 'truediv', 'pow']
if not compat.PY3:
simple_ops.append('div')
for opname in simple_ops:
op = getattr(Series, opname)
if op == 'div':
alt = operator.truediv
else:
alt = getattr(operator, opname)
result = op(series, other)
expected = alt(series, other)
tm.assert_almost_equal(result, expected)
if check_reverse:
rop = getattr(Series, "r" + opname)
result = rop(series, other)
expected = alt(other, series)
tm.assert_almost_equal(result, expected)
check(self.ts, self.ts * 2)
check(self.ts, self.ts[::2])
check(self.ts, 5, check_reverse=True)
check(tm.makeFloatSeries(), tm.makeFloatSeries(), check_reverse=True)
class TestSeriesFlexArithmetic:
@pytest.mark.parametrize('ts', [
(lambda x: x, lambda x: x * 2, False),
(lambda x: x, lambda x: x[::2], False),
(lambda x: x, lambda x: 5, True),
(lambda x: tm.makeFloatSeries(), lambda x: tm.makeFloatSeries(), True)
])
@pytest.mark.parametrize(
'opname', ['add', 'sub', 'mul', 'floordiv', 'truediv', 'div', 'pow'])
def test_flex_method_equivalence(self, opname, ts):
# check that Series.{opname} behaves like Series.__{opname}__,
tser = tm.makeTimeSeries().rename('ts')
series = ts[0](tser)
other = ts[1](tser)
check_reverse = ts[2]
if opname == 'div':
pytest.skip('div test only for Py3')
op = getattr(Series, opname)
if op == 'div':
alt = operator.truediv
else:
alt = getattr(operator, opname)
result = op(series, other)
expected = alt(series, other)
tm.assert_almost_equal(result, expected)
if check_reverse:
rop = getattr(Series, "r" + opname)
result = rop(series, other)
expected = alt(other, series)
tm.assert_almost_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_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_squeeze(self):
# noop
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries()]:
tm.assert_series_equal(s.squeeze(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.squeeze(), df)
# squeezing
df = tm.makeTimeDataFrame().reindex(columns=['A'])
tm.assert_series_equal(df.squeeze(), df['A'])
# don't fail with 0 length dimensions GH11229 & GH8999
empty_series = Series([], name='five')
empty_frame = DataFrame([empty_series])
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
empty_panel = Panel({'six': empty_frame})
[tm.assert_series_equal(empty_series, higher_dim.squeeze())
for higher_dim in [empty_series, empty_frame, empty_panel]]
# axis argument
df = tm.makeTimeDataFrame(nper=1).iloc[:, :1]
assert df.shape == (1, 1)
tm.assert_series_equal(df.squeeze(axis=0), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis='index'), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis=1), df.iloc[:, 0])
tm.assert_series_equal(df.squeeze(axis='columns'), df.iloc[:, 0])
assert df.squeeze() == df.iloc[0, 0]
pytest.raises(ValueError, df.squeeze, axis=2)
pytest.raises(ValueError, df.squeeze, axis='x')
df = tm.makeTimeDataFrame(3)
tm.assert_frame_equal(df.squeeze(axis=0), df)
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_transpose(self):
msg = (r"transpose\(\) got multiple values for "
r"keyword argument 'axes'")
for s in [
tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries()
]:
# calls implementation in pandas/core/base.py
tm.assert_series_equal(s.transpose(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.transpose().transpose(), df)
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
for p in [tm.makePanel()]:
tm.assert_panel_equal(
p.transpose(2, 0, 1).transpose(1, 2, 0), p)
tm.assert_raises_regex(TypeError,
msg,
p.transpose,
2,
0,
1,
axes=(2, 0, 1))
def test_numpy_transpose(self):
msg = "the 'axes' parameter is not supported"
s = tm.makeFloatSeries()
tm.assert_series_equal(
np.transpose(s), s)
tm.assert_raises_regex(ValueError, msg,
np.transpose, s, axes=1)
df = tm.makeTimeDataFrame()
tm.assert_frame_equal(np.transpose(
np.transpose(df)), df)
tm.assert_raises_regex(ValueError, msg,
np.transpose, df, axes=1)
with catch_warnings(record=True):
p = tm.makePanel()
tm.assert_panel_equal(np.transpose(
np.transpose(p, axes=(2, 0, 1)),
axes=(1, 2, 0)), p)
with catch_warnings(record=True):
p4d = tm.makePanel4D()
tm.assert_panel4d_equal(np.transpose(
np.transpose(p4d, axes=(2, 0, 3, 1)),
axes=(1, 3, 0, 2)), p4d)
def test_squeeze(self):
# noop
for s in [
tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries()
]:
tm.assert_series_equal(s.squeeze(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.squeeze(), df)
with catch_warnings(record=True):
for p in [tm.makePanel()]:
tm.assert_panel_equal(p.squeeze(), p)
with catch_warnings(record=True):
for p4d in [tm.makePanel4D()]:
tm.assert_panel4d_equal(p4d.squeeze(), p4d)
# squeezing
df = tm.makeTimeDataFrame().reindex(columns=['A'])
tm.assert_series_equal(df.squeeze(), df['A'])
with catch_warnings(record=True):
p = tm.makePanel().reindex(items=['ItemA'])
tm.assert_frame_equal(p.squeeze(), p['ItemA'])
p = tm.makePanel().reindex(items=['ItemA'], minor_axis=['A'])
tm.assert_series_equal(p.squeeze(), p.loc['ItemA', :, 'A'])
with catch_warnings(record=True):
p4d = tm.makePanel4D().reindex(labels=['label1'])
tm.assert_panel_equal(p4d.squeeze(), p4d['label1'])
with catch_warnings(record=True):
p4d = tm.makePanel4D().reindex(labels=['label1'], items=['ItemA'])
tm.assert_frame_equal(p4d.squeeze(), p4d.loc['label1', 'ItemA'])
# don't fail with 0 length dimensions GH11229 & GH8999
empty_series = Series([], name='five')
empty_frame = DataFrame([empty_series])
with catch_warnings(record=True):
empty_panel = Panel({'six': empty_frame})
[
tm.assert_series_equal(empty_series, higher_dim.squeeze())
for higher_dim in [empty_series, empty_frame, empty_panel]
]
# axis argument
df = tm.makeTimeDataFrame(nper=1).iloc[:, :1]
assert df.shape == (1, 1)
tm.assert_series_equal(df.squeeze(axis=0), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis='index'), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis=1), df.iloc[:, 0])
tm.assert_series_equal(df.squeeze(axis='columns'), df.iloc[:, 0])
assert df.squeeze() == df.iloc[0, 0]
pytest.raises(ValueError, df.squeeze, axis=2)
pytest.raises(ValueError, df.squeeze, axis='x')
df = tm.makeTimeDataFrame(3)
tm.assert_frame_equal(df.squeeze(axis=0), df)
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):
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_squeeze(self):
# noop
for s in [
tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries()
]:
tm.assert_series_equal(s.squeeze(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.squeeze(), df)
for p in [tm.makePanel()]:
tm.assert_panel_equal(p.squeeze(), p)
for p4d in [tm.makePanel4D()]:
tm.assert_panel4d_equal(p4d.squeeze(), p4d)
# squeezing
df = tm.makeTimeDataFrame().reindex(columns=['A'])
tm.assert_series_equal(df.squeeze(), df['A'])
p = tm.makePanel().reindex(items=['ItemA'])
tm.assert_frame_equal(p.squeeze(), p['ItemA'])
p = tm.makePanel().reindex(items=['ItemA'], minor_axis=['A'])
tm.assert_series_equal(p.squeeze(), p.ix['ItemA', :, 'A'])
p4d = tm.makePanel4D().reindex(labels=['label1'])
tm.assert_panel_equal(p4d.squeeze(), p4d['label1'])
p4d = tm.makePanel4D().reindex(labels=['label1'], items=['ItemA'])
tm.assert_frame_equal(p4d.squeeze(), p4d.ix['label1', 'ItemA'])
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_take_invalid_kwargs(self):
indices = [-3, 2, 0, 1]
s = tm.makeFloatSeries()
df = tm.makeTimeDataFrame()
with catch_warnings(record=True):
p = tm.makePanel()
for obj in (s, df, p):
msg = r"take\(\) got an unexpected keyword argument 'foo'"
tm.assert_raises_regex(TypeError, msg, obj.take, indices, foo=2)
msg = "the 'out' parameter is not supported"
tm.assert_raises_regex(ValueError,
msg,
obj.take,
indices,
out=indices)
msg = "the 'mode' parameter is not supported"
tm.assert_raises_regex(ValueError,
msg,
obj.take,
indices,
mode='clip')
def test_notnull():
assert notnull(1.)
assert not notnull(None)
assert not notnull(np.NaN)
with cf.option_context("mode.use_inf_as_null", False):
assert notnull(np.inf)
assert notnull(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notnull(arr)
assert result.all()
with cf.option_context("mode.use_inf_as_null", True):
assert not notnull(np.inf)
assert not notnull(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notnull(arr)
assert result.sum() == 2
with cf.option_context("mode.use_inf_as_null", False):
for s in [tm.makeFloatSeries(),tm.makeStringSeries(),
tm.makeObjectSeries(),tm.makeTimeSeries(),tm.makePeriodSeries()]:
assert(isinstance(isnull(s), Series))
def test_transpose(self):
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries()]:
# calls implementation in pandas/core/base.py
tm.assert_series_equal(s.transpose(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.transpose().transpose(), df)
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_transpose(self):
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries()]:
# calls implementation in pandas/core/base.py
tm.assert_series_equal(s.transpose(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.transpose().transpose(), df)
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
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(1.0)
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(dtype=object)))
assert not isna_f(type(pd.Series(dtype=np.float64)))
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_squeeze(self):
# noop
for s in [ tm.makeFloatSeries(), tm.makeStringSeries(), tm.makeObjectSeries() ]:
tm.assert_series_equal(s.squeeze(),s)
for df in [ tm.makeTimeDataFrame() ]:
tm.assert_frame_equal(df.squeeze(),df)
for p in [ tm.makePanel() ]:
tm.assert_panel_equal(p.squeeze(),p)
for p4d in [ tm.makePanel4D() ]:
tm.assert_panel4d_equal(p4d.squeeze(),p4d)
# squeezing
df = tm.makeTimeDataFrame().reindex(columns=['A'])
tm.assert_series_equal(df.squeeze(),df['A'])
p = tm.makePanel().reindex(items=['ItemA'])
tm.assert_frame_equal(p.squeeze(),p['ItemA'])
p = tm.makePanel().reindex(items=['ItemA'],minor_axis=['A'])
tm.assert_series_equal(p.squeeze(),p.ix['ItemA',:,'A'])
p4d = tm.makePanel4D().reindex(labels=['label1'])
tm.assert_panel_equal(p4d.squeeze(),p4d['label1'])
p4d = tm.makePanel4D().reindex(labels=['label1'],items=['ItemA'])
tm.assert_frame_equal(p4d.squeeze(),p4d.ix['label1','ItemA'])
def test_take(self):
indices = [1, 5, -2, 6, 3, -1]
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries()]:
out = s.take(indices)
expected = Series(data=s.values.take(indices),
index=s.index.take(indices), dtype=s.dtype)
tm.assert_series_equal(out, expected)
for df in [tm.makeTimeDataFrame()]:
out = df.take(indices)
expected = DataFrame(data=df.values.take(indices, axis=0),
index=df.index.take(indices),
columns=df.columns)
tm.assert_frame_equal(out, expected)
indices = [-3, 2, 0, 1]
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
for p in [tm.makePanel()]:
out = p.take(indices)
expected = Panel(data=p.values.take(indices, axis=0),
items=p.items.take(indices),
major_axis=p.major_axis,
minor_axis=p.minor_axis)
tm.assert_panel_equal(out, expected)
def test_notnull():
assert notnull(1.)
assert not notnull(None)
assert not notnull(np.NaN)
with cf.option_context("mode.use_inf_as_null", False):
assert notnull(np.inf)
assert notnull(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notnull(arr)
assert result.all()
with cf.option_context("mode.use_inf_as_null", True):
assert not notnull(np.inf)
assert not notnull(-np.inf)
arr = np.array([1.5, np.inf, 3.5, -np.inf])
result = notnull(arr)
assert result.sum() == 2
with cf.option_context("mode.use_inf_as_null", False):
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries(), tm.makeTimeSeries(),
tm.makePeriodSeries()]:
assert (isinstance(isnull(s), Series))
def test_take(self):
indices = [1, 5, -2, 6, 3, -1]
for s in [
tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries()
]:
out = s.take(indices)
expected = Series(data=s.values.take(indices),
index=s.index.take(indices),
dtype=s.dtype)
tm.assert_series_equal(out, expected)
for df in [tm.makeTimeDataFrame()]:
out = df.take(indices)
expected = DataFrame(data=df.values.take(indices, axis=0),
index=df.index.take(indices),
columns=df.columns)
tm.assert_frame_equal(out, expected)
indices = [-3, 2, 0, 1]
with catch_warnings(record=True):
for p in [tm.makePanel()]:
out = p.take(indices)
expected = Panel(data=p.values.take(indices, axis=0),
items=p.items.take(indices),
major_axis=p.major_axis,
minor_axis=p.minor_axis)
tm.assert_panel_equal(out, expected)
def test_squeeze(self):
# noop
for s in [tm.makeFloatSeries(), tm.makeStringSeries(), tm.makeObjectSeries()]:
tm.assert_series_equal(s.squeeze(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.squeeze(), df)
# squeezing
df = tm.makeTimeDataFrame().reindex(columns=["A"])
tm.assert_series_equal(df.squeeze(), df["A"])
# don't fail with 0 length dimensions GH11229 & GH8999
empty_series = Series([], name="five", dtype=np.float64)
empty_frame = DataFrame([empty_series])
tm.assert_series_equal(empty_series, empty_series.squeeze())
tm.assert_series_equal(empty_series, empty_frame.squeeze())
# axis argument
df = tm.makeTimeDataFrame(nper=1).iloc[:, :1]
assert df.shape == (1, 1)
tm.assert_series_equal(df.squeeze(axis=0), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis="index"), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis=1), df.iloc[:, 0])
tm.assert_series_equal(df.squeeze(axis="columns"), df.iloc[:, 0])
assert df.squeeze() == df.iloc[0, 0]
msg = "No axis named 2 for object type <class 'pandas.core.frame.DataFrame'>"
with pytest.raises(ValueError, match=msg):
df.squeeze(axis=2)
msg = "No axis named x for object type <class 'pandas.core.frame.DataFrame'>"
with pytest.raises(ValueError, match=msg):
df.squeeze(axis="x")
df = tm.makeTimeDataFrame(3)
tm.assert_frame_equal(df.squeeze(axis=0), df)
def test_squeeze(self):
# noop
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries()]:
tm.assert_series_equal(s.squeeze(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.squeeze(), df)
with catch_warnings(record=True):
for p in [tm.makePanel()]:
tm.assert_panel_equal(p.squeeze(), p)
with catch_warnings(record=True):
for p4d in [tm.makePanel4D()]:
tm.assert_panel4d_equal(p4d.squeeze(), p4d)
# squeezing
df = tm.makeTimeDataFrame().reindex(columns=['A'])
tm.assert_series_equal(df.squeeze(), df['A'])
with catch_warnings(record=True):
p = tm.makePanel().reindex(items=['ItemA'])
tm.assert_frame_equal(p.squeeze(), p['ItemA'])
p = tm.makePanel().reindex(items=['ItemA'], minor_axis=['A'])
tm.assert_series_equal(p.squeeze(), p.loc['ItemA', :, 'A'])
with catch_warnings(record=True):
p4d = tm.makePanel4D().reindex(labels=['label1'])
tm.assert_panel_equal(p4d.squeeze(), p4d['label1'])
with catch_warnings(record=True):
p4d = tm.makePanel4D().reindex(labels=['label1'], items=['ItemA'])
tm.assert_frame_equal(p4d.squeeze(), p4d.loc['label1', 'ItemA'])
# don't fail with 0 length dimensions GH11229 & GH8999
empty_series = Series([], name='five')
empty_frame = DataFrame([empty_series])
with catch_warnings(record=True):
empty_panel = Panel({'six': empty_frame})
[tm.assert_series_equal(empty_series, higher_dim.squeeze())
for higher_dim in [empty_series, empty_frame, empty_panel]]
# axis argument
df = tm.makeTimeDataFrame(nper=1).iloc[:, :1]
assert df.shape == (1, 1)
tm.assert_series_equal(df.squeeze(axis=0), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis='index'), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis=1), df.iloc[:, 0])
tm.assert_series_equal(df.squeeze(axis='columns'), df.iloc[:, 0])
assert df.squeeze() == df.iloc[0, 0]
pytest.raises(ValueError, df.squeeze, axis=2)
pytest.raises(ValueError, df.squeeze, axis='x')
df = tm.makeTimeDataFrame(3)
tm.assert_frame_equal(df.squeeze(axis=0), df)
def test_take(self):
indices = [1, 5, -2, 6, 3, -1]
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries()]:
out = s.take(indices)
expected = Series(data=s.values.take(indices),
index=s.index.take(indices), dtype=s.dtype)
tm.assert_series_equal(out, expected)
for df in [tm.makeTimeDataFrame()]:
out = df.take(indices)
expected = DataFrame(data=df.values.take(indices, axis=0),
index=df.index.take(indices),
columns=df.columns)
tm.assert_frame_equal(out, expected)
def test_numpy_transpose(self):
msg = "the 'axes' parameter is not supported"
s = tm.makeFloatSeries()
tm.assert_series_equal(np.transpose(s), s)
with pytest.raises(ValueError, match=msg):
np.transpose(s, axes=1)
df = tm.makeTimeDataFrame()
tm.assert_frame_equal(np.transpose(np.transpose(df)), df)
with pytest.raises(ValueError, match=msg):
np.transpose(df, axes=1)
def test_numpy_transpose(self):
msg = "the 'axes' parameter is not supported"
s = tm.makeFloatSeries()
tm.assert_series_equal(np.transpose(s), s)
with pytest.raises(ValueError, match=msg):
np.transpose(s, axes=1)
df = tm.makeTimeDataFrame()
tm.assert_frame_equal(np.transpose(np.transpose(df)), df)
with pytest.raises(ValueError, match=msg):
np.transpose(df, axes=1)
def test_take(self):
indices = [1, 5, -2, 6, 3, -1]
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries()]:
out = s.take(indices)
expected = Series(data=s.values.take(indices),
index=s.index.take(indices), dtype=s.dtype)
tm.assert_series_equal(out, expected)
for df in [tm.makeTimeDataFrame()]:
out = df.take(indices)
expected = DataFrame(data=df.values.take(indices, axis=0),
index=df.index.take(indices),
columns=df.columns)
tm.assert_frame_equal(out, expected)
def test_numpy_transpose(self):
msg = "the 'axes' parameter is not supported"
s = tm.makeFloatSeries()
tm.assert_series_equal(np.transpose(s), s)
tm.assert_raises_regex(ValueError, msg, np.transpose, s, axes=1)
df = tm.makeTimeDataFrame()
tm.assert_frame_equal(np.transpose(np.transpose(df)), df)
tm.assert_raises_regex(ValueError, msg, np.transpose, df, axes=1)
with catch_warnings(record=True):
p = tm.makePanel()
tm.assert_panel_equal(
np.transpose(np.transpose(p, axes=(2, 0, 1)), axes=(1, 2, 0)),
p)
def test_transpose(self):
msg = (r"transpose\(\) got multiple values for "
r"keyword argument 'axes'")
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries()]:
# calls implementation in pandas/core/base.py
tm.assert_series_equal(s.transpose(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.transpose().transpose(), df)
with catch_warnings(record=True):
for p in [tm.makePanel()]:
tm.assert_panel_equal(p.transpose(2, 0, 1)
.transpose(1, 2, 0), p)
tm.assert_raises_regex(TypeError, msg, p.transpose,
2, 0, 1, axes=(2, 0, 1))
def test_isnull():
assert not isnull(1.)
assert isnull(None)
assert isnull(np.NaN)
assert not isnull(np.inf)
assert not isnull(-np.inf)
for s in [tm.makeFloatSeries(),tm.makeStringSeries(),
tm.makeObjectSeries(),tm.makeTimeSeries(),tm.makePeriodSeries()]:
assert(isinstance(isnull(s), np.ndarray))
# call on DataFrame
df = DataFrame(np.random.randn(10, 5))
df['foo'] = 'bar'
result = isnull(df)
expected = result.apply(isnull)
tm.assert_frame_equal(result, expected)
def test_take_invalid_kwargs(self):
indices = [-3, 2, 0, 1]
s = tm.makeFloatSeries()
df = tm.makeTimeDataFrame()
for obj in (s, df):
msg = r"take\(\) got an unexpected keyword argument 'foo'"
with pytest.raises(TypeError, match=msg):
obj.take(indices, foo=2)
msg = "the 'out' parameter is not supported"
with pytest.raises(ValueError, match=msg):
obj.take(indices, out=indices)
msg = "the 'mode' parameter is not supported"
with pytest.raises(ValueError, match=msg):
obj.take(indices, mode='clip')
def test_isnull():
assert not isnull(1.)
assert isnull(None)
assert isnull(np.NaN)
assert not isnull(np.inf)
assert not isnull(-np.inf)
for s in [tm.makeFloatSeries(),tm.makeStringSeries(),
tm.makeObjectSeries(),tm.makeTimeSeries(),tm.makePeriodSeries()]:
assert(isinstance(isnull(s), Series))
# call on DataFrame
df = DataFrame(np.random.randn(10, 5))
df['foo'] = 'bar'
result = isnull(df)
expected = result.apply(isnull)
tm.assert_frame_equal(result, expected)
def test_squeeze(self):
# noop
for s in [
tm.makeFloatSeries(),
tm.makeStringSeries(),
tm.makeObjectSeries()
]:
tm.assert_series_equal(s.squeeze(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.squeeze(), df)
# squeezing
df = tm.makeTimeDataFrame().reindex(columns=['A'])
tm.assert_series_equal(df.squeeze(), df['A'])
# don't fail with 0 length dimensions GH11229 & GH8999
empty_series = Series([], name='five')
empty_frame = DataFrame([empty_series])
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
empty_panel = Panel({'six': empty_frame})
[
tm.assert_series_equal(empty_series, higher_dim.squeeze())
for higher_dim in [empty_series, empty_frame, empty_panel]
]
# axis argument
df = tm.makeTimeDataFrame(nper=1).iloc[:, :1]
assert df.shape == (1, 1)
tm.assert_series_equal(df.squeeze(axis=0), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis='index'), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis=1), df.iloc[:, 0])
tm.assert_series_equal(df.squeeze(axis='columns'), df.iloc[:, 0])
assert df.squeeze() == df.iloc[0, 0]
msg = ("No axis named 2 for object type <class"
" 'pandas.core.frame.DataFrame'>")
with pytest.raises(ValueError, match=msg):
df.squeeze(axis=2)
msg = ("No axis named x for object type <class"
" 'pandas.core.frame.DataFrame'>")
with pytest.raises(ValueError, match=msg):
df.squeeze(axis='x')
df = tm.makeTimeDataFrame(3)
tm.assert_frame_equal(df.squeeze(axis=0), df)
def test_take_invalid_kwargs(self):
indices = [-3, 2, 0, 1]
s = tm.makeFloatSeries()
df = tm.makeTimeDataFrame()
for obj in (s, df):
msg = r"take\(\) got an unexpected keyword argument 'foo'"
with pytest.raises(TypeError, match=msg):
obj.take(indices, foo=2)
msg = "the 'out' parameter is not supported"
with pytest.raises(ValueError, match=msg):
obj.take(indices, out=indices)
msg = "the 'mode' parameter is not supported"
with pytest.raises(ValueError, match=msg):
obj.take(indices, mode="clip")
def test_take_invalid_kwargs(self):
indices = [-3, 2, 0, 1]
s = tm.makeFloatSeries()
df = tm.makeTimeDataFrame()
with catch_warnings(record=True):
p = tm.makePanel()
for obj in (s, df, p):
msg = r"take\(\) got an unexpected keyword argument 'foo'"
tm.assert_raises_regex(TypeError, msg, obj.take,
indices, foo=2)
msg = "the 'out' parameter is not supported"
tm.assert_raises_regex(ValueError, msg, obj.take,
indices, out=indices)
msg = "the 'mode' parameter is not supported"
tm.assert_raises_regex(ValueError, msg, obj.take,
indices, mode='clip')
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_take_invalid_kwargs(self):
indices = [-3, 2, 0, 1]
s = tm.makeFloatSeries()
df = tm.makeTimeDataFrame()
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
p = tm.makePanel()
for obj in (s, df, p):
msg = r"take\(\) got an unexpected keyword argument 'foo'"
with pytest.raises(TypeError, match=msg):
obj.take(indices, foo=2)
msg = "the 'out' parameter is not supported"
with pytest.raises(ValueError, match=msg):
obj.take(indices, out=indices)
msg = "the 'mode' parameter is not supported"
with pytest.raises(ValueError, match=msg):
obj.take(indices, mode='clip')
def test_numpy_transpose(self):
msg = "the 'axes' parameter is not supported"
s = tm.makeFloatSeries()
tm.assert_series_equal(np.transpose(s), s)
with pytest.raises(ValueError, match=msg):
np.transpose(s, axes=1)
df = tm.makeTimeDataFrame()
tm.assert_frame_equal(np.transpose(np.transpose(df)), df)
with pytest.raises(ValueError, match=msg):
np.transpose(df, axes=1)
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
p = tm.makePanel()
tm.assert_panel_equal(
np.transpose(np.transpose(p, axes=(2, 0, 1)), axes=(1, 2, 0)),
p)
def test_take_invalid_kwargs(self):
indices = [-3, 2, 0, 1]
s = tm.makeFloatSeries()
df = tm.makeTimeDataFrame()
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
p = tm.makePanel()
for obj in (s, df, p):
msg = r"take\(\) got an unexpected keyword argument 'foo'"
with pytest.raises(TypeError, match=msg):
obj.take(indices, foo=2)
msg = "the 'out' parameter is not supported"
with pytest.raises(ValueError, match=msg):
obj.take(indices, out=indices)
msg = "the 'mode' parameter is not supported"
with pytest.raises(ValueError, match=msg):
obj.take(indices, mode='clip')
def test_numpy_transpose(self):
msg = "the 'axes' parameter is not supported"
s = tm.makeFloatSeries()
tm.assert_series_equal(np.transpose(s), s)
with pytest.raises(ValueError, match=msg):
np.transpose(s, axes=1)
df = tm.makeTimeDataFrame()
tm.assert_frame_equal(np.transpose(np.transpose(df)), df)
with pytest.raises(ValueError, match=msg):
np.transpose(df, axes=1)
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
p = tm.makePanel()
tm.assert_panel_equal(np.transpose(
np.transpose(p, axes=(2, 0, 1)),
axes=(1, 2, 0)), p)
def test_squeeze(self):
# noop
for s in [tm.makeFloatSeries(), tm.makeStringSeries(),
tm.makeObjectSeries()]:
tm.assert_series_equal(s.squeeze(), s)
for df in [tm.makeTimeDataFrame()]:
tm.assert_frame_equal(df.squeeze(), df)
# squeezing
df = tm.makeTimeDataFrame().reindex(columns=['A'])
tm.assert_series_equal(df.squeeze(), df['A'])
# don't fail with 0 length dimensions GH11229 & GH8999
empty_series = Series([], name='five')
empty_frame = DataFrame([empty_series])
[tm.assert_series_equal(empty_series, higher_dim.squeeze())
for higher_dim in [empty_series, empty_frame]]
# axis argument
df = tm.makeTimeDataFrame(nper=1).iloc[:, :1]
assert df.shape == (1, 1)
tm.assert_series_equal(df.squeeze(axis=0), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis='index'), df.iloc[0])
tm.assert_series_equal(df.squeeze(axis=1), df.iloc[:, 0])
tm.assert_series_equal(df.squeeze(axis='columns'), df.iloc[:, 0])
assert df.squeeze() == df.iloc[0, 0]
msg = ("No axis named 2 for object type <class"
" 'pandas.core.frame.DataFrame'>")
with pytest.raises(ValueError, match=msg):
df.squeeze(axis=2)
msg = ("No axis named x for object type <class"
" 'pandas.core.frame.DataFrame'>")
with pytest.raises(ValueError, match=msg):
df.squeeze(axis='x')
df = tm.makeTimeDataFrame(3)
tm.assert_frame_equal(df.squeeze(axis=0), df)
import pandas.util.testing as pd_samples
from pandas.testing import assert_frame_equal, assert_series_equal
import pytest
from pandasbikeshed.fancyfilter import me
ex_df = pd_samples.makeDataFrame()
ex_df.iloc[0, :] = 0
ex_df.iloc[1, :] = np.nan
ex_df.iloc[2, :] = np.inf
ex_df2 = pd.DataFrame({'A': ['a', 'b', 'c'], 'B': ['c', 'b', 'a']})
ex_df2.set_index('B', inplace=True)
ex_series = pd_samples.makeFloatSeries('test')
def test_nullindexing():
assert_frame_equal(ex_df[me], ex_df)
assert_series_equal(ex_series[me], ex_series)
@pytest.mark.parametrize('fancy,traditional', [
(ex_df[me.A < 0], ex_df[ex_df.A < 0]),
(ex_df[me.A <= 0], ex_df[ex_df.A <= 0]),
(ex_df[me.A == 0], ex_df[ex_df.A == 0]),
(ex_df[me.A != 0], ex_df[ex_df.A != 0]),
(ex_df[me.A >= 0], ex_df[ex_df.A >= 0]),
(ex_df[me.A > 0], ex_df[ex_df.A > 0]),
])
def test_numpy_squeeze(self):
s = tm.makeFloatSeries()
tm.assert_series_equal(np.squeeze(s), s)
df = tm.makeTimeDataFrame().reindex(columns=["A"])
tm.assert_series_equal(np.squeeze(df), df["A"])
def test_numpy_squeeze(self):
s = tm.makeFloatSeries()
tm.assert_series_equal(np.squeeze(s), s)
df = tm.makeTimeDataFrame().reindex(columns=['A'])
tm.assert_series_equal(np.squeeze(df), df['A'])
class TestSeriesOperators(TestData):
@pytest.mark.parametrize(
'ts',
[
(lambda x: x, lambda x: x * 2, False),
(lambda x: x, lambda x: x[::2], False),
(lambda x: x, lambda x: 5, True),
(lambda x: tm.makeFloatSeries(),
lambda x: tm.makeFloatSeries(),
True)
])
@pytest.mark.parametrize('opname', ['add', 'sub', 'mul', 'floordiv',
'truediv', 'div', 'pow'])
def test_op_method(self, opname, ts):
# check that Series.{opname} behaves like Series.__{opname}__,
tser = tm.makeTimeSeries().rename('ts')
series = ts[0](tser)
other = ts[1](tser)
check_reverse = ts[2]
if opname == 'div' and compat.PY3:
pytest.skip('div test only for Py3')
op = getattr(Series, opname)
if op == 'div':
alt = operator.truediv
else:
alt = getattr(operator, opname)
result = op(series, other)
expected = alt(series, other)
assert_almost_equal(result, expected)
if check_reverse:
rop = getattr(Series, "r" + opname)
result = rop(series, other)
expected = alt(other, series)
assert_almost_equal(result, expected)
def test_operators_empty_int_corner(self):
s1 = Series([], [], dtype=np.int32)
s2 = Series({'x': 0.})
assert_series_equal(s1 * s2, Series([np.nan], index=['x']))
def test_ops_datetimelike_align(self):
# GH 7500
# datetimelike ops need to align
dt = Series(date_range('2012-1-1', periods=3, freq='D'))
dt.iloc[2] = np.nan
dt2 = dt[::-1]
expected = Series([timedelta(0), timedelta(0), pd.NaT])
# name is reset
result = dt2 - dt
assert_series_equal(result, expected)
expected = Series(expected, name=0)
result = (dt2.to_frame() - dt.to_frame())[0]
assert_series_equal(result, expected)
def test_operators_corner(self):
series = self.ts
empty = Series([], index=Index([]))
result = series + empty
assert np.isnan(result).all()
result = empty + Series([], index=Index([]))
assert len(result) == 0
# TODO: this returned NotImplemented earlier, what to do?
# deltas = Series([timedelta(1)] * 5, index=np.arange(5))
# sub_deltas = deltas[::2]
# deltas5 = deltas * 5
# deltas = deltas + sub_deltas
# float + int
int_ts = self.ts.astype(int)[:-5]
added = self.ts + int_ts
expected = Series(self.ts.values[:-5] + int_ts.values,
index=self.ts.index[:-5], name='ts')
tm.assert_series_equal(added[:-5], expected)
pairings = []
for op in ['add', 'sub', 'mul', 'pow', 'truediv', 'floordiv']:
fv = 0
lop = getattr(Series, op)
lequiv = getattr(operator, op)
rop = getattr(Series, 'r' + op)
# bind op at definition time...
requiv = lambda x, y, op=op: getattr(operator, op)(y, x)
pairings.append((lop, lequiv, fv))
pairings.append((rop, requiv, fv))
if compat.PY3:
pairings.append((Series.div, operator.truediv, 1))
pairings.append((Series.rdiv, lambda x, y: operator.truediv(y, x), 1))
else:
pairings.append((Series.div, operator.div, 1))
pairings.append((Series.rdiv, lambda x, y: operator.div(y, x), 1))
@pytest.mark.parametrize('op, equiv_op, fv', pairings)
def test_operators_combine(self, op, equiv_op, fv):
def _check_fill(meth, op, a, b, fill_value=0):
exp_index = a.index.union(b.index)
a = a.reindex(exp_index)
b = b.reindex(exp_index)
amask = isna(a)
bmask = isna(b)
exp_values = []
for i in range(len(exp_index)):
with np.errstate(all='ignore'):
if amask[i]:
if bmask[i]:
exp_values.append(nan)
continue
exp_values.append(op(fill_value, b[i]))
elif bmask[i]:
if amask[i]:
exp_values.append(nan)
continue
exp_values.append(op(a[i], fill_value))
else:
exp_values.append(op(a[i], b[i]))
result = meth(a, b, fill_value=fill_value)
expected = Series(exp_values, exp_index)
assert_series_equal(result, expected)
a = Series([nan, 1., 2., 3., nan], index=np.arange(5))
b = Series([nan, 1, nan, 3, nan, 4.], index=np.arange(6))
result = op(a, b)
exp = equiv_op(a, b)
assert_series_equal(result, exp)
_check_fill(op, equiv_op, a, b, fill_value=fv)
# should accept axis=0 or axis='rows'
op(a, b, axis=0)
def test_operators_na_handling(self):
from decimal import Decimal
from datetime import date
s = Series([Decimal('1.3'), Decimal('2.3')],
index=[date(2012, 1, 1), date(2012, 1, 2)])
result = s + s.shift(1)
result2 = s.shift(1) + s
assert isna(result[0])
assert isna(result2[0])
def test_op_duplicate_index(self):
# GH14227
s1 = Series([1, 2], index=[1, 1])
s2 = Series([10, 10], index=[1, 2])
result = s1 + s2
expected = pd.Series([11, 12, np.nan], index=[1, 1, 2])
assert_series_equal(result, expected)
@pytest.mark.parametrize(
"test_input,error_type",
[
(pd.Series([]), ValueError),
# For strings, or any Series with dtype 'O'
(pd.Series(['foo', 'bar', 'baz']), TypeError),
(pd.Series([(1,), (2,)]), TypeError),
# For mixed data types
(
pd.Series(['foo', 'foo', 'bar', 'bar', None, np.nan, 'baz']),
TypeError
),
]
)
def test_assert_idxminmax_raises(self, test_input, error_type):
"""
Cases where ``Series.argmax`` and related should raise an exception
"""
with pytest.raises(error_type):
test_input.idxmin()
with pytest.raises(error_type):
test_input.idxmin(skipna=False)
with pytest.raises(error_type):
test_input.idxmax()
with pytest.raises(error_type):
test_input.idxmax(skipna=False)
def test_idxminmax_with_inf(self):
# For numeric data with NA and Inf (GH #13595)
s = pd.Series([0, -np.inf, np.inf, np.nan])
assert s.idxmin() == 1
assert np.isnan(s.idxmin(skipna=False))
assert s.idxmax() == 2
assert np.isnan(s.idxmax(skipna=False))
# Using old-style behavior that treats floating point nan, -inf, and
# +inf as missing
with pd.option_context('mode.use_inf_as_na', True):
assert s.idxmin() == 0
assert np.isnan(s.idxmin(skipna=False))
assert s.idxmax() == 0
np.isnan(s.idxmax(skipna=False))
class TestSeriesOperators(TestData):
@pytest.mark.parametrize('ts', [
(lambda x: x, lambda x: x * 2, False),
(lambda x: x, lambda x: x[::2], False),
(lambda x: x, lambda x: 5, True),
(lambda x: tm.makeFloatSeries(), lambda x: tm.makeFloatSeries(), True)
])
@pytest.mark.parametrize(
'opname', ['add', 'sub', 'mul', 'floordiv', 'truediv', 'div', 'pow'])
def test_op_method(self, opname, ts):
# check that Series.{opname} behaves like Series.__{opname}__,
tser = tm.makeTimeSeries().rename('ts')
series = ts[0](tser)
other = ts[1](tser)
check_reverse = ts[2]
if opname == 'div' and compat.PY3:
pytest.skip('div test only for Py3')
op = getattr(Series, opname)
if op == 'div':
alt = operator.truediv
else:
alt = getattr(operator, opname)
result = op(series, other)
expected = alt(series, other)
assert_almost_equal(result, expected)
if check_reverse:
rop = getattr(Series, "r" + opname)
result = rop(series, other)
expected = alt(other, series)
assert_almost_equal(result, expected)
def test_neg(self):
assert_series_equal(-self.series, -1 * self.series)
def test_invert(self):
assert_series_equal(-(self.series < 0), ~(self.series < 0))
def test_operators_empty_int_corner(self):
s1 = Series([], [], dtype=np.int32)
s2 = Series({'x': 0.})
assert_series_equal(s1 * s2, Series([np.nan], index=['x']))
def test_ops_datetimelike_align(self):
# GH 7500
# datetimelike ops need to align
dt = Series(date_range('2012-1-1', periods=3, freq='D'))
dt.iloc[2] = np.nan
dt2 = dt[::-1]
expected = Series([timedelta(0), timedelta(0), pd.NaT])
# name is reset
result = dt2 - dt
assert_series_equal(result, expected)
expected = Series(expected, name=0)
result = (dt2.to_frame() - dt.to_frame())[0]
assert_series_equal(result, expected)
@pytest.mark.parametrize('op', [
operator.and_, operator.or_, operator.xor,
pytest.param(ops.rand_,
marks=pytest.mark.xfail(reason="GH#22092 Index "
"implementation returns "
"Index",
raises=AssertionError,
strict=True)),
pytest.param(ops.ror_,
marks=pytest.mark.xfail(reason="GH#22092 Index "
"implementation raises",
raises=ValueError,
strict=True)),
pytest.param(ops.rxor,
marks=pytest.mark.xfail(reason="GH#22092 Index "
"implementation raises",
raises=TypeError,
strict=True))
])
def test_bool_ops_with_index(self, op):
# GH#22092, GH#19792
ser = Series([True, True, False, False])
idx1 = Index([True, False, True, False])
idx2 = Index([1, 0, 1, 0])
expected = Series([op(ser[n], idx1[n]) for n in range(len(ser))])
result = op(ser, idx1)
assert_series_equal(result, expected)
expected = Series([op(ser[n], idx2[n]) for n in range(len(ser))],
dtype=bool)
result = op(ser, idx2)
assert_series_equal(result, expected)
def test_operators_bitwise(self):
# GH 9016: support bitwise op for integer types
index = list('bca')
s_tft = Series([True, False, True], index=index)
s_fff = Series([False, False, False], index=index)
s_tff = Series([True, False, False], index=index)
s_empty = Series([])
# TODO: unused
# s_0101 = Series([0, 1, 0, 1])
s_0123 = Series(range(4), dtype='int64')
s_3333 = Series([3] * 4)
s_4444 = Series([4] * 4)
res = s_tft & s_empty
expected = s_fff
assert_series_equal(res, expected)
res = s_tft | s_empty
expected = s_tft
assert_series_equal(res, expected)
res = s_0123 & s_3333
expected = Series(range(4), dtype='int64')
assert_series_equal(res, expected)
res = s_0123 | s_4444
expected = Series(range(4, 8), dtype='int64')
assert_series_equal(res, expected)
s_a0b1c0 = Series([1], list('b'))
res = s_tft & s_a0b1c0
expected = s_tff.reindex(list('abc'))
assert_series_equal(res, expected)
res = s_tft | s_a0b1c0
expected = s_tft.reindex(list('abc'))
assert_series_equal(res, expected)
n0 = 0
res = s_tft & n0
expected = s_fff
assert_series_equal(res, expected)
res = s_0123 & n0
expected = Series([0] * 4)
assert_series_equal(res, expected)
n1 = 1
res = s_tft & n1
expected = s_tft
assert_series_equal(res, expected)
res = s_0123 & n1
expected = Series([0, 1, 0, 1])
assert_series_equal(res, expected)
s_1111 = Series([1] * 4, dtype='int8')
res = s_0123 & s_1111
expected = Series([0, 1, 0, 1], dtype='int64')
assert_series_equal(res, expected)
res = s_0123.astype(np.int16) | s_1111.astype(np.int32)
expected = Series([1, 1, 3, 3], dtype='int32')
assert_series_equal(res, expected)
with pytest.raises(TypeError):
s_1111 & 'a'
with pytest.raises(TypeError):
s_1111 & ['a', 'b', 'c', 'd']
with pytest.raises(TypeError):
s_0123 & np.NaN
with pytest.raises(TypeError):
s_0123 & 3.14
with pytest.raises(TypeError):
s_0123 & [0.1, 4, 3.14, 2]
# s_0123 will be all false now because of reindexing like s_tft
if compat.PY3:
# unable to sort incompatible object via .union.
exp = Series([False] * 7, index=['b', 'c', 'a', 0, 1, 2, 3])
with tm.assert_produces_warning(RuntimeWarning):
assert_series_equal(s_tft & s_0123, exp)
else:
exp = Series([False] * 7, index=[0, 1, 2, 3, 'a', 'b', 'c'])
assert_series_equal(s_tft & s_0123, exp)
# s_tft will be all false now because of reindexing like s_0123
if compat.PY3:
# unable to sort incompatible object via .union.
exp = Series([False] * 7, index=[0, 1, 2, 3, 'b', 'c', 'a'])
with tm.assert_produces_warning(RuntimeWarning):
assert_series_equal(s_0123 & s_tft, exp)
else:
exp = Series([False] * 7, index=[0, 1, 2, 3, 'a', 'b', 'c'])
assert_series_equal(s_0123 & s_tft, exp)
assert_series_equal(s_0123 & False, Series([False] * 4))
assert_series_equal(s_0123 ^ False, Series([False, True, True, True]))
assert_series_equal(s_0123 & [False], Series([False] * 4))
assert_series_equal(s_0123 & (False), Series([False] * 4))
assert_series_equal(s_0123 & Series([False, np.NaN, False, False]),
Series([False] * 4))
s_ftft = Series([False, True, False, True])
assert_series_equal(s_0123 & Series([0.1, 4, -3.14, 2]), s_ftft)
s_abNd = Series(['a', 'b', np.NaN, 'd'])
res = s_0123 & s_abNd
expected = s_ftft
assert_series_equal(res, expected)
def test_scalar_na_cmp_corners(self):
s = Series([2, 3, 4, 5, 6, 7, 8, 9, 10])
def tester(a, b):
return a & b
with pytest.raises(TypeError):
s & datetime(2005, 1, 1)
s = Series([2, 3, 4, 5, 6, 7, 8, 9, datetime(2005, 1, 1)])
s[::2] = np.nan
expected = Series(True, index=s.index)
expected[::2] = False
result = s & list(s)
assert_series_equal(result, expected)
d = DataFrame({'A': s})
# TODO: Fix this exception - needs to be fixed! (see GH5035)
# (previously this was a TypeError because series returned
# NotImplemented
# this is an alignment issue; these are equivalent
# https://github.com/pandas-dev/pandas/issues/5284
pytest.raises(ValueError, lambda: d.__and__(s, axis='columns'))
pytest.raises(ValueError, tester, s, d)
# this is wrong as its not a boolean result
# result = d.__and__(s,axis='index')
def test_operators_corner(self):
series = self.ts
empty = Series([], index=Index([]))
result = series + empty
assert np.isnan(result).all()
result = empty + Series([], index=Index([]))
assert len(result) == 0
# TODO: this returned NotImplemented earlier, what to do?
# deltas = Series([timedelta(1)] * 5, index=np.arange(5))
# sub_deltas = deltas[::2]
# deltas5 = deltas * 5
# deltas = deltas + sub_deltas
# float + int
int_ts = self.ts.astype(int)[:-5]
added = self.ts + int_ts
expected = Series(self.ts.values[:-5] + int_ts.values,
index=self.ts.index[:-5],
name='ts')
tm.assert_series_equal(added[:-5], expected)
pairings = []
for op in ['add', 'sub', 'mul', 'pow', 'truediv', 'floordiv']:
fv = 0
lop = getattr(Series, op)
lequiv = getattr(operator, op)
rop = getattr(Series, 'r' + op)
# bind op at definition time...
requiv = lambda x, y, op=op: getattr(operator, op)(y, x)
pairings.append((lop, lequiv, fv))
pairings.append((rop, requiv, fv))
if compat.PY3:
pairings.append((Series.div, operator.truediv, 1))
pairings.append((Series.rdiv, lambda x, y: operator.truediv(y, x), 1))
else:
pairings.append((Series.div, operator.div, 1))
pairings.append((Series.rdiv, lambda x, y: operator.div(y, x), 1))
@pytest.mark.parametrize('op, equiv_op, fv', pairings)
def test_operators_combine(self, op, equiv_op, fv):
def _check_fill(meth, op, a, b, fill_value=0):
exp_index = a.index.union(b.index)
a = a.reindex(exp_index)
b = b.reindex(exp_index)
amask = isna(a)
bmask = isna(b)
exp_values = []
for i in range(len(exp_index)):
with np.errstate(all='ignore'):
if amask[i]:
if bmask[i]:
exp_values.append(nan)
continue
exp_values.append(op(fill_value, b[i]))
elif bmask[i]:
if amask[i]:
exp_values.append(nan)
continue
exp_values.append(op(a[i], fill_value))
else:
exp_values.append(op(a[i], b[i]))
result = meth(a, b, fill_value=fill_value)
expected = Series(exp_values, exp_index)
assert_series_equal(result, expected)
a = Series([nan, 1., 2., 3., nan], index=np.arange(5))
b = Series([nan, 1, nan, 3, nan, 4.], index=np.arange(6))
result = op(a, b)
exp = equiv_op(a, b)
assert_series_equal(result, exp)
_check_fill(op, equiv_op, a, b, fill_value=fv)
# should accept axis=0 or axis='rows'
op(a, b, axis=0)
def test_operators_na_handling(self):
from decimal import Decimal
from datetime import date
s = Series([Decimal('1.3'), Decimal('2.3')],
index=[date(2012, 1, 1), date(2012, 1, 2)])
result = s + s.shift(1)
result2 = s.shift(1) + s
assert isna(result[0])
assert isna(result2[0])
def test_op_duplicate_index(self):
# GH14227
s1 = Series([1, 2], index=[1, 1])
s2 = Series([10, 10], index=[1, 2])
result = s1 + s2
expected = pd.Series([11, 12, np.nan], index=[1, 1, 2])
assert_series_equal(result, expected)
@pytest.mark.parametrize(
"test_input,error_type",
[
(pd.Series([]), ValueError),
# For strings, or any Series with dtype 'O'
(pd.Series(['foo', 'bar', 'baz']), TypeError),
(pd.Series([(1, ), (2, )]), TypeError),
# For mixed data types
(pd.Series(['foo', 'foo', 'bar', 'bar', None, np.nan, 'baz'
]), TypeError),
])
def test_assert_idxminmax_raises(self, test_input, error_type):
"""
Cases where ``Series.argmax`` and related should raise an exception
"""
with pytest.raises(error_type):
test_input.idxmin()
with pytest.raises(error_type):
test_input.idxmin(skipna=False)
with pytest.raises(error_type):
test_input.idxmax()
with pytest.raises(error_type):
test_input.idxmax(skipna=False)
def test_idxminmax_with_inf(self):
# For numeric data with NA and Inf (GH #13595)
s = pd.Series([0, -np.inf, np.inf, np.nan])
assert s.idxmin() == 1
assert np.isnan(s.idxmin(skipna=False))
assert s.idxmax() == 2
assert np.isnan(s.idxmax(skipna=False))
# Using old-style behavior that treats floating point nan, -inf, and
# +inf as missing
with pd.option_context('mode.use_inf_as_na', True):
assert s.idxmin() == 0
assert np.isnan(s.idxmin(skipna=False))
assert s.idxmax() == 0
np.isnan(s.idxmax(skipna=False))
np.zeros(10) pd.Series(np.arange(4,9)) # using the numpy function pd.Series(np.linspace(0,9,5)) # allows to specify the number of values to be created btw boundaries pd.Series(np.random.normal(size=5)) np.random.randint(50,101,10) a = np.array([4] * 16) a[1::] = [42] * 15 a[1:8:2] = 16 import pandas.util.testing as tm tm.N, tm.K = 5,3 tm.makeFloatSeries(), tm.makeBoolIndex(), tm.makeCategoricalIndex() tm.makeCustomIndex(nentries=4,nlevels=2), tm.makeFloatIndex(), tm.makeIntIndex() tm.makeMultiIndex(), tm.makeRangeIndex(), tm.makeIntervalIndex() # All possible combinations (Permutations) from itertools import permutations my_list = [1,2,3] perm = list(permutations(my_list)) #(1, 2, 3) #(1, 3, 2) #(2, 1, 3) #(2, 3, 1) #(3, 1, 2) #(3, 2, 1)