def test_kurt(self):
from scipy.stats import kurtosis
string_series = tm.makeStringSeries().rename('series')
alt = lambda x: kurtosis(x, bias=False)
self._check_stat_op('kurt', alt, string_series)
index = pd.MultiIndex(
levels=[['bar'], ['one', 'two', 'three'], [0, 1]],
codes=[[0, 0, 0, 0, 0, 0], [0, 1, 2, 0, 1, 2], [0, 1, 0, 1, 0, 1]]
)
s = Series(np.random.randn(6), index=index)
tm.assert_almost_equal(s.kurt(), s.kurt(level=0)['bar'])
# test corner cases, kurt() returns NaN unless there's at least 4
# values
min_N = 4
for i in range(1, min_N + 1):
s = Series(np.ones(i))
df = DataFrame(np.ones((i, i)))
if i < min_N:
assert np.isnan(s.kurt())
assert np.isnan(df.kurt()).all()
else:
assert 0 == s.kurt()
assert (df.kurt() == 0).all()
def test_var_std(self):
string_series = tm.makeStringSeries().rename('series')
datetime_series = tm.makeTimeSeries().rename('ts')
alt = lambda x: np.std(x, ddof=1)
self._check_stat_op('std', alt, string_series)
alt = lambda x: np.var(x, ddof=1)
self._check_stat_op('var', alt, string_series)
result = datetime_series.std(ddof=4)
expected = np.std(datetime_series.values, ddof=4)
tm.assert_almost_equal(result, expected)
result = datetime_series.var(ddof=4)
expected = np.var(datetime_series.values, ddof=4)
tm.assert_almost_equal(result, expected)
# 1 - element series with ddof=1
s = datetime_series.iloc[[0]]
result = s.var(ddof=1)
assert pd.isna(result)
result = s.std(ddof=1)
assert pd.isna(result)
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_median(self):
string_series = tm.makeStringSeries().rename('series')
self._check_stat_op('median', np.median, string_series)
# test with integers, test failure
int_ts = Series(np.ones(10, dtype=int), index=lrange(10))
tm.assert_almost_equal(np.median(int_ts), int_ts.median())
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_idxmin(self):
# test idxmin
# _check_stat_op approach can not be used here because of isna check.
string_series = tm.makeStringSeries().rename('series')
# add some NaNs
string_series[5:15] = np.NaN
# skipna or no
assert string_series[string_series.idxmin()] == string_series.min()
assert pd.isna(string_series.idxmin(skipna=False))
# no NaNs
nona = string_series.dropna()
assert nona[nona.idxmin()] == nona.min()
assert (nona.index.values.tolist().index(nona.idxmin()) ==
nona.values.argmin())
# all NaNs
allna = string_series * np.nan
assert pd.isna(allna.idxmin())
# datetime64[ns]
s = Series(pd.date_range('20130102', periods=6))
result = s.idxmin()
assert result == 0
s[0] = np.nan
result = s.idxmin()
assert result == 1
def string_series():
"""
Fixture for Series of floats with Index of unique strings
"""
s = tm.makeStringSeries()
s.name = 'series'
return s
def test_len_keys(self):
self.store['a'] = tm.makeTimeSeries()
self.store['b'] = tm.makeStringSeries()
self.store['c'] = tm.makeDataFrame()
self.store['d'] = tm.makePanel()
self.assertEquals(len(self.store), 4)
self.assert_(set(self.store.keys()) == set(['a', 'b', 'c', 'd']))
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):
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_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_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():
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_repr(self):
repr(self.store)
self.store['a'] = tm.makeTimeSeries()
self.store['b'] = tm.makeStringSeries()
self.store['c'] = tm.makeDataFrame()
self.store['d'] = tm.makePanel()
repr(self.store)
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_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 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_keys(self):
self.store['a'] = tm.makeTimeSeries()
self.store['b'] = tm.makeStringSeries()
self.store['c'] = tm.makeDataFrame()
self.store['d'] = tm.makePanel()
self.store['foo/bar'] = tm.makePanel()
self.assertEquals(len(self.store), 5)
self.assert_(set(self.store.keys()) == set(['/a', '/b', '/c', '/d', '/foo/bar']))
def setUp(self):
self.ts = tm.makeTimeSeries()
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
self.iseries = tm.makePeriodSeries()
self.iseries.name = 'iseries'
def setUp(self):
self.ts = tm.makeTimeSeries()
self.ts.name = "ts"
self.series = tm.makeStringSeries()
self.series.name = "series"
self.iseries = tm.makePeriodSeries()
self.iseries.name = "iseries"
def test_repr(self):
repr(self.store)
self.store['a'] = tm.makeTimeSeries()
self.store['b'] = tm.makeStringSeries()
self.store['c'] = tm.makeDataFrame()
self.store['d'] = tm.makePanel()
self.store['foo/bar'] = tm.makePanel()
self.store.append('e', tm.makePanel())
repr(self.store)
str(self.store)
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 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 setUp(self):
import matplotlib as mpl
self.mpl_le_1_2_1 = str(mpl.__version__) <= LooseVersion('1.2.1')
self.ts = tm.makeTimeSeries()
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
self.iseries = tm.makePeriodSeries()
self.iseries.name = 'iseries'
def setUp(self):
import matplotlib as mpl
self.mpl_le_1_2_1 = str(mpl.__version__) <= LooseVersion('1.2.1')
self.ts = tm.makeTimeSeries()
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
self.iseries = tm.makePeriodSeries()
self.iseries.name = 'iseries'
def test_sparse_series(self):
s = tm.makeStringSeries()
s[3:5] = np.nan
ss = s.to_sparse()
self._check_roundtrip(ss, tm.assert_series_equal, check_series_type=True)
ss2 = s.to_sparse(kind="integer")
self._check_roundtrip(ss2, tm.assert_series_equal, check_series_type=True)
ss3 = s.to_sparse(fill_value=0)
self._check_roundtrip(ss3, tm.assert_series_equal, check_series_type=True)
def test_sparse_series(self):
s = tm.makeStringSeries()
s[3:5] = np.nan
ss = s.to_sparse()
self._check_roundtrip(ss, tm.assert_series_equal, check_series_type=True)
ss2 = s.to_sparse(kind="integer")
self._check_roundtrip(ss2, tm.assert_series_equal, check_series_type=True)
ss3 = s.to_sparse(fill_value=0)
self._check_roundtrip(ss3, tm.assert_series_equal, check_series_type=True)
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_series(self):
s = tm.makeStringSeries()
self._check_roundtrip(s, tm.assert_series_equal)
ts = tm.makeTimeSeries()
self._check_roundtrip(ts, tm.assert_series_equal)
ts2 = Series(ts.index, Index(ts.index, dtype=object))
self._check_roundtrip(ts2, tm.assert_series_equal)
ts3 = Series(ts.values, Index(np.asarray(ts.index, dtype=object),
dtype=object))
self._check_roundtrip(ts3, tm.assert_series_equal)
def setUp(self):
TestPlotBase.setUp(self)
import matplotlib as mpl
mpl.rcdefaults()
self.ts = tm.makeTimeSeries()
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
self.iseries = tm.makePeriodSeries()
self.iseries.name = 'iseries'
def setup_method(self, method):
TestPlotBase.setup_method(self, method)
import matplotlib as mpl
mpl.rcdefaults()
self.ts = tm.makeTimeSeries()
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
self.iseries = tm.makePeriodSeries()
self.iseries.name = 'iseries'
def test_series(self):
s = tm.makeStringSeries()
self._check_roundtrip(s, tm.assert_series_equal)
ts = tm.makeTimeSeries()
self._check_roundtrip(ts, tm.assert_series_equal)
ts2 = Series(ts.index, Index(ts.index, dtype=object))
self._check_roundtrip(ts2, tm.assert_series_equal)
ts3 = Series(ts.values,
Index(np.asarray(ts.index, dtype=object), dtype=object))
self._check_roundtrip(ts3, tm.assert_series_equal)
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_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_sem(self):
string_series = tm.makeStringSeries().rename('series')
datetime_series = tm.makeTimeSeries().rename('ts')
alt = lambda x: np.std(x, ddof=1) / np.sqrt(len(x))
self._check_stat_op('sem', alt, string_series)
result = datetime_series.sem(ddof=4)
expected = np.std(datetime_series.values,
ddof=4) / np.sqrt(len(datetime_series.values))
tm.assert_almost_equal(result, expected)
# 1 - element series with ddof=1
s = datetime_series.iloc[[0]]
result = s.sem(ddof=1)
assert pd.isna(result)
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), 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_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(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_idxmax(self):
# test idxmax
# _check_stat_op approach can not be used here because of isna check.
string_series = tm.makeStringSeries().rename("series")
# add some NaNs
string_series[5:15] = np.NaN
# skipna or no
assert string_series[string_series.idxmax()] == string_series.max()
assert pd.isna(string_series.idxmax(skipna=False))
# no NaNs
nona = string_series.dropna()
assert nona[nona.idxmax()] == nona.max()
assert nona.index.values.tolist().index(
nona.idxmax()) == nona.values.argmax()
# all NaNs
allna = string_series * np.nan
assert pd.isna(allna.idxmax())
from pandas import date_range
s = Series(date_range("20130102", periods=6))
result = s.idxmax()
assert result == 5
s[5] = np.nan
result = s.idxmax()
assert result == 4
# Float64Index
# GH#5914
s = pd.Series([1, 2, 3], [1.1, 2.1, 3.1])
result = s.idxmax()
assert result == 3.1
result = s.idxmin()
assert result == 1.1
s = pd.Series(s.index, s.index)
result = s.idxmax()
assert result == 3.1
result = s.idxmin()
assert result == 1.1
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 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_skew(self):
from scipy.stats import skew
string_series = tm.makeStringSeries().rename('series')
alt = lambda x: skew(x, bias=False)
self._check_stat_op('skew', alt, string_series)
# test corner cases, skew() returns NaN unless there's at least 3
# values
min_N = 3
for i in range(1, min_N + 1):
s = Series(np.ones(i))
df = DataFrame(np.ones((i, i)))
if i < min_N:
assert np.isnan(s.skew())
assert np.isnan(df.skew()).all()
else:
assert 0 == s.skew()
assert (df.skew() == 0).all()
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):
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 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 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(self):
self.ts = tm.makeTimeSeries() # Was at top level in test_series
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
def setup_method(self):
self.ts = tm.makeTimeSeries() # Was at top level in test_series
self.ts.name = "ts"
self.series = tm.makeStringSeries()
self.series.name = "series"
def setUp(self):
self.ts = common.makeTimeSeries()
self.series = common.makeStringSeries()
self.objSeries = common.makeObjectSeries()
self.empty = Series([], index=[])
def test_neg(self):
ser = tm.makeStringSeries()
ser.name = "series"
assert_series_equal(-ser, -1 * ser)
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 series(self):
series = tm.makeStringSeries()
series.name = 'series'
return series
def test_invert(self):
ser = tm.makeStringSeries()
ser.name = "series"
assert_series_equal(-(ser < 0), ~(ser < 0))
def setUp(self):
self.ts = tm.makeTimeSeries()
self.ts.name = 'ts'
self.series = tm.makeStringSeries()
self.series.name = 'series'
