def setUp(self):
self.bool_index = tm.makeBoolIndex(10, name='a')
self.int_index = tm.makeIntIndex(10, name='a')
self.float_index = tm.makeFloatIndex(10, name='a')
self.dt_index = tm.makeDateIndex(10, name='a')
self.dt_tz_index = tm.makeDateIndex(10, name='a').tz_localize(
tz='US/Eastern')
self.period_index = tm.makePeriodIndex(10, name='a')
self.string_index = tm.makeStringIndex(10, name='a')
self.unicode_index = tm.makeUnicodeIndex(10, name='a')
arr = np.random.randn(10)
self.int_series = Series(arr, index=self.int_index, name='a')
self.float_series = Series(arr, index=self.float_index, name='a')
self.dt_series = Series(arr, index=self.dt_index, name='a')
self.dt_tz_series = self.dt_tz_index.to_series(keep_tz=True)
self.period_series = Series(arr, index=self.period_index, name='a')
self.string_series = Series(arr, index=self.string_index, name='a')
types = ['bool', 'int', 'float', 'dt', 'dt_tz', 'period', 'string',
'unicode']
fmts = ["{0}_{1}".format(t, f)
for t in types for f in ['index', 'series']]
self.objs = [getattr(self, f)
for f in fmts if getattr(self, f, None) is not None]
def setup_method(self, method):
self.bool_index = tm.makeBoolIndex(10, name='a')
self.int_index = tm.makeIntIndex(10, name='a')
self.float_index = tm.makeFloatIndex(10, name='a')
self.dt_index = tm.makeDateIndex(10, name='a')
self.dt_tz_index = tm.makeDateIndex(10, name='a').tz_localize(
tz='US/Eastern')
self.period_index = tm.makePeriodIndex(10, name='a')
self.string_index = tm.makeStringIndex(10, name='a')
self.unicode_index = tm.makeUnicodeIndex(10, name='a')
arr = np.random.randn(10)
self.bool_series = Series(arr, index=self.bool_index, name='a')
self.int_series = Series(arr, index=self.int_index, name='a')
self.float_series = Series(arr, index=self.float_index, name='a')
self.dt_series = Series(arr, index=self.dt_index, name='a')
self.dt_tz_series = self.dt_tz_index.to_series(keep_tz=True)
self.period_series = Series(arr, index=self.period_index, name='a')
self.string_series = Series(arr, index=self.string_index, name='a')
self.unicode_series = Series(arr, index=self.unicode_index, name='a')
types = ['bool', 'int', 'float', 'dt', 'dt_tz', 'period', 'string',
'unicode']
self.indexes = [getattr(self, '{}_index'.format(t)) for t in types]
self.series = [getattr(self, '{}_series'.format(t)) for t in types]
self.objs = self.indexes + self.series
def setUp(self):
self.strIndex = tm.makeStringIndex(100)
self.dateIndex = tm.makeDateIndex(100)
self.intIndex = tm.makeIntIndex(100)
self.floatIndex = tm.makeFloatIndex(100)
self.empty = Index([])
self.tuples = Index(zip(["foo", "bar", "baz"], [1, 2, 3]))
def test_constructor_dict_cast(self):
# cast float tests
test_data = {
'A' : {'1' : 1, '2' : 2},
'B' : {'1' : '1', '2' : '2', '3' : '3'},
}
frame = self.klass(test_data, dtype=float)
self.assertEqual(len(frame), 3)
self.assert_(frame['B'].dtype == np.float_)
self.assert_(frame['A'].dtype == np.float_)
frame = self.klass(test_data)
self.assertEqual(len(frame), 3)
self.assert_(frame['B'].dtype == np.object_)
self.assert_(frame['A'].dtype == np.float_)
# can't cast to float
test_data = {
'A' : dict(zip(range(20), common.makeDateIndex(20))),
'B' : dict(zip(range(15), randn(15)))
}
frame = self.klass(test_data, dtype=float)
self.assertEqual(len(frame), 20)
self.assert_(frame['A'].dtype == np.object_)
self.assert_(frame['B'].dtype == np.float_)
def test_get_numeric_data(self):
int_ser = Series(np.array([0, 1, 2]))
float_ser = Series(np.array([0., 1., 2.]))
complex_ser = Series(np.array([0j, 1j, 2j]))
str_ser = Series(np.array(['a', 'b', 'c']))
bool_ser = Series(np.array([True, False, True]))
obj_ser = Series(np.array([1, 'a', 5]))
dt_ser = Series(tm.makeDateIndex(3))
# check types
df = DataFrame({'int': int_ser, 'float': float_ser,
'complex': complex_ser, 'str': str_ser,
'bool': bool_ser, 'obj': obj_ser,
'dt': dt_ser})
xp = DataFrame({'int': int_ser, 'float': float_ser,
'complex': complex_ser})
rs = DataFrame(df._data.get_numeric_data())
assert_frame_equal(xp, rs)
xp = DataFrame({'bool': bool_ser})
rs = DataFrame(df._data.get_numeric_data(type_list=bool))
assert_frame_equal(xp, rs)
rs = DataFrame(df._data.get_numeric_data(type_list=bool))
df.ix[0, 'bool'] = not df.ix[0, 'bool']
self.assertEqual(rs.ix[0, 'bool'], df.ix[0, 'bool'])
rs = DataFrame(df._data.get_numeric_data(type_list=bool, copy=True))
df.ix[0, 'bool'] = not df.ix[0, 'bool']
self.assertEqual(rs.ix[0, 'bool'], not df.ix[0, 'bool'])
def setup_method(self, method):
super(TestIndex, self).setup_method(method)
self.d = {
'string': tm.makeStringIndex(100),
'date': tm.makeDateIndex(100),
'int': tm.makeIntIndex(100),
'rng': tm.makeRangeIndex(100),
'float': tm.makeFloatIndex(100),
'empty': Index([]),
'tuple': Index(zip(['foo', 'bar', 'baz'], [1, 2, 3])),
'period': Index(period_range('2012-1-1', freq='M', periods=3)),
'date2': Index(date_range('2013-01-1', periods=10)),
'bdate': Index(bdate_range('2013-01-02', periods=10)),
'cat': tm.makeCategoricalIndex(100),
'interval': tm.makeIntervalIndex(100),
'timedelta': tm.makeTimedeltaIndex(100, 'H')
}
self.mi = {
'reg': MultiIndex.from_tuples([('bar', 'one'), ('baz', 'two'),
('foo', 'two'),
('qux', 'one'), ('qux', 'two')],
names=['first', 'second']),
}
def test_timeseries_coercion(self):
idx = tm.makeDateIndex(10000)
ser = Series(np.random.randn(len(idx)), idx.astype(object))
with tm.assert_produces_warning(FutureWarning):
self.assertTrue(ser.is_time_series)
self.assertTrue(ser.index.is_all_dates)
self.assertIsInstance(ser.index, DatetimeIndex)
def test_replace2(self):
N = 100
ser = pd.Series(np.fabs(np.random.randn(N)), tm.makeDateIndex(N),
dtype=object)
ser[:5] = np.nan
ser[6:10] = 'foo'
ser[20:30] = 'bar'
# replace list with a single value
rs = ser.replace([np.nan, 'foo', 'bar'], -1)
assert (rs[:5] == -1).all()
assert (rs[6:10] == -1).all()
assert (rs[20:30] == -1).all()
assert (pd.isnull(ser[:5])).all()
# replace with different values
rs = ser.replace({np.nan: -1, 'foo': -2, 'bar': -3})
assert (rs[:5] == -1).all()
assert (rs[6:10] == -2).all()
assert (rs[20:30] == -3).all()
assert (pd.isnull(ser[:5])).all()
# replace with different values with 2 lists
rs2 = ser.replace([np.nan, 'foo', 'bar'], [-1, -2, -3])
tm.assert_series_equal(rs, rs2)
# replace inplace
ser.replace([np.nan, 'foo', 'bar'], -1, inplace=True)
assert (ser[:5] == -1).all()
assert (ser[6:10] == -1).all()
assert (ser[20:30] == -1).all()
def test_dateindex_conversion(self):
decimals = 9
for freq in ('B', 'L', 'S'):
dateindex = tm.makeDateIndex(k=10, freq=freq)
rs = self.dtc.convert(dateindex, None, None)
xp = converter.dates.date2num(dateindex._mpl_repr())
tm.assert_almost_equal(rs, xp, decimals)
def get_objs():
indexes = [
tm.makeBoolIndex(10, name='a'),
tm.makeIntIndex(10, name='a'),
tm.makeFloatIndex(10, name='a'),
tm.makeDateIndex(10, name='a'),
tm.makeDateIndex(10, name='a').tz_localize(tz='US/Eastern'),
tm.makePeriodIndex(10, name='a'),
tm.makeStringIndex(10, name='a'),
tm.makeUnicodeIndex(10, name='a')
]
arr = np.random.randn(10)
series = [Series(arr, index=idx, name='a') for idx in indexes]
objs = indexes + series
return objs
def setUp(self):
self.int_index = tm.makeIntIndex(10)
self.float_index = tm.makeFloatIndex(10)
self.dt_index = tm.makeDateIndex(10)
self.dt_tz_index = tm.makeDateIndex(10).tz_localize(tz="US/Eastern")
self.period_index = tm.makePeriodIndex(10)
self.string_index = tm.makeStringIndex(10)
arr = np.random.randn(10)
self.int_series = Series(arr, index=self.int_index)
self.float_series = Series(arr, index=self.int_index)
self.dt_series = Series(arr, index=self.dt_index)
self.dt_tz_series = self.dt_tz_index.to_series(keep_tz=True)
self.period_series = Series(arr, index=self.period_index)
self.string_series = Series(arr, index=self.string_index)
types = ["int", "float", "dt", "dt_tz", "period", "string"]
self.objs = [getattr(self, "{0}_{1}".format(t, f)) for t in types for f in ["index", "series"]]
def test_set_index_makes_timeseries(self):
idx = tm.makeDateIndex(10)
s = Series(lrange(10))
s.index = idx
with tm.assert_produces_warning(FutureWarning):
self.assertTrue(s.is_time_series)
self.assertTrue(s.index.is_all_dates)
def setUp(self):
self.int_index = tm.makeIntIndex(10)
self.float_index = tm.makeFloatIndex(10)
self.dt_index = tm.makeDateIndex(10)
self.dt_tz_index = tm.makeDateIndex(10).tz_localize(tz='US/Eastern')
self.period_index = tm.makePeriodIndex(10)
self.string_index = tm.makeStringIndex(10)
arr = np.random.randn(10)
self.int_series = Series(arr, index=self.int_index)
self.float_series = Series(arr, index=self.int_index)
self.dt_series = Series(arr, index=self.dt_index)
self.dt_tz_series = self.dt_tz_index.to_series(keep_tz=True)
self.period_series = Series(arr, index=self.period_index)
self.string_series = Series(arr, index=self.string_index)
types = ['int','float','dt', 'dt_tz', 'period','string']
self.objs = [ getattr(self,"{0}_{1}".format(t,f)) for t in types for f in ['index','series'] ]
def test_isin(self):
index = tm.makeDateIndex(4)
result = index.isin(index)
assert result.all()
result = index.isin(list(index))
assert result.all()
assert_almost_equal(index.isin([index[2], 5]),
np.array([False, False, True, False]))
def test_fill(self):
ts = Series([0., 1., 2., 3., 4.], index=common.makeDateIndex(5))
self.assert_(np.array_equal(ts, ts.fill()))
ts[2] = np.NaN
self.assert_(np.array_equal(ts.fill(), [0., 1., 1., 3., 4.]))
self.assert_(np.array_equal(ts.fill(method='backfill'), [0., 1., 3., 3., 4.]))
self.assert_(np.array_equal(ts.fill(value=5), [0., 1., 5., 3., 4.]))
def test_dti_timestamp_fields(self, field):
# extra fields from DatetimeIndex like quarter and week
idx = tm.makeDateIndex(100)
expected = getattr(idx, field)[-1]
if field == 'weekday_name':
with tm.assert_produces_warning(FutureWarning,
check_stacklevel=False):
result = getattr(Timestamp(idx[-1]), field)
else:
result = getattr(Timestamp(idx[-1]), field)
assert result == expected
def setUp(self):
self.bool_index = tm.makeBoolIndex(10, name='a')
self.int_index = tm.makeIntIndex(10, name='a')
self.float_index = tm.makeFloatIndex(10, name='a')
self.dt_index = tm.makeDateIndex(10, name='a')
self.dt_tz_index = tm.makeDateIndex(10, name='a').tz_localize(tz='US/Eastern')
self.period_index = tm.makePeriodIndex(10, name='a')
self.string_index = tm.makeStringIndex(10, name='a')
self.unicode_index = tm.makeUnicodeIndex(10, name='a')
arr = np.random.randn(10)
self.int_series = Series(arr, index=self.int_index, name='a')
self.float_series = Series(arr, index=self.float_index, name='a')
self.dt_series = Series(arr, index=self.dt_index, name='a')
self.dt_tz_series = self.dt_tz_index.to_series(keep_tz=True)
self.period_series = Series(arr, index=self.period_index, name='a')
self.string_series = Series(arr, index=self.string_index, name='a')
types = ['bool','int','float','dt', 'dt_tz', 'period','string', 'unicode']
fmts = [ "{0}_{1}".format(t,f) for t in types for f in ['index','series'] ]
self.objs = [ getattr(self,f) for f in fmts if getattr(self,f,None) is not None ]
def test_union2(self):
everything = tm.makeDateIndex(10)
first = everything[:5]
second = everything[5:]
union = first.union(second)
assert tm.equalContents(union, everything)
# GH 10149
cases = [klass(second.values) for klass in [np.array, Series, list]]
for case in cases:
result = first.union(case)
assert tm.equalContents(result, everything)
def test_union2(self):
everything = tm.makeDateIndex(10)
first = everything[:5]
second = everything[5:]
union = first.union(second)
assert tm.equalContents(union, everything)
# GH 10149
cases = [klass(second.values) for klass in [np.array, Series, list]]
for case in cases:
result = first.union(case)
assert tm.equalContents(result, everything)
def setUp(self):
self.bool_index = tm.makeBoolIndex(10, name="a")
self.int_index = tm.makeIntIndex(10, name="a")
self.float_index = tm.makeFloatIndex(10, name="a")
self.dt_index = tm.makeDateIndex(10, name="a")
self.dt_tz_index = tm.makeDateIndex(10, name="a").tz_localize(tz="US/Eastern")
self.period_index = tm.makePeriodIndex(10, name="a")
self.string_index = tm.makeStringIndex(10, name="a")
self.unicode_index = tm.makeUnicodeIndex(10, name="a")
arr = np.random.randn(10)
self.int_series = Series(arr, index=self.int_index, name="a")
self.float_series = Series(arr, index=self.float_index, name="a")
self.dt_series = Series(arr, index=self.dt_index, name="a")
self.dt_tz_series = self.dt_tz_index.to_series(keep_tz=True)
self.period_series = Series(arr, index=self.period_index, name="a")
self.string_series = Series(arr, index=self.string_index, name="a")
types = ["bool", "int", "float", "dt", "dt_tz", "period", "string", "unicode"]
fmts = ["{0}_{1}".format(t, f) for t in types for f in ["index", "series"]]
self.objs = [getattr(self, f) for f in fmts if getattr(self, f, None) is not None]
def setUp(self):
self.int_index = tm.makeIntIndex(10)
self.float_index = tm.makeFloatIndex(10)
self.dt_index = tm.makeDateIndex(10)
self.dt_tz_index = tm.makeDateIndex(10).tz_localize(tz='US/Eastern')
self.period_index = tm.makePeriodIndex(10)
self.string_index = tm.makeStringIndex(10)
arr = np.random.randn(10)
self.int_series = Series(arr, index=self.int_index)
self.float_series = Series(arr, index=self.int_index)
self.dt_series = Series(arr, index=self.dt_index)
self.dt_tz_series = self.dt_tz_index.to_series(keep_tz=True)
self.period_series = Series(arr, index=self.period_index)
self.string_series = Series(arr, index=self.string_index)
types = ['int', 'float', 'dt', 'dt_tz', 'period', 'string']
self.objs = [
getattr(self, "{0}_{1}".format(t, f)) for t in types
for f in ['index', 'series']
]
def test_union2(self, sort):
everything = tm.makeDateIndex(10)
first = everything[:5]
second = everything[5:]
union = first.union(second, sort=sort)
tm.assert_index_equal(union, everything)
# GH 10149
cases = [klass(second.values) for klass in [np.array, Series, list]]
for case in cases:
result = first.union(case, sort=sort)
tm.assert_index_equal(result, everything)
def test_union3(self, sort, box):
everything = tm.makeDateIndex(10)
first = everything[:5]
second = everything[5:]
# GH 10149
expected = first.astype('O').union(
pd.Index(second.values, dtype='O')
).astype('O')
case = box(second.values)
result = first.union(case, sort=sort)
tm.assert_index_equal(result, expected)
def test_fill(self):
ts = Series([0., 1., 2., 3., 4.], index=common.makeDateIndex(5))
self.assert_(np.array_equal(ts, ts.fill()))
ts[2] = np.NaN
self.assert_(np.array_equal(ts.fill(), [0., 1., 1., 3., 4.]))
self.assert_(
np.array_equal(ts.fill(method='backfill'), [0., 1., 3., 3., 4.]))
self.assert_(np.array_equal(ts.fill(value=5), [0., 1., 5., 3., 4.]))
def test_union2(self, sort):
everything = tm.makeDateIndex(10)
first = everything[:5]
second = everything[5:]
union = first.union(second, sort=sort)
tm.assert_index_equal(union, everything)
# GH 10149
cases = [klass(second.values) for klass in [np.array, Series, list]]
for case in cases:
result = first.union(case, sort=sort)
tm.assert_index_equal(result, everything)
def test_timestamp_fields(self):
# extra fields from DatetimeIndex like quarter and week
from pandas._tseries import Timestamp
idx = tm.makeDateIndex(10)
fields = ['dayofweek', 'dayofyear', 'week', 'weekofyear', 'quarter']
for f in fields:
expected = getattr(idx, f)[0]
result = getattr(Timestamp(idx[0]), f)
self.assertEqual(result, expected)
self.assertEqual(idx.freq, Timestamp(idx[0], idx.freq).freq)
self.assertEqual(idx.freqstr, Timestamp(idx[0], idx.freq).freqstr)
def test_timestamp_fields(self):
# extra fields from DatetimeIndex like quarter and week
idx = tm.makeDateIndex(100)
fields = ['dayofweek', 'dayofyear', 'week', 'weekofyear', 'quarter',
'days_in_month', 'is_month_start', 'is_month_end',
'is_quarter_start', 'is_quarter_end', 'is_year_start',
'is_year_end', 'weekday_name']
for f in fields:
expected = getattr(idx, f)[-1]
result = getattr(Timestamp(idx[-1]), f)
assert result == expected
assert idx.freq == Timestamp(idx[-1], idx.freq).freq
assert idx.freqstr == Timestamp(idx[-1], idx.freq).freqstr
def test_timestamp_fields(self):
# extra fields from DatetimeIndex like quarter and week
idx = tm.makeDateIndex(100)
fields = ['dayofweek', 'dayofyear', 'week', 'weekofyear', 'quarter',
'days_in_month', 'is_month_start', 'is_month_end',
'is_quarter_start', 'is_quarter_end', 'is_year_start',
'is_year_end', 'weekday_name']
for f in fields:
expected = getattr(idx, f)[-1]
result = getattr(Timestamp(idx[-1]), f)
assert result == expected
assert idx.freq == Timestamp(idx[-1], idx.freq).freq
assert idx.freqstr == Timestamp(idx[-1], idx.freq).freqstr
def setUp(self):
self.int_index = tm.makeIntIndex(10)
self.float_index = tm.makeFloatIndex(10)
self.dt_index = tm.makeDateIndex(10)
self.period_index = tm.makePeriodIndex(10)
self.string_index = tm.makeStringIndex(10)
arr = np.random.randn(10)
self.int_series = Series(arr, index=self.int_index)
self.float_series = Series(arr, index=self.int_index)
self.dt_series = Series(arr, index=self.dt_index)
self.period_series = Series(arr, index=self.period_index)
self.string_series = Series(arr, index=self.string_index)
self.objs = [ getattr(self,"{0}_{1}".format(t,f)) for t in ['int','float','dt','period','string'] for f in ['index','series'] ]
def test_intersection2(self):
first = tm.makeDateIndex(10)
second = first[5:]
intersect = first.intersection(second)
assert tm.equalContents(intersect, second)
# GH 10149
cases = [klass(second.values) for klass in [np.array, Series, list]]
for case in cases:
result = first.intersection(case)
assert tm.equalContents(result, second)
third = Index(["a", "b", "c"])
result = first.intersection(third)
expected = pd.Index([], dtype=object)
tm.assert_index_equal(result, expected)
def test_intersection2(self):
first = tm.makeDateIndex(10)
second = first[5:]
intersect = first.intersection(second)
assert tm.equalContents(intersect, second)
# GH 10149
cases = [klass(second.values) for klass in [np.array, Series, list]]
for case in cases:
result = first.intersection(case)
assert tm.equalContents(result, second)
third = Index(['a', 'b', 'c'])
result = first.intersection(third)
expected = pd.Index([], dtype=object)
tm.assert_index_equal(result, expected)
def test_tseries_indices_frame(self):
idx = tm.makeDateIndex(10)
df = DataFrame(np.random.randn(len(idx), 3), index=idx)
self.store['a'] = df
result = self.store['a']
assert_frame_equal(result, df)
self.assertEquals(type(result.index), type(df.index))
self.assertEquals(result.index.freq, df.index.freq)
idx = tm.makePeriodIndex(10)
df = DataFrame(np.random.randn(len(idx), 3), idx)
self.store['a'] = df
result = self.store['a']
assert_frame_equal(result, df)
self.assertEquals(type(result.index), type(df.index))
self.assertEquals(result.index.freq, df.index.freq)
def test_tseries_indices_series(self):
idx = tm.makeDateIndex(10)
ser = Series(np.random.randn(len(idx)), idx)
self.store['a'] = ser
result = self.store['a']
assert_series_equal(result, ser)
self.assertEquals(type(result.index), type(ser.index))
self.assertEquals(result.index.freq, ser.index.freq)
idx = tm.makePeriodIndex(10)
ser = Series(np.random.randn(len(idx)), idx)
self.store['a'] = ser
result = self.store['a']
assert_series_equal(result, ser)
self.assertEquals(type(result.index), type(ser.index))
self.assertEquals(result.index.freq, ser.index.freq)
def test_tseries_indices_series(self):
idx = tm.makeDateIndex(10)
ser = Series(np.random.randn(len(idx)), idx)
self.store['a'] = ser
result = self.store['a']
assert_series_equal(result, ser)
self.assertEquals(type(result.index), type(ser.index))
self.assertEquals(result.index.freq, ser.index.freq)
idx = tm.makePeriodIndex(10)
ser = Series(np.random.randn(len(idx)), idx)
self.store['a'] = ser
result = self.store['a']
assert_series_equal(result, ser)
self.assertEquals(type(result.index), type(ser.index))
self.assertEquals(result.index.freq, ser.index.freq)
def test_tseries_indices_frame(self):
idx = tm.makeDateIndex(10)
df = DataFrame(np.random.randn(len(idx), 3), index=idx)
self.store['a'] = df
result = self.store['a']
assert_frame_equal(result, df)
self.assertEquals(type(result.index), type(df.index))
self.assertEquals(result.index.freq, df.index.freq)
idx = tm.makePeriodIndex(10)
df = DataFrame(np.random.randn(len(idx), 3), idx)
self.store['a'] = df
result = self.store['a']
assert_frame_equal(result, df)
self.assertEquals(type(result.index), type(df.index))
self.assertEquals(result.index.freq, df.index.freq)
def setUp(self):
self.int_index = tm.makeIntIndex(10)
self.float_index = tm.makeFloatIndex(10)
self.dt_index = tm.makeDateIndex(10)
self.period_index = tm.makePeriodIndex(10)
self.string_index = tm.makeStringIndex(10)
arr = np.random.randn(10)
self.int_series = Series(arr, index=self.int_index)
self.float_series = Series(arr, index=self.int_index)
self.dt_series = Series(arr, index=self.dt_index)
self.period_series = Series(arr, index=self.period_index)
self.string_series = Series(arr, index=self.string_index)
self.objs = [
getattr(self, "{0}_{1}".format(t, f))
for t in ['int', 'float', 'dt', 'period', 'string']
for f in ['index', 'series']
]
def setUp(self):
super(TestIndex, self).setUp()
self.d = {
'string': tm.makeStringIndex(100),
'date': tm.makeDateIndex(100),
'int': tm.makeIntIndex(100),
'float': tm.makeFloatIndex(100),
'empty': Index([]),
'tuple': Index(zip(['foo', 'bar', 'baz'], [1, 2, 3])),
'period': Index(period_range('2012-1-1', freq='M', periods=3)),
'date2': Index(date_range('2013-01-1', periods=10)),
'bdate': Index(bdate_range('2013-01-02', periods=10)),
}
self.mi = {
'reg': MultiIndex.from_tuples([('bar', 'one'), ('baz', 'two'), ('foo', 'two'),
('qux', 'one'), ('qux', 'two')], names=['first', 'second']),
}
def setUp(self):
super(TestIndex, self).setUp()
self.d = {
'string': tm.makeStringIndex(100),
'date': tm.makeDateIndex(100),
'int': tm.makeIntIndex(100),
'float': tm.makeFloatIndex(100),
'empty': Index([]),
'tuple': Index(zip(['foo', 'bar', 'baz'], [1, 2, 3])),
'period': Index(period_range('2012-1-1', freq='M', periods=3)),
'date2': Index(date_range('2013-01-1', periods=10)),
'bdate': Index(bdate_range('2013-01-02', periods=10)),
}
self.mi = {
'reg': MultiIndex.from_tuples([('bar', 'one'), ('baz', 'two'), ('foo', 'two'),
('qux', 'one'), ('qux', 'two')], names=['first', 'second']),
}
def test_line_area_nan_series(self):
values = [1, 2, np.nan, 3]
s = Series(values)
ts = Series(values, index=tm.makeDateIndex(k=4))
for d in [s, ts]:
ax = _check_plot_works(d.plot)
masked = ax.lines[0].get_ydata()
# remove nan for comparison purpose
exp = np.array([1, 2, 3], dtype=np.float64)
self.assert_numpy_array_equal(np.delete(masked.data, 2), exp)
self.assert_numpy_array_equal(masked.mask, np.array([False, False, True, False]))
expected = np.array([1, 2, 0, 3], dtype=np.float64)
ax = _check_plot_works(d.plot, stacked=True)
self.assert_numpy_array_equal(ax.lines[0].get_ydata(), expected)
ax = _check_plot_works(d.plot.area)
self.assert_numpy_array_equal(ax.lines[0].get_ydata(), expected)
ax = _check_plot_works(d.plot.area, stacked=False)
self.assert_numpy_array_equal(ax.lines[0].get_ydata(), expected)
def test_line_area_nan_series(self):
values = [1, 2, np.nan, 3]
s = Series(values)
ts = Series(values, index=tm.makeDateIndex(k=4))
for d in [s, ts]:
ax = _check_plot_works(d.plot)
masked = ax.lines[0].get_ydata()
# remove nan for comparison purpose
exp = np.array([1, 2, 3], dtype=np.float64)
tm.assert_numpy_array_equal(np.delete(masked.data, 2), exp)
tm.assert_numpy_array_equal(
masked.mask, np.array([False, False, True, False]))
expected = np.array([1, 2, 0, 3], dtype=np.float64)
ax = _check_plot_works(d.plot, stacked=True)
tm.assert_numpy_array_equal(ax.lines[0].get_ydata(), expected)
ax = _check_plot_works(d.plot.area)
tm.assert_numpy_array_equal(ax.lines[0].get_ydata(), expected)
ax = _check_plot_works(d.plot.area, stacked=False)
tm.assert_numpy_array_equal(ax.lines[0].get_ydata(), expected)
def setUp(self):
super(TestIndex, self).setUp()
self.d = {
"string": tm.makeStringIndex(100),
"date": tm.makeDateIndex(100),
"int": tm.makeIntIndex(100),
"float": tm.makeFloatIndex(100),
"empty": Index([]),
"tuple": Index(zip(["foo", "bar", "baz"], [1, 2, 3])),
"period": Index(period_range("2012-1-1", freq="M", periods=3)),
"date2": Index(date_range("2013-01-1", periods=10)),
"bdate": Index(bdate_range("2013-01-02", periods=10)),
}
self.mi = {
"reg": MultiIndex.from_tuples(
[("bar", "one"), ("baz", "two"), ("foo", "two"), ("qux", "one"), ("qux", "two")],
names=["first", "second"],
)
}
def test_get_numeric_data(self):
int_ser = Series(np.array([0, 1, 2]))
float_ser = Series(np.array([0., 1., 2.]))
complex_ser = Series(np.array([0j, 1j, 2j]))
str_ser = Series(np.array(['a', 'b', 'c']))
bool_ser = Series(np.array([True, False, True]))
obj_ser = Series(np.array([1, 'a', 5]))
dt_ser = Series(tm.makeDateIndex(3))
# check types
df = DataFrame({
'int': int_ser,
'float': float_ser,
'complex': complex_ser,
'str': str_ser,
'bool': bool_ser,
'obj': obj_ser,
'dt': dt_ser
})
xp = DataFrame({
'int': int_ser,
'float': float_ser,
'complex': complex_ser,
'bool': bool_ser
})
rs = DataFrame(df._data.get_numeric_data())
assert_frame_equal(xp, rs)
xp = DataFrame({'bool': bool_ser})
rs = DataFrame(df._data.get_bool_data())
assert_frame_equal(xp, rs)
rs = DataFrame(df._data.get_bool_data())
df.ix[0, 'bool'] = not df.ix[0, 'bool']
self.assertEqual(rs.ix[0, 'bool'], df.ix[0, 'bool'])
rs = DataFrame(df._data.get_bool_data(copy=True))
df.ix[0, 'bool'] = not df.ix[0, 'bool']
self.assertEqual(rs.ix[0, 'bool'], not df.ix[0, 'bool'])
def test_replace(self):
N = 100
ser = pd.Series(np.random.randn(N))
ser[0:4] = np.nan
ser[6:10] = 0
# replace list with a single value
ser.replace([np.nan], -1, inplace=True)
exp = ser.fillna(-1)
tm.assert_series_equal(ser, exp)
rs = ser.replace(0., np.nan)
ser[ser == 0.] = np.nan
tm.assert_series_equal(rs, ser)
ser = pd.Series(np.fabs(np.random.randn(N)), tm.makeDateIndex(N),
dtype=object)
ser[:5] = np.nan
ser[6:10] = 'foo'
ser[20:30] = 'bar'
# replace list with a single value
rs = ser.replace([np.nan, 'foo', 'bar'], -1)
assert (rs[:5] == -1).all()
assert (rs[6:10] == -1).all()
assert (rs[20:30] == -1).all()
assert (pd.isnull(ser[:5])).all()
# replace with different values
rs = ser.replace({np.nan: -1, 'foo': -2, 'bar': -3})
assert (rs[:5] == -1).all()
assert (rs[6:10] == -2).all()
assert (rs[20:30] == -3).all()
assert (pd.isnull(ser[:5])).all()
# replace with different values with 2 lists
rs2 = ser.replace([np.nan, 'foo', 'bar'], [-1, -2, -3])
tm.assert_series_equal(rs, rs2)
# replace inplace
ser.replace([np.nan, 'foo', 'bar'], -1, inplace=True)
assert (ser[:5] == -1).all()
assert (ser[6:10] == -1).all()
assert (ser[20:30] == -1).all()
ser = pd.Series([np.nan, 0, np.inf])
tm.assert_series_equal(ser.replace(np.nan, 0), ser.fillna(0))
ser = pd.Series([np.nan, 0, 'foo', 'bar', np.inf, None, lib.NaT])
tm.assert_series_equal(ser.replace(np.nan, 0), ser.fillna(0))
filled = ser.copy()
filled[4] = 0
tm.assert_series_equal(ser.replace(np.inf, 0), filled)
ser = pd.Series(self.ts.index)
tm.assert_series_equal(ser.replace(np.nan, 0), ser.fillna(0))
# malformed
pytest.raises(ValueError, ser.replace, [1, 2, 3], [np.nan, 0])
# make sure that we aren't just masking a TypeError because bools don't
# implement indexing
with tm.assert_raises_regex(TypeError, 'Cannot compare types .+'):
ser.replace([1, 2], [np.nan, 0])
ser = pd.Series([0, 1, 2, 3, 4])
result = ser.replace([0, 1, 2, 3, 4], [4, 3, 2, 1, 0])
tm.assert_series_equal(result, pd.Series([4, 3, 2, 1, 0]))
assert s.iloc[0] == s["a"]
s.iloc[0] = 5
tm.assert_almost_equal(s["a"], 5)
def test_getitem_box_float64(datetime_series):
value = datetime_series[5]
assert isinstance(value, np.float64)
@pytest.mark.parametrize(
"arr",
[
np.random.randn(10),
tm.makeDateIndex(10, name="a").tz_localize(tz="US/Eastern")
],
)
def test_get(arr):
# GH 21260
s = Series(arr, index=[2 * i for i in range(len(arr))])
assert s.get(4) == s.iloc[2]
result = s.get([4, 6])
expected = s.iloc[[2, 3]]
tm.assert_series_equal(result, expected)
result = s.get(slice(2))
expected = s.iloc[[0, 1]]
tm.assert_series_equal(result, expected)
import numpy as np
import pytest
import pandas as pd
from pandas.core.indexes.api import Index, MultiIndex
import pandas.util.testing as tm
@pytest.fixture(params=[tm.makeUnicodeIndex(100),
tm.makeStringIndex(100),
tm.makeDateIndex(100),
tm.makePeriodIndex(100),
tm.makeTimedeltaIndex(100),
tm.makeIntIndex(100),
tm.makeUIntIndex(100),
tm.makeRangeIndex(100),
tm.makeFloatIndex(100),
Index([True, False]),
tm.makeCategoricalIndex(100),
Index([]),
MultiIndex.from_tuples(zip(
['foo', 'bar', 'baz'], [1, 2, 3])),
Index([0, 0, 1, 1, 2, 2])],
ids=lambda x: type(x).__name__)
def indices(request):
return request.param
@pytest.fixture(params=[1, np.array(1, dtype=np.int64)])
def one(request):
# zero-dim integer array behaves like an integer
def setUp(self):
self.strIndex = common.makeStringIndex(100)
self.dateIndex = common.makeDateIndex(100)
self.intIndex = common.makeIntIndex(100)
def test_fillna(self):
ts = Series([0., 1., 2., 3., 4.], index=tm.makeDateIndex(5))
self.assert_numpy_array_equal(ts, ts.fillna(method='ffill'))
ts[2] = np.NaN
self.assert_numpy_array_equal(ts.fillna(method='ffill'),
[0., 1., 1., 3., 4.])
self.assert_numpy_array_equal(ts.fillna(method='backfill'),
[0., 1., 3., 3., 4.])
self.assert_numpy_array_equal(ts.fillna(value=5), [0., 1., 5., 3., 4.])
self.assertRaises(ValueError, ts.fillna)
self.assertRaises(ValueError, self.ts.fillna, value=0, method='ffill')
# GH 5703
s1 = Series([np.nan])
s2 = Series([1])
result = s1.fillna(s2)
expected = Series([1.])
assert_series_equal(result, expected)
result = s1.fillna({})
assert_series_equal(result, s1)
result = s1.fillna(Series(()))
assert_series_equal(result, s1)
result = s2.fillna(s1)
assert_series_equal(result, s2)
result = s1.fillna({0: 1})
assert_series_equal(result, expected)
result = s1.fillna({1: 1})
assert_series_equal(result, Series([np.nan]))
result = s1.fillna({0: 1, 1: 1})
assert_series_equal(result, expected)
result = s1.fillna(Series({0: 1, 1: 1}))
assert_series_equal(result, expected)
result = s1.fillna(Series({0: 1, 1: 1}, index=[4, 5]))
assert_series_equal(result, s1)
s1 = Series([0, 1, 2], list('abc'))
s2 = Series([0, np.nan, 2], list('bac'))
result = s2.fillna(s1)
expected = Series([0, 0, 2.], list('bac'))
assert_series_equal(result, expected)
# limit
s = Series(np.nan, index=[0, 1, 2])
result = s.fillna(999, limit=1)
expected = Series([999, np.nan, np.nan], index=[0, 1, 2])
assert_series_equal(result, expected)
result = s.fillna(999, limit=2)
expected = Series([999, 999, np.nan], index=[0, 1, 2])
assert_series_equal(result, expected)
# GH 9043
# make sure a string representation of int/float values can be filled
# correctly without raising errors or being converted
vals = ['0', '1.5', '-0.3']
for val in vals:
s = Series([0, 1, np.nan, np.nan, 4], dtype='float64')
result = s.fillna(val)
expected = Series([0, 1, val, val, 4], dtype='object')
assert_series_equal(result, expected)
def test_union2(self, sort):
everything = tm.makeDateIndex(10)
first = everything[:5]
second = everything[5:]
union = first.union(second, sort=sort)
tm.assert_index_equal(union, everything)
class TestSeriesMisc(TestData, SharedWithSparse):
series_klass = Series
# SharedWithSparse tests use generic, series_klass-agnostic assertion
_assert_series_equal = staticmethod(tm.assert_series_equal)
def test_tab_completion(self):
# GH 9910
s = Series(list("abcd"))
# Series of str values should have .str but not .dt/.cat in __dir__
assert "str" in dir(s)
assert "dt" not in dir(s)
assert "cat" not in dir(s)
# similarly for .dt
s = Series(date_range("1/1/2015", periods=5))
assert "dt" in dir(s)
assert "str" not in dir(s)
assert "cat" not in dir(s)
# Similarly for .cat, but with the twist that str and dt should be
# there if the categories are of that type first cat and str.
s = Series(list("abbcd"), dtype="category")
assert "cat" in dir(s)
assert "str" in dir(s) # as it is a string categorical
assert "dt" not in dir(s)
# similar to cat and str
s = Series(date_range("1/1/2015", periods=5)).astype("category")
assert "cat" in dir(s)
assert "str" not in dir(s)
assert "dt" in dir(s) # as it is a datetime categorical
def test_tab_completion_with_categorical(self):
# test the tab completion display
ok_for_cat = [
"name",
"index",
"categorical",
"categories",
"codes",
"ordered",
"set_categories",
"add_categories",
"remove_categories",
"rename_categories",
"reorder_categories",
"remove_unused_categories",
"as_ordered",
"as_unordered",
]
def get_dir(s):
results = [r for r in s.cat.__dir__() if not r.startswith("_")]
return list(sorted(set(results)))
s = Series(list("aabbcde")).astype("category")
results = get_dir(s)
tm.assert_almost_equal(results, list(sorted(set(ok_for_cat))))
@pytest.mark.parametrize(
"index",
[
tm.makeUnicodeIndex(10),
tm.makeStringIndex(10),
tm.makeCategoricalIndex(10),
Index(["foo", "bar", "baz"] * 2),
tm.makeDateIndex(10),
tm.makePeriodIndex(10),
tm.makeTimedeltaIndex(10),
tm.makeIntIndex(10),
tm.makeUIntIndex(10),
tm.makeIntIndex(10),
tm.makeFloatIndex(10),
Index([True, False]),
Index(["a{}".format(i) for i in range(101)]),
pd.MultiIndex.from_tuples(zip("ABCD", "EFGH")),
pd.MultiIndex.from_tuples(zip([0, 1, 2, 3], "EFGH")),
],
)
def test_index_tab_completion(self, index):
# dir contains string-like values of the Index.
s = pd.Series(index=index)
dir_s = dir(s)
for i, x in enumerate(s.index.unique(level=0)):
if i < 100:
assert not isinstance(
x, str) or not x.isidentifier() or x in dir_s
else:
assert x not in dir_s
def test_not_hashable(self):
s_empty = Series()
s = Series([1])
msg = "'Series' objects are mutable, thus they cannot be hashed"
with pytest.raises(TypeError, match=msg):
hash(s_empty)
with pytest.raises(TypeError, match=msg):
hash(s)
def test_contains(self):
tm.assert_contains_all(self.ts.index, self.ts)
def test_iter(self):
for i, val in enumerate(self.series):
assert val == self.series[i]
for i, val in enumerate(self.ts):
assert val == self.ts[i]
def test_keys(self):
# HACK: By doing this in two stages, we avoid 2to3 wrapping the call
# to .keys() in a list()
getkeys = self.ts.keys
assert getkeys() is self.ts.index
def test_values(self):
tm.assert_almost_equal(self.ts.values, self.ts, check_dtype=False)
def test_iteritems(self):
for idx, val in self.series.iteritems():
assert val == self.series[idx]
for idx, val in self.ts.iteritems():
assert val == self.ts[idx]
# assert is lazy (genrators don't define reverse, lists do)
assert not hasattr(self.series.iteritems(), "reverse")
def test_items(self):
for idx, val in self.series.items():
assert val == self.series[idx]
for idx, val in self.ts.items():
assert val == self.ts[idx]
# assert is lazy (genrators don't define reverse, lists do)
assert not hasattr(self.series.items(), "reverse")
def test_raise_on_info(self):
s = Series(np.random.randn(10))
msg = "'Series' object has no attribute 'info'"
with pytest.raises(AttributeError, match=msg):
s.info()
def test_copy(self):
for deep in [None, False, True]:
s = Series(np.arange(10), dtype="float64")
# default deep is True
if deep is None:
s2 = s.copy()
else:
s2 = s.copy(deep=deep)
s2[::2] = np.NaN
if deep is None or deep is True:
# Did not modify original Series
assert np.isnan(s2[0])
assert not np.isnan(s[0])
else:
# we DID modify the original Series
assert np.isnan(s2[0])
assert np.isnan(s[0])
def test_copy_tzaware(self):
# GH#11794
# copy of tz-aware
expected = Series([Timestamp("2012/01/01", tz="UTC")])
expected2 = Series([Timestamp("1999/01/01", tz="UTC")])
for deep in [None, False, True]:
s = Series([Timestamp("2012/01/01", tz="UTC")])
if deep is None:
s2 = s.copy()
else:
s2 = s.copy(deep=deep)
s2[0] = pd.Timestamp("1999/01/01", tz="UTC")
# default deep is True
if deep is None or deep is True:
# Did not modify original Series
assert_series_equal(s2, expected2)
assert_series_equal(s, expected)
else:
# we DID modify the original Series
assert_series_equal(s2, expected2)
assert_series_equal(s, expected2)
def test_axis_alias(self):
s = Series([1, 2, np.nan])
assert_series_equal(s.dropna(axis="rows"), s.dropna(axis="index"))
assert s.dropna().sum("rows") == 3
assert s._get_axis_number("rows") == 0
assert s._get_axis_name("rows") == "index"
def test_class_axis(self):
# https://github.com/pandas-dev/pandas/issues/18147
# no exception and no empty docstring
assert pydoc.getdoc(Series.index)
def test_numpy_unique(self):
# it works!
np.unique(self.ts)
def test_ndarray_compat(self):
# test numpy compat with Series as sub-class of NDFrame
tsdf = DataFrame(
np.random.randn(1000, 3),
columns=["A", "B", "C"],
index=date_range("1/1/2000", periods=1000),
)
def f(x):
return x[x.idxmax()]
result = tsdf.apply(f)
expected = tsdf.max()
tm.assert_series_equal(result, expected)
# .item()
with tm.assert_produces_warning(FutureWarning):
s = Series([1])
result = s.item()
assert result == 1
assert s.item() == s.iloc[0]
# using an ndarray like function
s = Series(np.random.randn(10))
result = Series(np.ones_like(s))
expected = Series(1, index=range(10), dtype="float64")
tm.assert_series_equal(result, expected)
# ravel
s = Series(np.random.randn(10))
tm.assert_almost_equal(s.ravel(order="F"), s.values.ravel(order="F"))
# compress
# GH 6658
s = Series([0, 1.0, -1], index=list("abc"))
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s > 0, s)
tm.assert_series_equal(result, Series([1.0], index=["b"]))
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s < -1, s)
# result empty Index(dtype=object) as the same as original
exp = Series([], dtype="float64", index=Index([], dtype="object"))
tm.assert_series_equal(result, exp)
s = Series([0, 1.0, -1], index=[0.1, 0.2, 0.3])
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s > 0, s)
tm.assert_series_equal(result, Series([1.0], index=[0.2]))
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s < -1, s)
# result empty Float64Index as the same as original
exp = Series([], dtype="float64", index=Index([], dtype="float64"))
tm.assert_series_equal(result, exp)
def test_str_accessor_updates_on_inplace(self):
s = pd.Series(list("abc"))
s.drop([0], inplace=True)
assert len(s.str.lower()) == 2
def test_str_attribute(self):
# GH9068
methods = ["strip", "rstrip", "lstrip"]
s = Series([" jack", "jill ", " jesse ", "frank"])
for method in methods:
expected = Series([getattr(str, method)(x) for x in s.values])
assert_series_equal(getattr(Series.str, method)(s.str), expected)
# str accessor only valid with string values
s = Series(range(5))
with pytest.raises(AttributeError, match="only use .str accessor"):
s.str.repeat(2)
def test_empty_method(self):
s_empty = pd.Series()
assert s_empty.empty
for full_series in [pd.Series([1]), pd.Series(index=[1])]:
assert not full_series.empty
def test_tab_complete_warning(self, ip):
# https://github.com/pandas-dev/pandas/issues/16409
pytest.importorskip("IPython", minversion="6.0.0")
from IPython.core.completer import provisionalcompleter
code = "import pandas as pd; s = pd.Series()"
ip.run_code(code)
with tm.assert_produces_warning(None):
with provisionalcompleter("ignore"):
list(ip.Completer.completions("s.", 1))
def test_integer_series_size(self):
# GH 25580
s = Series(range(9))
assert s.size == 9
s = Series(range(9), dtype="Int64")
assert s.size == 9
def test_get_values_deprecation(self):
s = Series(range(9))
with tm.assert_produces_warning(FutureWarning):
res = s.get_values()
tm.assert_numpy_array_equal(res, s.values)
def setUp(self):
self.indices = dict(index=tm.makeDateIndex(10))
self.setup_indices()
import numpy as np
import pytest
import pandas as pd
from pandas.core.indexes.api import Index, MultiIndex
import pandas.util.testing as tm
indices_dict = {
"unicode": tm.makeUnicodeIndex(100),
"string": tm.makeStringIndex(100),
"datetime": tm.makeDateIndex(100),
"period": tm.makePeriodIndex(100),
"timedelta": tm.makeTimedeltaIndex(100),
"int": tm.makeIntIndex(100),
"uint": tm.makeUIntIndex(100),
"range": tm.makeRangeIndex(100),
"float": tm.makeFloatIndex(100),
"bool": Index([True, False]),
"categorical": tm.makeCategoricalIndex(100),
"interval": tm.makeIntervalIndex(100),
"empty": Index([]),
"tuples": MultiIndex.from_tuples(zip(["foo", "bar", "baz"], [1, 2, 3])),
"repeats": Index([0, 0, 1, 1, 2, 2]),
}
@pytest.fixture(params=indices_dict.keys())
def indices(request):
# copy to avoid mutation, e.g. setting .name
return indices_dict[request.param].copy()
def test_dti_timestamp_freq_fields(self):
# extra fields from DatetimeIndex like quarter and week
idx = tm.makeDateIndex(100)
assert idx.freq == Timestamp(idx[-1], idx.freq).freq
assert idx.freqstr == Timestamp(idx[-1], idx.freq).freqstr
class TestSeriesMisc(TestData, SharedWithSparse):
series_klass = Series
# SharedWithSparse tests use generic, series_klass-agnostic assertion
_assert_series_equal = staticmethod(tm.assert_series_equal)
def test_tab_completion(self):
# GH 9910
s = Series(list('abcd'))
# Series of str values should have .str but not .dt/.cat in __dir__
assert 'str' in dir(s)
assert 'dt' not in dir(s)
assert 'cat' not in dir(s)
# similarly for .dt
s = Series(date_range('1/1/2015', periods=5))
assert 'dt' in dir(s)
assert 'str' not in dir(s)
assert 'cat' not in dir(s)
# Similarly for .cat, but with the twist that str and dt should be
# there if the categories are of that type first cat and str.
s = Series(list('abbcd'), dtype="category")
assert 'cat' in dir(s)
assert 'str' in dir(s) # as it is a string categorical
assert 'dt' not in dir(s)
# similar to cat and str
s = Series(date_range('1/1/2015', periods=5)).astype("category")
assert 'cat' in dir(s)
assert 'str' not in dir(s)
assert 'dt' in dir(s) # as it is a datetime categorical
def test_tab_completion_with_categorical(self):
# test the tab completion display
ok_for_cat = [
'categories', 'codes', 'ordered', 'set_categories',
'add_categories', 'remove_categories', 'rename_categories',
'reorder_categories', 'remove_unused_categories', 'as_ordered',
'as_unordered'
]
def get_dir(s):
results = [r for r in s.cat.__dir__() if not r.startswith('_')]
return list(sorted(set(results)))
s = Series(list('aabbcde')).astype('category')
results = get_dir(s)
tm.assert_almost_equal(results, list(sorted(set(ok_for_cat))))
@pytest.mark.parametrize("index", [
tm.makeUnicodeIndex(10),
tm.makeStringIndex(10),
tm.makeCategoricalIndex(10),
Index(['foo', 'bar', 'baz'] * 2),
tm.makeDateIndex(10),
tm.makePeriodIndex(10),
tm.makeTimedeltaIndex(10),
tm.makeIntIndex(10),
tm.makeUIntIndex(10),
tm.makeIntIndex(10),
tm.makeFloatIndex(10),
Index([True, False]),
Index(['a{}'.format(i) for i in range(101)]),
pd.MultiIndex.from_tuples(lzip('ABCD', 'EFGH')),
pd.MultiIndex.from_tuples(lzip([0, 1, 2, 3], 'EFGH')),
])
def test_index_tab_completion(self, index):
# dir contains string-like values of the Index.
s = pd.Series(index=index)
dir_s = dir(s)
for i, x in enumerate(s.index.unique(level=0)):
if i < 100:
assert (not isinstance(x, string_types) or not isidentifier(x)
or x in dir_s)
else:
assert x not in dir_s
def test_not_hashable(self):
s_empty = Series()
s = Series([1])
pytest.raises(TypeError, hash, s_empty)
pytest.raises(TypeError, hash, s)
def test_contains(self):
tm.assert_contains_all(self.ts.index, self.ts)
def test_iter(self):
for i, val in enumerate(self.series):
assert val == self.series[i]
for i, val in enumerate(self.ts):
assert val == self.ts[i]
def test_keys(self):
# HACK: By doing this in two stages, we avoid 2to3 wrapping the call
# to .keys() in a list()
getkeys = self.ts.keys
assert getkeys() is self.ts.index
def test_values(self):
tm.assert_almost_equal(self.ts.values, self.ts, check_dtype=False)
def test_iteritems(self):
for idx, val in compat.iteritems(self.series):
assert val == self.series[idx]
for idx, val in compat.iteritems(self.ts):
assert val == self.ts[idx]
# assert is lazy (genrators don't define reverse, lists do)
assert not hasattr(self.series.iteritems(), 'reverse')
def test_items(self):
for idx, val in self.series.items():
assert val == self.series[idx]
for idx, val in self.ts.items():
assert val == self.ts[idx]
# assert is lazy (genrators don't define reverse, lists do)
assert not hasattr(self.series.items(), 'reverse')
def test_raise_on_info(self):
s = Series(np.random.randn(10))
with pytest.raises(AttributeError):
s.info()
def test_copy(self):
for deep in [None, False, True]:
s = Series(np.arange(10), dtype='float64')
# default deep is True
if deep is None:
s2 = s.copy()
else:
s2 = s.copy(deep=deep)
s2[::2] = np.NaN
if deep is None or deep is True:
# Did not modify original Series
assert np.isnan(s2[0])
assert not np.isnan(s[0])
else:
# we DID modify the original Series
assert np.isnan(s2[0])
assert np.isnan(s[0])
# GH 11794
# copy of tz-aware
expected = Series([Timestamp('2012/01/01', tz='UTC')])
expected2 = Series([Timestamp('1999/01/01', tz='UTC')])
for deep in [None, False, True]:
s = Series([Timestamp('2012/01/01', tz='UTC')])
if deep is None:
s2 = s.copy()
else:
s2 = s.copy(deep=deep)
s2[0] = pd.Timestamp('1999/01/01', tz='UTC')
# default deep is True
if deep is None or deep is True:
# Did not modify original Series
assert_series_equal(s2, expected2)
assert_series_equal(s, expected)
else:
# we DID modify the original Series
assert_series_equal(s2, expected2)
assert_series_equal(s, expected2)
def test_axis_alias(self):
s = Series([1, 2, np.nan])
assert_series_equal(s.dropna(axis='rows'), s.dropna(axis='index'))
assert s.dropna().sum('rows') == 3
assert s._get_axis_number('rows') == 0
assert s._get_axis_name('rows') == 'index'
def test_class_axis(self):
# https://github.com/pandas-dev/pandas/issues/18147
# no exception and no empty docstring
assert pydoc.getdoc(Series.index)
def test_numpy_unique(self):
# it works!
np.unique(self.ts)
def test_ndarray_compat(self):
# test numpy compat with Series as sub-class of NDFrame
tsdf = DataFrame(np.random.randn(1000, 3),
columns=['A', 'B', 'C'],
index=date_range('1/1/2000', periods=1000))
def f(x):
return x[x.idxmax()]
result = tsdf.apply(f)
expected = tsdf.max()
tm.assert_series_equal(result, expected)
# .item()
s = Series([1])
result = s.item()
assert result == 1
assert s.item() == s.iloc[0]
# using an ndarray like function
s = Series(np.random.randn(10))
result = Series(np.ones_like(s))
expected = Series(1, index=range(10), dtype='float64')
tm.assert_series_equal(result, expected)
# ravel
s = Series(np.random.randn(10))
tm.assert_almost_equal(s.ravel(order='F'), s.values.ravel(order='F'))
# compress
# GH 6658
s = Series([0, 1., -1], index=list('abc'))
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s > 0, s)
tm.assert_series_equal(result, Series([1.], index=['b']))
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s < -1, s)
# result empty Index(dtype=object) as the same as original
exp = Series([], dtype='float64', index=Index([], dtype='object'))
tm.assert_series_equal(result, exp)
s = Series([0, 1., -1], index=[.1, .2, .3])
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s > 0, s)
tm.assert_series_equal(result, Series([1.], index=[.2]))
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s < -1, s)
# result empty Float64Index as the same as original
exp = Series([], dtype='float64', index=Index([], dtype='float64'))
tm.assert_series_equal(result, exp)
def test_str_attribute(self):
# GH9068
methods = ['strip', 'rstrip', 'lstrip']
s = Series([' jack', 'jill ', ' jesse ', 'frank'])
for method in methods:
expected = Series([getattr(str, method)(x) for x in s.values])
assert_series_equal(getattr(Series.str, method)(s.str), expected)
# str accessor only valid with string values
s = Series(range(5))
with tm.assert_raises_regex(AttributeError, 'only use .str accessor'):
s.str.repeat(2)
def test_empty_method(self):
s_empty = pd.Series()
assert s_empty.empty
for full_series in [pd.Series([1]), pd.Series(index=[1])]:
assert not full_series.empty
def test_tab_complete_warning(self, ip):
# https://github.com/pandas-dev/pandas/issues/16409
pytest.importorskip('IPython', minversion="6.0.0")
from IPython.core.completer import provisionalcompleter
code = "import pandas as pd; s = pd.Series()"
ip.run_code(code)
with tm.assert_produces_warning(None):
with provisionalcompleter('ignore'):
list(ip.Completer.completions('s.', 1))
def test_set_index_makes_timeseries(self):
idx = tm.makeDateIndex(10)
s = Series(lrange(10))
s.index = idx
assert s.index.is_all_dates
def test_bfill(self):
ts = Series([0., 1., 2., 3., 4.], index=tm.makeDateIndex(5))
ts[2] = np.NaN
assert_series_equal(ts.bfill(), ts.fillna(method='bfill'))
def test_timeseries_coercion(self):
idx = tm.makeDateIndex(10000)
ser = Series(np.random.randn(len(idx)), idx.astype(object))
assert ser.index.is_all_dates
assert isinstance(ser.index, DatetimeIndex)
class TestSeriesMisc:
def test_scalarop_preserve_name(self, datetime_series):
result = datetime_series * 2
assert result.name == datetime_series.name
def test_copy_name(self, datetime_series):
result = datetime_series.copy()
assert result.name == datetime_series.name
def test_copy_index_name_checking(self, datetime_series):
# don't want to be able to modify the index stored elsewhere after
# making a copy
datetime_series.index.name = None
assert datetime_series.index.name is None
assert datetime_series is datetime_series
cp = datetime_series.copy()
cp.index.name = "foo"
printing.pprint_thing(datetime_series.index.name)
assert datetime_series.index.name is None
def test_append_preserve_name(self, datetime_series):
result = datetime_series[:5].append(datetime_series[5:])
assert result.name == datetime_series.name
def test_binop_maybe_preserve_name(self, datetime_series):
# names match, preserve
result = datetime_series * datetime_series
assert result.name == datetime_series.name
result = datetime_series.mul(datetime_series)
assert result.name == datetime_series.name
result = datetime_series * datetime_series[:-2]
assert result.name == datetime_series.name
# names don't match, don't preserve
cp = datetime_series.copy()
cp.name = "something else"
result = datetime_series + cp
assert result.name is None
result = datetime_series.add(cp)
assert result.name is None
ops = ["add", "sub", "mul", "div", "truediv", "floordiv", "mod", "pow"]
ops = ops + ["r" + op for op in ops]
for op in ops:
# names match, preserve
s = datetime_series.copy()
result = getattr(s, op)(s)
assert result.name == datetime_series.name
# names don't match, don't preserve
cp = datetime_series.copy()
cp.name = "changed"
result = getattr(s, op)(cp)
assert result.name is None
def test_combine_first_name(self, datetime_series):
result = datetime_series.combine_first(datetime_series[:5])
assert result.name == datetime_series.name
def test_getitem_preserve_name(self, datetime_series):
result = datetime_series[datetime_series > 0]
assert result.name == datetime_series.name
result = datetime_series[[0, 2, 4]]
assert result.name == datetime_series.name
result = datetime_series[5:10]
assert result.name == datetime_series.name
def test_pickle_datetimes(self, datetime_series):
unp_ts = self._pickle_roundtrip(datetime_series)
tm.assert_series_equal(unp_ts, datetime_series)
def test_pickle_strings(self, string_series):
unp_series = self._pickle_roundtrip(string_series)
tm.assert_series_equal(unp_series, string_series)
def _pickle_roundtrip(self, obj):
with tm.ensure_clean() as path:
obj.to_pickle(path)
unpickled = pd.read_pickle(path)
return unpickled
def test_argsort_preserve_name(self, datetime_series):
result = datetime_series.argsort()
assert result.name == datetime_series.name
def test_sort_index_name(self, datetime_series):
result = datetime_series.sort_index(ascending=False)
assert result.name == datetime_series.name
def test_constructor_dict(self):
d = {"a": 0.0, "b": 1.0, "c": 2.0}
result = Series(d)
expected = Series(d, index=sorted(d.keys()))
tm.assert_series_equal(result, expected)
result = Series(d, index=["b", "c", "d", "a"])
expected = Series([1, 2, np.nan, 0], index=["b", "c", "d", "a"])
tm.assert_series_equal(result, expected)
def test_constructor_subclass_dict(self):
data = tm.TestSubDict((x, 10.0 * x) for x in range(10))
series = Series(data)
expected = Series(dict(data.items()))
tm.assert_series_equal(series, expected)
def test_constructor_ordereddict(self):
# GH3283
data = OrderedDict(
("col{i}".format(i=i), np.random.random()) for i in range(12)
)
series = Series(data)
expected = Series(list(data.values()), list(data.keys()))
tm.assert_series_equal(series, expected)
# Test with subclass
class A(OrderedDict):
pass
series = Series(A(data))
tm.assert_series_equal(series, expected)
def test_constructor_dict_multiindex(self):
d = {("a", "a"): 0.0, ("b", "a"): 1.0, ("b", "c"): 2.0}
_d = sorted(d.items())
result = Series(d)
expected = Series(
[x[1] for x in _d], index=pd.MultiIndex.from_tuples([x[0] for x in _d])
)
tm.assert_series_equal(result, expected)
d["z"] = 111.0
_d.insert(0, ("z", d["z"]))
result = Series(d)
expected = Series(
[x[1] for x in _d], index=pd.Index([x[0] for x in _d], tupleize_cols=False)
)
result = result.reindex(index=expected.index)
tm.assert_series_equal(result, expected)
def test_constructor_dict_timedelta_index(self):
# GH #12169 : Resample category data with timedelta index
# construct Series from dict as data and TimedeltaIndex as index
# will result NaN in result Series data
expected = Series(
data=["A", "B", "C"], index=pd.to_timedelta([0, 10, 20], unit="s")
)
result = Series(
data={
pd.to_timedelta(0, unit="s"): "A",
pd.to_timedelta(10, unit="s"): "B",
pd.to_timedelta(20, unit="s"): "C",
},
index=pd.to_timedelta([0, 10, 20], unit="s"),
)
tm.assert_series_equal(result, expected)
def test_sparse_accessor_updates_on_inplace(self):
s = pd.Series([1, 1, 2, 3], dtype="Sparse[int]")
s.drop([0, 1], inplace=True)
assert s.sparse.density == 1.0
def test_tab_completion(self):
# GH 9910
s = Series(list("abcd"))
# Series of str values should have .str but not .dt/.cat in __dir__
assert "str" in dir(s)
assert "dt" not in dir(s)
assert "cat" not in dir(s)
# similarly for .dt
s = Series(date_range("1/1/2015", periods=5))
assert "dt" in dir(s)
assert "str" not in dir(s)
assert "cat" not in dir(s)
# Similarly for .cat, but with the twist that str and dt should be
# there if the categories are of that type first cat and str.
s = Series(list("abbcd"), dtype="category")
assert "cat" in dir(s)
assert "str" in dir(s) # as it is a string categorical
assert "dt" not in dir(s)
# similar to cat and str
s = Series(date_range("1/1/2015", periods=5)).astype("category")
assert "cat" in dir(s)
assert "str" not in dir(s)
assert "dt" in dir(s) # as it is a datetime categorical
def test_tab_completion_with_categorical(self):
# test the tab completion display
ok_for_cat = [
"categories",
"codes",
"ordered",
"set_categories",
"add_categories",
"remove_categories",
"rename_categories",
"reorder_categories",
"remove_unused_categories",
"as_ordered",
"as_unordered",
]
def get_dir(s):
results = [r for r in s.cat.__dir__() if not r.startswith("_")]
return sorted(set(results))
s = Series(list("aabbcde")).astype("category")
results = get_dir(s)
tm.assert_almost_equal(results, sorted(set(ok_for_cat)))
@pytest.mark.parametrize(
"index",
[
tm.makeUnicodeIndex(10),
tm.makeStringIndex(10),
tm.makeCategoricalIndex(10),
Index(["foo", "bar", "baz"] * 2),
tm.makeDateIndex(10),
tm.makePeriodIndex(10),
tm.makeTimedeltaIndex(10),
tm.makeIntIndex(10),
tm.makeUIntIndex(10),
tm.makeIntIndex(10),
tm.makeFloatIndex(10),
Index([True, False]),
Index(["a{}".format(i) for i in range(101)]),
pd.MultiIndex.from_tuples(zip("ABCD", "EFGH")),
pd.MultiIndex.from_tuples(zip([0, 1, 2, 3], "EFGH")),
],
)
def test_index_tab_completion(self, index):
# dir contains string-like values of the Index.
s = pd.Series(index=index)
dir_s = dir(s)
for i, x in enumerate(s.index.unique(level=0)):
if i < 100:
assert not isinstance(x, str) or not x.isidentifier() or x in dir_s
else:
assert x not in dir_s
def test_not_hashable(self):
s_empty = Series()
s = Series([1])
msg = "'Series' objects are mutable, thus they cannot be hashed"
with pytest.raises(TypeError, match=msg):
hash(s_empty)
with pytest.raises(TypeError, match=msg):
hash(s)
def test_contains(self, datetime_series):
tm.assert_contains_all(datetime_series.index, datetime_series)
def test_iter_datetimes(self, datetime_series):
for i, val in enumerate(datetime_series):
assert val == datetime_series[i]
def test_iter_strings(self, string_series):
for i, val in enumerate(string_series):
assert val == string_series[i]
def test_keys(self, datetime_series):
# HACK: By doing this in two stages, we avoid 2to3 wrapping the call
# to .keys() in a list()
getkeys = datetime_series.keys
assert getkeys() is datetime_series.index
def test_values(self, datetime_series):
tm.assert_almost_equal(
datetime_series.values, datetime_series, check_dtype=False
)
def test_iteritems_datetimes(self, datetime_series):
for idx, val in datetime_series.iteritems():
assert val == datetime_series[idx]
def test_iteritems_strings(self, string_series):
for idx, val in string_series.iteritems():
assert val == string_series[idx]
# assert is lazy (genrators don't define reverse, lists do)
assert not hasattr(string_series.iteritems(), "reverse")
def test_items_datetimes(self, datetime_series):
for idx, val in datetime_series.items():
assert val == datetime_series[idx]
def test_items_strings(self, string_series):
for idx, val in string_series.items():
assert val == string_series[idx]
# assert is lazy (genrators don't define reverse, lists do)
assert not hasattr(string_series.items(), "reverse")
def test_raise_on_info(self):
s = Series(np.random.randn(10))
msg = "'Series' object has no attribute 'info'"
with pytest.raises(AttributeError, match=msg):
s.info()
def test_copy(self):
for deep in [None, False, True]:
s = Series(np.arange(10), dtype="float64")
# default deep is True
if deep is None:
s2 = s.copy()
else:
s2 = s.copy(deep=deep)
s2[::2] = np.NaN
if deep is None or deep is True:
# Did not modify original Series
assert np.isnan(s2[0])
assert not np.isnan(s[0])
else:
# we DID modify the original Series
assert np.isnan(s2[0])
assert np.isnan(s[0])
def test_copy_tzaware(self):
# GH#11794
# copy of tz-aware
expected = Series([Timestamp("2012/01/01", tz="UTC")])
expected2 = Series([Timestamp("1999/01/01", tz="UTC")])
for deep in [None, False, True]:
s = Series([Timestamp("2012/01/01", tz="UTC")])
if deep is None:
s2 = s.copy()
else:
s2 = s.copy(deep=deep)
s2[0] = pd.Timestamp("1999/01/01", tz="UTC")
# default deep is True
if deep is None or deep is True:
# Did not modify original Series
tm.assert_series_equal(s2, expected2)
tm.assert_series_equal(s, expected)
else:
# we DID modify the original Series
tm.assert_series_equal(s2, expected2)
tm.assert_series_equal(s, expected2)
def test_axis_alias(self):
s = Series([1, 2, np.nan])
tm.assert_series_equal(s.dropna(axis="rows"), s.dropna(axis="index"))
assert s.dropna().sum("rows") == 3
assert s._get_axis_number("rows") == 0
assert s._get_axis_name("rows") == "index"
def test_class_axis(self):
# https://github.com/pandas-dev/pandas/issues/18147
# no exception and no empty docstring
assert pydoc.getdoc(Series.index)
def test_numpy_unique(self, datetime_series):
# it works!
np.unique(datetime_series)
def test_ndarray_compat(self):
# test numpy compat with Series as sub-class of NDFrame
tsdf = DataFrame(
np.random.randn(1000, 3),
columns=["A", "B", "C"],
index=date_range("1/1/2000", periods=1000),
)
def f(x):
return x[x.idxmax()]
result = tsdf.apply(f)
expected = tsdf.max()
tm.assert_series_equal(result, expected)
# .item()
with tm.assert_produces_warning(FutureWarning):
s = Series([1])
result = s.item()
assert result == 1
assert s.item() == s.iloc[0]
# using an ndarray like function
s = Series(np.random.randn(10))
result = Series(np.ones_like(s))
expected = Series(1, index=range(10), dtype="float64")
tm.assert_series_equal(result, expected)
# ravel
s = Series(np.random.randn(10))
tm.assert_almost_equal(s.ravel(order="F"), s.values.ravel(order="F"))
# compress
# GH 6658
s = Series([0, 1.0, -1], index=list("abc"))
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s > 0, s)
tm.assert_series_equal(result, Series([1.0], index=["b"]))
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s < -1, s)
# result empty Index(dtype=object) as the same as original
exp = Series([], dtype="float64", index=Index([], dtype="object"))
tm.assert_series_equal(result, exp)
s = Series([0, 1.0, -1], index=[0.1, 0.2, 0.3])
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s > 0, s)
tm.assert_series_equal(result, Series([1.0], index=[0.2]))
with tm.assert_produces_warning(FutureWarning, check_stacklevel=False):
result = np.compress(s < -1, s)
# result empty Float64Index as the same as original
exp = Series([], dtype="float64", index=Index([], dtype="float64"))
tm.assert_series_equal(result, exp)
def test_str_accessor_updates_on_inplace(self):
s = pd.Series(list("abc"))
s.drop([0], inplace=True)
assert len(s.str.lower()) == 2
def test_str_attribute(self):
# GH9068
methods = ["strip", "rstrip", "lstrip"]
s = Series([" jack", "jill ", " jesse ", "frank"])
for method in methods:
expected = Series([getattr(str, method)(x) for x in s.values])
tm.assert_series_equal(getattr(Series.str, method)(s.str), expected)
# str accessor only valid with string values
s = Series(range(5))
with pytest.raises(AttributeError, match="only use .str accessor"):
s.str.repeat(2)
def test_empty_method(self):
s_empty = pd.Series()
assert s_empty.empty
for full_series in [pd.Series([1]), pd.Series(index=[1])]:
assert not full_series.empty
def test_tab_complete_warning(self, ip):
# https://github.com/pandas-dev/pandas/issues/16409
pytest.importorskip("IPython", minversion="6.0.0")
from IPython.core.completer import provisionalcompleter
code = "import pandas as pd; s = pd.Series()"
ip.run_code(code)
with tm.assert_produces_warning(None):
with provisionalcompleter("ignore"):
list(ip.Completer.completions("s.", 1))
def test_integer_series_size(self):
# GH 25580
s = Series(range(9))
assert s.size == 9
s = Series(range(9), dtype="Int64")
assert s.size == 9
def test_get_values_deprecation(self):
s = Series(range(9))
with tm.assert_produces_warning(FutureWarning):
res = s.get_values()
tm.assert_numpy_array_equal(res, s.values)
def setup_method(self, method):
self.indices = dict(index=tm.makeDateIndex(10),
index_dec=date_range('20130110',
periods=10,
freq='-1D'))
self.setup_indices()
pd.DataFrame({"x": [1.0, 2.0, 3.0]}),
pd.DataFrame({0: [1, 2, 3]}),
pd.DataFrame({"x": [1.0, 2.0, 3.0], "y": [4.0, 5.0, 6.0]}),
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:
def test_replace(self):
N = 100
ser = pd.Series(np.random.randn(N))
ser[0:4] = np.nan
ser[6:10] = 0
# replace list with a single value
ser.replace([np.nan], -1, inplace=True)
exp = ser.fillna(-1)
tm.assert_series_equal(ser, exp)
rs = ser.replace(0., np.nan)
ser[ser == 0.] = np.nan
tm.assert_series_equal(rs, ser)
ser = pd.Series(np.fabs(np.random.randn(N)), tm.makeDateIndex(N),
dtype=object)
ser[:5] = np.nan
ser[6:10] = 'foo'
ser[20:30] = 'bar'
# replace list with a single value
rs = ser.replace([np.nan, 'foo', 'bar'], -1)
assert (rs[:5] == -1).all()
assert (rs[6:10] == -1).all()
assert (rs[20:30] == -1).all()
assert (pd.isna(ser[:5])).all()
# replace with different values
rs = ser.replace({np.nan: -1, 'foo': -2, 'bar': -3})
assert (rs[:5] == -1).all()
assert (rs[6:10] == -2).all()
assert (rs[20:30] == -3).all()
assert (pd.isna(ser[:5])).all()
# replace with different values with 2 lists
rs2 = ser.replace([np.nan, 'foo', 'bar'], [-1, -2, -3])
tm.assert_series_equal(rs, rs2)
# replace inplace
ser.replace([np.nan, 'foo', 'bar'], -1, inplace=True)
assert (ser[:5] == -1).all()
assert (ser[6:10] == -1).all()
assert (ser[20:30] == -1).all()
ser = pd.Series([np.nan, 0, np.inf])
tm.assert_series_equal(ser.replace(np.nan, 0), ser.fillna(0))
ser = pd.Series([np.nan, 0, 'foo', 'bar', np.inf, None, pd.NaT])
tm.assert_series_equal(ser.replace(np.nan, 0), ser.fillna(0))
filled = ser.copy()
filled[4] = 0
tm.assert_series_equal(ser.replace(np.inf, 0), filled)
ser = pd.Series(self.ts.index)
tm.assert_series_equal(ser.replace(np.nan, 0), ser.fillna(0))
# malformed
msg = r"Replacement lists must match in length\. Expecting 3 got 2"
with pytest.raises(ValueError, match=msg):
ser.replace([1, 2, 3], [np.nan, 0])
# make sure that we aren't just masking a TypeError because bools don't
# implement indexing
with pytest.raises(TypeError, match='Cannot compare types .+'):
ser.replace([1, 2], [np.nan, 0])
ser = pd.Series([0, 1, 2, 3, 4])
result = ser.replace([0, 1, 2, 3, 4], [4, 3, 2, 1, 0])
tm.assert_series_equal(result, pd.Series([4, 3, 2, 1, 0]))