def object_series():
"""
Fixture for Series of dtype datetime64[ns] with Index of unique strings
"""
s = tm.makeObjectSeries()
s.name = 'objects'
return s
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 setUp(self):
super(TestSeries, self).setUp()
self.d = {}
s = tm.makeStringSeries()
s.name = "string"
self.d["string"] = s
s = tm.makeObjectSeries()
s.name = "object"
self.d["object"] = s
s = Series(tslib.iNaT, dtype="M8[ns]", index=range(5))
self.d["date"] = s
data = {
"A": [0.0, 1.0, 2.0, 3.0, np.nan],
"B": [0, 1, 0, 1, 0],
"C": ["foo1", "foo2", "foo3", "foo4", "foo5"],
"D": date_range("1/1/2009", periods=5),
"E": [0.0, 1, Timestamp("20100101"), "foo", 2.0],
}
self.d["float"] = Series(data["A"])
self.d["int"] = Series(data["B"])
self.d["mixed"] = Series(data["E"])
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()]:
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(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_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_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_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 setUp(self):
super(TestSeries, self).setUp()
self.d = {}
s = tm.makeStringSeries()
s.name = 'string'
self.d['string'] = s
s = tm.makeObjectSeries()
s.name = 'object'
self.d['object'] = s
s = Series(tslib.iNaT, dtype='M8[ns]', index=range(5))
self.d['date'] = s
data = {
'A': [0., 1., 2., 3., np.nan],
'B': [0, 1, 0, 1, 0],
'C': ['foo1', 'foo2', 'foo3', 'foo4', 'foo5'],
'D': date_range('1/1/2009', periods=5),
'E': [0., 1, Timestamp('20100101'), 'foo', 2.],
}
self.d['float'] = Series(data['A'])
self.d['int'] = Series(data['B'])
self.d['mixed'] = Series(data['E'])
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_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_objarr_add_invalid(self, op, box):
# invalid ops
obj_ser = tm.makeObjectSeries()
obj_ser.name = 'objects'
obj_ser = tm.box_expected(obj_ser, box)
with pytest.raises(Exception):
op(obj_ser, 1)
with pytest.raises(Exception):
op(obj_ser, np.array(1, dtype=np.int64))
def setUp(self):
self.ts = tm.makeTimeSeries()
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
self.objSeries = tm.makeObjectSeries()
self.objSeries.name = 'objects'
self.empty = Series([], index=[])
def test_object_ser_add_invalid(self):
# invalid ops
obj_ser = tm.makeObjectSeries()
obj_ser.name = 'objects'
with pytest.raises(Exception):
obj_ser + 1
with pytest.raises(Exception):
obj_ser + np.array(1, dtype=np.int64)
with pytest.raises(Exception):
obj_ser - 1
with pytest.raises(Exception):
obj_ser - np.array(1, dtype=np.int64)
def test_object_ser_add_invalid(self):
# invalid ops
obj_ser = tm.makeObjectSeries()
obj_ser.name = 'objects'
with pytest.raises(Exception):
obj_ser + 1
with pytest.raises(Exception):
obj_ser + np.array(1, dtype=np.int64)
with pytest.raises(Exception):
obj_ser - 1
with pytest.raises(Exception):
obj_ser - np.array(1, dtype=np.int64)
def test_objarr_add_invalid(self, op, box_with_array):
# invalid ops
box = box_with_array
obj_ser = tm.makeObjectSeries()
obj_ser.name = "objects"
obj_ser = tm.box_expected(obj_ser, box)
with pytest.raises(Exception):
op(obj_ser, 1)
with pytest.raises(Exception):
op(obj_ser, np.array(1, dtype=np.int64))
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):
simplefilter("ignore", FutureWarning)
for p in [tm.makePanel()]:
tm.assert_panel_equal(p.squeeze(), p)
# squeezing
df = tm.makeTimeDataFrame().reindex(columns=['A'])
tm.assert_series_equal(df.squeeze(), df['A'])
with catch_warnings(record=True):
simplefilter("ignore", FutureWarning)
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'])
# 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_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_objarr_add_invalid(self, op, box):
# invalid ops
if box is pd.DataFrame and op is ops.radd:
pytest.xfail(reason="DataFrame op incorrectly casts the np.array"
"case to M8[ns]")
obj_ser = tm.makeObjectSeries()
obj_ser.name = 'objects'
obj_ser = tm.box_expected(obj_ser, box)
with pytest.raises(Exception):
op(obj_ser, 1)
with pytest.raises(Exception):
op(obj_ser, np.array(1, dtype=np.int64))
def test_objarr_add_invalid(self, op, box):
# invalid ops
if box is pd.DataFrame and op is ops.radd:
pytest.xfail(reason="DataFrame op incorrectly casts the np.array"
"case to M8[ns]")
obj_ser = tm.makeObjectSeries()
obj_ser.name = 'objects'
obj_ser = tm.box_expected(obj_ser, box)
with pytest.raises(Exception):
op(obj_ser, 1)
with pytest.raises(Exception):
op(obj_ser, np.array(1, dtype=np.int64))
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_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_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_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_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)
# panel 4d
with catch_warnings(record=True):
for p in [tm.makePanel4D(), tm.add_nans_panel4d(tm.makePanel4D())]:
result = isna_f(p)
expected = p.apply(isna_f)
tm.assert_panel4d_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
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 setUp(self):
self.ts = tm.makeTimeSeries()
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
self.objSeries = tm.makeObjectSeries()
self.objSeries.name = 'objects'
self.empty_series = Series([], index=[])
self.empty_frame = DataFrame({})
self.frame = _frame.copy()
self.frame2 = _frame2.copy()
self.intframe = _intframe.copy()
self.tsframe = _tsframe.copy()
self.mixed_frame = _mixed_frame.copy()
def setUp(self):
self.ts = tm.makeTimeSeries()
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
self.objSeries = tm.makeObjectSeries()
self.objSeries.name = 'objects'
self.empty_series = Series([], index=[])
self.empty_frame = DataFrame({})
self.frame = _frame.copy()
self.frame2 = _frame2.copy()
self.intframe = _intframe.copy()
self.tsframe = _tsframe.copy()
self.mixed_frame = _mixed_frame.copy()
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.)
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)
def setUp(self):
self.dirpath = tm.get_data_path()
self.ts = tm.makeTimeSeries()
self.ts.name = "ts"
self.series = tm.makeStringSeries()
self.series.name = "series"
self.objSeries = tm.makeObjectSeries()
self.objSeries.name = "objects"
self.empty_series = Series([], index=[])
self.empty_frame = DataFrame({})
self.frame = _frame.copy()
self.frame2 = _frame2.copy()
self.intframe = _intframe.copy()
self.tsframe = _tsframe.copy()
self.mixed_frame = _mixed_frame.copy()
def setup_method(self, method):
super().setup_method(method)
self.d = {}
s = tm.makeStringSeries()
s.name = "string"
self.d["string"] = s
s = tm.makeObjectSeries()
s.name = "object"
self.d["object"] = s
s = Series(iNaT, dtype="M8[ns]", index=range(5))
self.d["date"] = s
data = {
"A": [0.0, 1.0, 2.0, 3.0, np.nan],
"B": [0, 1, 0, 1, 0],
"C": ["foo1", "foo2", "foo3", "foo4", "foo5"],
"D":
date_range("1/1/2009", periods=5),
"E": [0.0, 1, Timestamp("20100101"), "foo", 2.0],
"F": [Timestamp("20130102", tz="US/Eastern")] * 2 +
[Timestamp("20130603", tz="CET")] * 3,
"G": [Timestamp("20130102", tz="US/Eastern")] * 5,
"H":
Categorical([1, 2, 3, 4, 5]),
"I":
Categorical([1, 2, 3, 4, 5], ordered=True),
"J": (np.bool_(1), 2, 3, 4, 5),
}
self.d["float"] = Series(data["A"])
self.d["int"] = Series(data["B"])
self.d["mixed"] = Series(data["E"])
self.d["dt_tz_mixed"] = Series(data["F"])
self.d["dt_tz"] = Series(data["G"])
self.d["cat_ordered"] = Series(data["H"])
self.d["cat_unordered"] = Series(data["I"])
self.d["numpy_bool_mixed"] = Series(data["J"])
def setup_method(self, method):
super(TestSeries, self).setup_method(method)
self.d = {}
s = tm.makeStringSeries()
s.name = 'string'
self.d['string'] = s
s = tm.makeObjectSeries()
s.name = 'object'
self.d['object'] = s
s = Series(iNaT, dtype='M8[ns]', index=range(5))
self.d['date'] = s
data = {
'A': [0., 1., 2., 3., np.nan],
'B': [0, 1, 0, 1, 0],
'C': ['foo1', 'foo2', 'foo3', 'foo4', 'foo5'],
'D':
date_range('1/1/2009', periods=5),
'E': [0., 1, Timestamp('20100101'), 'foo', 2.],
'F': [Timestamp('20130102', tz='US/Eastern')] * 2 +
[Timestamp('20130603', tz='CET')] * 3,
'G': [Timestamp('20130102', tz='US/Eastern')] * 5,
'H':
Categorical([1, 2, 3, 4, 5]),
'I':
Categorical([1, 2, 3, 4, 5], ordered=True),
'J': (np.bool_(1), 2, 3, 4, 5),
}
self.d['float'] = Series(data['A'])
self.d['int'] = Series(data['B'])
self.d['mixed'] = Series(data['E'])
self.d['dt_tz_mixed'] = Series(data['F'])
self.d['dt_tz'] = Series(data['G'])
self.d['cat_ordered'] = Series(data['H'])
self.d['cat_unordered'] = Series(data['I'])
self.d['numpy_bool_mixed'] = Series(data['J'])
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)
def setup_method(self, method):
self.dirpath = tm.get_data_path()
self.ts = tm.makeTimeSeries()
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
self.objSeries = tm.makeObjectSeries()
self.objSeries.name = 'objects'
self.empty_series = Series([], index=[])
self.empty_frame = DataFrame({})
self.frame = _frame.copy()
self.frame2 = _frame2.copy()
self.intframe = _intframe.copy()
self.tsframe = _tsframe.copy()
self.mixed_frame = _mixed_frame.copy()
self.categorical = _cat_frame.copy()
def setup_method(self, method):
self.dirpath = tm.get_data_path()
self.ts = tm.makeTimeSeries()
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
self.objSeries = tm.makeObjectSeries()
self.objSeries.name = 'objects'
self.empty_series = Series([], index=[])
self.empty_frame = DataFrame({})
self.frame = _frame.copy()
self.frame2 = _frame2.copy()
self.intframe = _intframe.copy()
self.tsframe = _tsframe.copy()
self.mixed_frame = _mixed_frame.copy()
self.categorical = _cat_frame.copy()
def setup(self, datapath):
self.dirpath = datapath("io", "json", "data")
self.ts = tm.makeTimeSeries()
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
self.objSeries = tm.makeObjectSeries()
self.objSeries.name = 'objects'
self.empty_series = Series([], index=[])
self.empty_frame = DataFrame({})
self.frame = _frame.copy()
self.frame2 = _frame2.copy()
self.intframe = _intframe.copy()
self.tsframe = _tsframe.copy()
self.mixed_frame = _mixed_frame.copy()
self.categorical = _cat_frame.copy()
yield
del self.dirpath
del self.ts
del self.series
del self.objSeries
del self.empty_series
del self.empty_frame
del self.frame
del self.frame2
del self.intframe
del self.tsframe
del self.mixed_frame
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)
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)
with catch_warnings(record=True):
for p4d in [tm.makePanel4D()]:
out = p4d.take(indices)
expected = Panel4D(data=p4d.values.take(indices, axis=0),
labels=p4d.labels.take(indices),
major_axis=p4d.major_axis,
minor_axis=p4d.minor_axis,
items=p4d.items)
tm.assert_panel4d_equal(out, expected)
def setup_method(self, method):
super(TestSeries, self).setup_method(method)
self.d = {}
s = tm.makeStringSeries()
s.name = 'string'
self.d['string'] = s
s = tm.makeObjectSeries()
s.name = 'object'
self.d['object'] = s
s = Series(iNaT, dtype='M8[ns]', index=range(5))
self.d['date'] = s
data = {
'A': [0., 1., 2., 3., np.nan],
'B': [0, 1, 0, 1, 0],
'C': ['foo1', 'foo2', 'foo3', 'foo4', 'foo5'],
'D': date_range('1/1/2009', periods=5),
'E': [0., 1, Timestamp('20100101'), 'foo', 2.],
'F': [Timestamp('20130102', tz='US/Eastern')] * 2 +
[Timestamp('20130603', tz='CET')] * 3,
'G': [Timestamp('20130102', tz='US/Eastern')] * 5,
'H': Categorical([1, 2, 3, 4, 5]),
'I': Categorical([1, 2, 3, 4, 5], ordered=True),
'J': (np.bool_(1), 2, 3, 4, 5),
}
self.d['float'] = Series(data['A'])
self.d['int'] = Series(data['B'])
self.d['mixed'] = Series(data['E'])
self.d['dt_tz_mixed'] = Series(data['F'])
self.d['dt_tz'] = Series(data['G'])
self.d['cat_ordered'] = Series(data['H'])
self.d['cat_unordered'] = Series(data['I'])
self.d['numpy_bool_mixed'] = Series(data['J'])
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 setUp(self):
self.ts = common.makeTimeSeries()
self.series = common.makeStringSeries()
self.objSeries = common.makeObjectSeries()
self.empty = Series([], index=[])
pd.DataFrame({"x": [1.0, 2.0, 3.0]}, index=pd.Index([4, 5, 6], name="bar")),
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)
def objSeries(self):
objSeries = tm.makeObjectSeries()
objSeries.name = 'objects'
return objSeries
pd.Series([1., 2., 3.], name='foo'),
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)
def objSeries(self):
objSeries = tm.makeObjectSeries()
objSeries.name = 'objects'
return objSeries
pd.Series(range(10),index=pd.date_range("2000",freq="D",periods=10))
start=pd.Timestamp("2018-01-06 00:00:00")
pd.date_range(start, periods=10,freq="2h20min")
rng=pd.date_range(start,end,freq="D")
ts=pd.Series(np.random.randn(len(rng)),index=rng)
ts.shift(2)[1]
# dummy datasets with dates
import pandas.util.testing as tm
tm.N, tm.K = 5,3
tm.makeTimedeltaIndex(), tm.makeTimeSeries(), tm.makePeriodSeries()
tm.makeDateIndex(), tm.makePeriodIndex(), tm.makeObjectSeries()
from itertools import product
datecols = ['year', 'month', 'day']
df = pd.DataFrame(list(product([2016,2017],[1,2],[1,2,3])),columns = datecols)
df['data']=np.random.randn(len(df))
df.index = pd.to_datetime(df[datecols])
# Align 2 datetime series and interpolate if necessary
from datetime import date, time
import numpy as np
from ..errors import MqValueError
def setUp(self):
self.ts = common.makeTimeSeries()
self.series = common.makeStringSeries()
self.objSeries = common.makeObjectSeries()
self.empty = Series([], index=[])
