def _wrap_results(result, dtype):
""" wrap our results if needed """
if issubclass(dtype.type, np.datetime64):
if not isinstance(result, np.ndarray):
result = lib.Timestamp(result)
else:
result = result.view(dtype)
elif issubclass(dtype.type, np.timedelta64):
if not isinstance(result, np.ndarray):
# this is a scalar timedelta result!
# we have series convert then take the element (scalar)
# as series will do the right thing in py3 (and deal with numpy
# 1.6.2 bug in that it results dtype of timedelta64[us]
from pandas import Series
# coerce float to results
if is_float(result):
result = int(result)
result = Series([result], dtype='timedelta64[ns]')
else:
result = result.view(dtype)
return result
def test_tz_aware_asfreq(self):
dr = date_range('2011-12-01','2012-07-20',freq = 'D', tz = 'US/Eastern')
s = Series(np.random.randn(len(dr)), index=dr)
# it works!
s.asfreq('T')
def _delegate_property_get(self, name):
from pandas import Series
result = getattr(self.values, name)
# maybe need to upcast (ints)
if isinstance(result, np.ndarray):
if is_integer_dtype(result):
result = result.astype('int64')
elif not is_list_like(result):
return result
result = np.asarray(result)
# blow up if we operate on categories
if self.orig is not None:
result = take_1d(result, self.orig.cat.codes)
# return the result as a Series, which is by definition a copy
result = Series(result, index=self.index, name=self.name)
# setting this object will show a SettingWithCopyWarning/Error
result.is_copy = ("modifications to a property of a datetimelike "
"object are not supported and are discarded. "
"Change values on the original.")
return result
def quarter_plot(x, dates=None, ylabel=None, ax=None):
"""
Seasonal plot of quarterly data
Parameters
----------
x : array-like
Seasonal data to plot. If dates is None, x must be a pandas object
with a PeriodIndex or DatetimeIndex with a monthly frequency.
dates : array-like, optional
If `x` is not a pandas object, then dates must be supplied.
ylabel : str, optional
The label for the y-axis. Will attempt to use the `name` attribute
of the Series.
ax : matplotlib.axes, optional
Existing axes instance.
Returns
-------
matplotlib.Figure
"""
from pandas import DataFrame
if dates is None:
from statsmodels.tools.data import _check_period_index
_check_period_index(x, freq="Q")
else:
from pandas import Series, PeriodIndex
x = Series(x, index=PeriodIndex(dates, freq="Q"))
xticklabels = ['q1', 'q2', 'q3', 'q4']
return seasonal_plot(x.groupby(lambda y : y.quarter), xticklabels,
ylabel=ylabel, ax=ax)
def test_tz_aware_asfreq(self):
dr = date_range("2011-12-01", "2012-07-20", freq="D", tz=self.tzstr("US/Eastern"))
s = Series(np.random.randn(len(dr)), index=dr)
# it works!
s.asfreq("T")
def test_shift_dst(self):
# GH 13926
dates = date_range('2016-11-06', freq='H', periods=10, tz='US/Eastern')
s = Series(dates)
res = s.shift(0)
tm.assert_series_equal(res, s)
self.assertEqual(res.dtype, 'datetime64[ns, US/Eastern]')
res = s.shift(1)
exp_vals = [NaT] + dates.asobject.values.tolist()[:9]
exp = Series(exp_vals)
tm.assert_series_equal(res, exp)
self.assertEqual(res.dtype, 'datetime64[ns, US/Eastern]')
res = s.shift(-2)
exp_vals = dates.asobject.values.tolist()[2:] + [NaT, NaT]
exp = Series(exp_vals)
tm.assert_series_equal(res, exp)
self.assertEqual(res.dtype, 'datetime64[ns, US/Eastern]')
for ex in [10, -10, 20, -20]:
res = s.shift(ex)
exp = Series([NaT] * 10, dtype='datetime64[ns, US/Eastern]')
tm.assert_series_equal(res, exp)
self.assertEqual(res.dtype, 'datetime64[ns, US/Eastern]')
def test_constructor_series(self):
index1 = ['d', 'b', 'a', 'c']
index2 = sorted(index1)
s1 = Series([4, 7, -5, 3], index=index1)
s2 = Series(s1, index=index2)
assert_series_equal(s2, s1.sort_index())
def test_endswith(self):
values = Series(['om', NA, 'foo_nom', 'nom', 'bar_foo', NA, 'foo'])
result = values.str.endswith('foo')
exp = Series([False, NA, False, False, True, NA, True])
tm.assert_series_equal(result, exp)
# mixed
mixed = ['a', NA, 'b', True, datetime.today(), 'foo', None, 1, 2.]
rs = strings.str_endswith(mixed, 'f')
xp = [False, NA, False, NA, NA, False, NA, NA, NA]
tm.assert_almost_equal(rs, xp)
rs = Series(mixed).str.endswith('f')
tm.assert_isinstance(rs, Series)
tm.assert_almost_equal(rs, xp)
# unicode
values = Series([u('om'), NA, u('foo_nom'), u('nom'), u('bar_foo'), NA,
u('foo')])
result = values.str.endswith('foo')
exp = Series([False, NA, False, False, True, NA, True])
tm.assert_series_equal(result, exp)
result = values.str.endswith('foo', na=False)
tm.assert_series_equal(result, exp.fillna(False).astype(bool))
def test_constructor_with_datetimelike(self):
# 12077
# constructor wwth a datetimelike and NaT
for dtl in [date_range('1995-01-01 00:00:00', periods=5, freq='s'),
date_range('1995-01-01 00:00:00', periods=5,
freq='s', tz='US/Eastern'),
timedelta_range('1 day', periods=5, freq='s')]:
s = Series(dtl)
c = Categorical(s)
expected = type(dtl)(s)
expected.freq = None
tm.assert_index_equal(c.categories, expected)
tm.assert_numpy_array_equal(c.codes, np.arange(5, dtype='int8'))
# with NaT
s2 = s.copy()
s2.iloc[-1] = NaT
c = Categorical(s2)
expected = type(dtl)(s2.dropna())
expected.freq = None
tm.assert_index_equal(c.categories, expected)
exp = np.array([0, 1, 2, 3, -1], dtype=np.int8)
tm.assert_numpy_array_equal(c.codes, exp)
result = repr(c)
assert 'NaT' in result
def test_valid_dt_with_missing_values(self):
from datetime import date, time
# GH 8689
s = Series(date_range('20130101', periods=5, freq='D'))
s.iloc[2] = pd.NaT
for attr in ['microsecond', 'nanosecond', 'second', 'minute', 'hour',
'day']:
expected = getattr(s.dt, attr).copy()
expected.iloc[2] = np.nan
result = getattr(s.dt, attr)
tm.assert_series_equal(result, expected)
result = s.dt.date
expected = Series(
[date(2013, 1, 1), date(2013, 1, 2), np.nan, date(2013, 1, 4),
date(2013, 1, 5)], dtype='object')
tm.assert_series_equal(result, expected)
result = s.dt.time
expected = Series(
[time(0), time(0), np.nan, time(0), time(0)], dtype='object')
tm.assert_series_equal(result, expected)
def shiftTs():
dates = [datetime(2014,1,2), datetime(2014,1,3), datetime(2014,1,4), datetime(2014,1,5)]
ts1 = Series(np.arange(4)+2, index=dates)
#ts1 = ts1/ts1.shift(1) - 1
print (ts1)
ts1 = ts1.shift(1, freq='M')
print (ts1)
def test_mixed_index_assignment(self):
# GH 19860
s = Series([1, 2, 3, 4, 5], index=['a', 'b', 'c', 1, 2])
s.at['a'] = 11
assert s.iat[0] == 11
s.at[1] = 22
assert s.iat[3] == 22
def test_timedelta(self):
converter = lambda x: pd.to_timedelta(x, unit='ms')
s = Series([timedelta(23), timedelta(seconds=5)])
self.assertEqual(s.dtype, 'timedelta64[ns]')
result = pd.read_json(s.to_json(), typ='series').apply(converter)
assert_series_equal(result, s)
s = Series([timedelta(23), timedelta(seconds=5)],
index=pd.Index([0, 1]))
self.assertEqual(s.dtype, 'timedelta64[ns]')
result = pd.read_json(s.to_json(), typ='series').apply(converter)
assert_series_equal(result, s)
frame = DataFrame([timedelta(23), timedelta(seconds=5)])
self.assertEqual(frame[0].dtype, 'timedelta64[ns]')
assert_frame_equal(frame, pd.read_json(frame.to_json())
.apply(converter))
frame = DataFrame({'a': [timedelta(days=23), timedelta(seconds=5)],
'b': [1, 2],
'c': pd.date_range(start='20130101', periods=2)})
result = pd.read_json(frame.to_json(date_unit='ns'))
result['a'] = pd.to_timedelta(result.a, unit='ns')
result['c'] = pd.to_datetime(result.c)
assert_frame_equal(frame, result)
def test_annual_upsample(self):
targets = ['D', 'B', 'M']
for month in MONTHS:
ts = _simple_pts('1/1/1990', '12/31/1995', freq='A-%s' % month)
for targ, conv, meth in product(targets, ['start', 'end'],
['ffill', 'bfill']):
result = ts.resample(targ, fill_method=meth,
convention=conv)
expected = result.to_timestamp(targ, how=conv)
expected = expected.asfreq(targ, meth).to_period()
assert_series_equal(result, expected)
df = DataFrame({'a' : ts})
rdf = df.resample('D', fill_method='ffill')
exp = df['a'].resample('D', fill_method='ffill')
assert_series_equal(rdf['a'], exp)
rng = period_range('2000', '2003', freq='A-DEC')
ts = Series([1, 2, 3, 4], index=rng)
result = ts.resample('M', fill_method='ffill')
ex_index = period_range('2000-01', '2003-12', freq='M')
expected = ts.asfreq('M', how='start').reindex(ex_index,
method='ffill')
assert_series_equal(result, expected)
def test_tshift(self):
# PeriodIndex
ps = tm.makePeriodSeries()
shifted = ps.tshift(1)
unshifted = shifted.tshift(-1)
assert_series_equal(unshifted, ps)
shifted2 = ps.tshift(freq='B')
assert_series_equal(shifted, shifted2)
shifted3 = ps.tshift(freq=datetools.bday)
assert_series_equal(shifted, shifted3)
self.assertRaises(ValueError, ps.tshift, freq='M')
# DatetimeIndex
shifted = self.ts.tshift(1)
unshifted = shifted.tshift(-1)
assert_series_equal(self.ts, unshifted)
shifted2 = self.ts.tshift(freq=self.ts.index.freq)
assert_series_equal(shifted, shifted2)
inferred_ts = Series(self.ts.values, Index(np.asarray(self.ts.index)),
name='ts')
shifted = inferred_ts.tshift(1)
unshifted = shifted.tshift(-1)
assert_series_equal(shifted, self.ts.tshift(1))
assert_series_equal(unshifted, inferred_ts)
no_freq = self.ts[[0, 5, 7]]
self.assertRaises(ValueError, no_freq.tshift)
def test_nat_operations():
# GH 8617
s = Series([0, pd.NaT], dtype='m8[ns]')
exp = s[0]
assert s.median() == exp
assert s.min() == exp
assert s.max() == exp
def test_getitem_setitem_datetime_tz_pytz(self):
tm._skip_if_no_pytz()
from pytz import timezone as tz
from pandas import date_range
N = 50
# testing with timezone, GH #2785
rng = date_range('1/1/1990', periods=N, freq='H', tz='US/Eastern')
ts = Series(np.random.randn(N), index=rng)
# also test Timestamp tz handling, GH #2789
result = ts.copy()
result["1990-01-01 09:00:00+00:00"] = 0
result["1990-01-01 09:00:00+00:00"] = ts[4]
assert_series_equal(result, ts)
result = ts.copy()
result["1990-01-01 03:00:00-06:00"] = 0
result["1990-01-01 03:00:00-06:00"] = ts[4]
assert_series_equal(result, ts)
# repeat with datetimes
result = ts.copy()
result[datetime(1990, 1, 1, 9, tzinfo=tz('UTC'))] = 0
result[datetime(1990, 1, 1, 9, tzinfo=tz('UTC'))] = ts[4]
assert_series_equal(result, ts)
result = ts.copy()
# comparison dates with datetime MUST be localized!
date = tz('US/Central').localize(datetime(1990, 1, 1, 3))
result[date] = 0
result[date] = ts[4]
assert_series_equal(result, ts)
def test_astype(self):
s = Series(np.random.randn(5), name='foo')
for dtype in ['float32', 'float64', 'int64', 'int32']:
astyped = s.astype(dtype)
self.assertEqual(astyped.dtype, dtype)
self.assertEqual(astyped.name, s.name)
def test_repr_unicode(self):
s = Series([u'\u03c3'] * 10)
repr(s)
a = Series([u"\u05d0"] * 1000)
a.name = 'title1'
repr(a)
def test_append_concat(self):
rng = date_range('5/8/2012 1:45', periods=10, freq='5T')
ts = Series(np.random.randn(len(rng)), rng)
df = DataFrame(np.random.randn(len(rng), 4), index=rng)
result = ts.append(ts)
result_df = df.append(df)
ex_index = DatetimeIndex(np.tile(rng.values, 2))
tm.assert_index_equal(result.index, ex_index)
tm.assert_index_equal(result_df.index, ex_index)
appended = rng.append(rng)
tm.assert_index_equal(appended, ex_index)
appended = rng.append([rng, rng])
ex_index = DatetimeIndex(np.tile(rng.values, 3))
tm.assert_index_equal(appended, ex_index)
# different index names
rng1 = rng.copy()
rng2 = rng.copy()
rng1.name = 'foo'
rng2.name = 'bar'
assert rng1.append(rng1).name == 'foo'
assert rng1.append(rng2).name is None
def test_constructor(self):
assert self.ts.index.is_all_dates
# Pass in Series
derived = Series(self.ts)
assert derived.index.is_all_dates
assert tm.equalContents(derived.index, self.ts.index)
# Ensure new index is not created
assert id(self.ts.index) == id(derived.index)
# Mixed type Series
mixed = Series(['hello', np.NaN], index=[0, 1])
assert mixed.dtype == np.object_
assert mixed[1] is np.NaN
assert not self.empty.index.is_all_dates
assert not Series({}).index.is_all_dates
pytest.raises(Exception, Series, np.random.randn(3, 3),
index=np.arange(3))
mixed.name = 'Series'
rs = Series(mixed).name
xp = 'Series'
assert rs == xp
# raise on MultiIndex GH4187
m = MultiIndex.from_arrays([[1, 2], [3, 4]])
pytest.raises(NotImplementedError, Series, m)
def test_first_last_nth_dtypes(df_mixed_floats):
df = df_mixed_floats.copy()
df['E'] = True
df['F'] = 1
# tests for first / last / nth
grouped = df.groupby('A')
first = grouped.first()
expected = df.loc[[1, 0], ['B', 'C', 'D', 'E', 'F']]
expected.index = Index(['bar', 'foo'], name='A')
expected = expected.sort_index()
assert_frame_equal(first, expected)
last = grouped.last()
expected = df.loc[[5, 7], ['B', 'C', 'D', 'E', 'F']]
expected.index = Index(['bar', 'foo'], name='A')
expected = expected.sort_index()
assert_frame_equal(last, expected)
nth = grouped.nth(1)
expected = df.loc[[3, 2], ['B', 'C', 'D', 'E', 'F']]
expected.index = Index(['bar', 'foo'], name='A')
expected = expected.sort_index()
assert_frame_equal(nth, expected)
# GH 2763, first/last shifting dtypes
idx = lrange(10)
idx.append(9)
s = Series(data=lrange(11), index=idx, name='IntCol')
assert s.dtype == 'int64'
f = s.groupby(level=0).first()
assert f.dtype == 'int64'
def test_mixed_freq_irreg_period(self):
ts = tm.makeTimeSeries()
irreg = ts[[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, 16, 17, 18, 29]]
rng = period_range('1/3/2000', periods=30, freq='B')
ps = Series(np.random.randn(len(rng)), rng)
irreg.plot()
ps.plot()
def test_upsample_with_limit(self):
rng = date_range('1/1/2000', periods=3, freq='5t')
ts = Series(np.random.randn(len(rng)), rng)
result = ts.resample('t', fill_method='ffill', limit=2)
expected = ts.reindex(result.index, method='ffill', limit=2)
assert_series_equal(result, expected)
def test_get():
# GH 6383
s = Series(np.array([43, 48, 60, 48, 50, 51, 50, 45, 57, 48, 56, 45,
51, 39, 55, 43, 54, 52, 51, 54]))
result = s.get(25, 0)
expected = 0
assert result == expected
s = Series(np.array([43, 48, 60, 48, 50, 51, 50, 45, 57, 48, 56,
45, 51, 39, 55, 43, 54, 52, 51, 54]),
index=pd.Float64Index(
[25.0, 36.0, 49.0, 64.0, 81.0, 100.0,
121.0, 144.0, 169.0, 196.0, 1225.0,
1296.0, 1369.0, 1444.0, 1521.0, 1600.0,
1681.0, 1764.0, 1849.0, 1936.0],
dtype='object'))
result = s.get(25, 0)
expected = 43
assert result == expected
# GH 7407
# with a boolean accessor
df = pd.DataFrame({'i': [0] * 3, 'b': [False] * 3})
vc = df.i.value_counts()
result = vc.get(99, default='Missing')
assert result == 'Missing'
vc = df.b.value_counts()
result = vc.get(False, default='Missing')
assert result == 3
result = vc.get(True, default='Missing')
assert result == 'Missing'
def test_quarterly_resampling(self):
rng = period_range('2000Q1', periods=10, freq='Q-DEC')
ts = Series(np.arange(10), index=rng)
result = ts.resample('A')
exp = ts.to_timestamp().resample('A').to_period()
assert_series_equal(result, exp)
def test_join_aware(self):
rng = date_range('1/1/2011', periods=10, freq='H')
ts = Series(np.random.randn(len(rng)), index=rng)
ts_utc = ts.tz_localize('utc')
self.assertRaises(Exception, ts.__add__, ts_utc)
self.assertRaises(Exception, ts_utc.__add__, ts)
test1 = DataFrame(np.zeros((6,3)),
index=date_range("2012-11-15 00:00:00", periods=6,
freq="100L", tz="US/Central"))
test2 = DataFrame(np.zeros((3,3)),
index=date_range("2012-11-15 00:00:00", periods=3,
freq="250L", tz="US/Central"),
columns=range(3,6))
result = test1.join(test2, how='outer')
ex_index = test1.index.union(test2.index)
self.assertTrue(result.index.equals(ex_index))
self.assertTrue(result.index.tz.zone == 'US/Central')
# non-overlapping
rng = date_range("2012-11-15 00:00:00", periods=6,
freq="H", tz="US/Central")
rng2 = date_range("2012-11-15 12:00:00", periods=6,
freq="H", tz="US/Eastern")
result = rng.union(rng2)
self.assertTrue(result.tz.zone == 'UTC')
def test_all_values_single_bin(self):
# 2070
index = period_range(start="2012-01-01", end="2012-12-31", freq="M")
s = Series(np.random.randn(len(index)), index=index)
result = s.resample("A", how='mean')
tm.assert_almost_equal(result[0], s.mean())
def test_coercion_with_loc_and_series(self):
for start_data, expected_result in self.EXPECTED_RESULTS:
start_series = Series(start_data)
start_series.loc[start_series == start_series[0]] = None
expected_series = Series(expected_result)
tm.assert_series_equal(start_series, expected_series)
def test_from_weekly_resampling(self):
idxh = date_range('1/1/1999', periods=52, freq='W')
idxl = date_range('1/1/1999', periods=12, freq='M')
high = Series(np.random.randn(len(idxh)), idxh)
low = Series(np.random.randn(len(idxl)), idxl)
low.plot()
ax = high.plot()
expected_h = idxh.to_period().asi8.astype(np.float64)
expected_l = np.array([1514, 1519, 1523, 1527, 1531, 1536, 1540, 1544,
1549, 1553, 1558, 1562], dtype=np.float64)
for l in ax.get_lines():
self.assertTrue(PeriodIndex(data=l.get_xdata()).freq, idxh.freq)
xdata = l.get_xdata(orig=False)
if len(xdata) == 12: # idxl lines
self.assert_numpy_array_equal(xdata, expected_l)
else:
self.assert_numpy_array_equal(xdata, expected_h)
tm.close()
# tsplot
from pandas.tseries.plotting import tsplot
import matplotlib.pyplot as plt
tsplot(low, plt.Axes.plot)
lines = tsplot(high, plt.Axes.plot)
for l in lines:
self.assertTrue(PeriodIndex(data=l.get_xdata()).freq, idxh.freq)
xdata = l.get_xdata(orig=False)
if len(xdata) == 12: # idxl lines
self.assert_numpy_array_equal(xdata, expected_l)
else:
self.assert_numpy_array_equal(xdata, expected_h)