def test_value_counts_unique(self):
# GH 7735
idx = pd.period_range('2011-01-01 09:00', freq='H', periods=10)
# create repeated values, 'n'th element is repeated by n+1 times
idx = PeriodIndex(np.repeat(idx.values, range(1, len(idx) + 1)), freq='H')
exp_idx = PeriodIndex(['2011-01-01 18:00', '2011-01-01 17:00', '2011-01-01 16:00',
'2011-01-01 15:00', '2011-01-01 14:00', '2011-01-01 13:00',
'2011-01-01 12:00', '2011-01-01 11:00', '2011-01-01 10:00',
'2011-01-01 09:00'], freq='H')
expected = Series(range(10, 0, -1), index=exp_idx, dtype='int64')
tm.assert_series_equal(idx.value_counts(), expected)
expected = pd.period_range('2011-01-01 09:00', freq='H', periods=10)
tm.assert_index_equal(idx.unique(), expected)
idx = PeriodIndex(['2013-01-01 09:00', '2013-01-01 09:00', '2013-01-01 09:00',
'2013-01-01 08:00', '2013-01-01 08:00', pd.NaT], freq='H')
exp_idx = PeriodIndex(['2013-01-01 09:00', '2013-01-01 08:00'], freq='H')
expected = Series([3, 2], index=exp_idx)
tm.assert_series_equal(idx.value_counts(), expected)
exp_idx = PeriodIndex(['2013-01-01 09:00', '2013-01-01 08:00', pd.NaT], freq='H')
expected = Series([3, 2, 1], index=exp_idx)
tm.assert_series_equal(idx.value_counts(dropna=False), expected)
tm.assert_index_equal(idx.unique(), exp_idx)
def test_value_counts_unique(self):
# GH 7735
idx = pd.period_range('2011-01-01 09:00', freq='H', periods=10)
# create repeated values, 'n'th element is repeated by n+1 times
idx = PeriodIndex(np.repeat(idx.values, range(1, len(idx) + 1)), freq='H')
exp_idx = PeriodIndex(['2011-01-01 18:00', '2011-01-01 17:00', '2011-01-01 16:00',
'2011-01-01 15:00', '2011-01-01 14:00', '2011-01-01 13:00',
'2011-01-01 12:00', '2011-01-01 11:00', '2011-01-01 10:00',
'2011-01-01 09:00'], freq='H')
expected = Series(range(10, 0, -1), index=exp_idx, dtype='int64')
tm.assert_series_equal(idx.value_counts(), expected)
expected = pd.period_range('2011-01-01 09:00', freq='H', periods=10)
tm.assert_index_equal(idx.unique(), expected)
idx = PeriodIndex(['2013-01-01 09:00', '2013-01-01 09:00', '2013-01-01 09:00',
'2013-01-01 08:00', '2013-01-01 08:00', pd.NaT], freq='H')
exp_idx = PeriodIndex(['2013-01-01 09:00', '2013-01-01 08:00'], freq='H')
expected = Series([3, 2], index=exp_idx)
tm.assert_series_equal(idx.value_counts(), expected)
exp_idx = PeriodIndex(['2013-01-01 09:00', '2013-01-01 08:00', pd.NaT], freq='H')
expected = Series([3, 2, 1], index=exp_idx)
tm.assert_series_equal(idx.value_counts(dropna=False), expected)
tm.assert_index_equal(idx.unique(), exp_idx)
class period_algorithm(object):
goal_time = 0.2
def setup(self):
data = [Period('2011-01', freq='M'), Period('2011-02', freq='M'),
Period('2011-03', freq='M'), Period('2011-04', freq='M')]
self.s = Series(data * 1000)
self.i = PeriodIndex(data, freq='M')
def time_period_series_drop_duplicates(self):
self.s.drop_duplicates()
def time_period_index_drop_duplicates(self):
self.i.drop_duplicates()
def time_period_series_value_counts(self):
self.s.value_counts()
def time_period_index_value_counts(self):
self.i.value_counts()
class Algorithms(object):
goal_time = 0.2
def setup(self):
data = [Period('2011-01', freq='M'), Period('2011-02', freq='M'),
Period('2011-03', freq='M'), Period('2011-04', freq='M')]
self.s = Series(data * 1000)
self.i = PeriodIndex(data, freq='M')
def time_drop_duplicates_pseries(self):
self.s.drop_duplicates()
def time_drop_duplicates_pindex(self):
self.i.drop_duplicates()
def time_value_counts_pseries(self):
self.s.value_counts()
def time_value_counts_pindex(self):
self.i.value_counts()
class Algorithms(object):
goal_time = 0.2
def setup(self):
data = [
Period("2011-01", freq="M"),
Period("2011-02", freq="M"),
Period("2011-03", freq="M"),
Period("2011-04", freq="M"),
]
self.s = Series(data * 1000)
self.i = PeriodIndex(data, freq="M")
def time_drop_duplicates_pseries(self):
self.s.drop_duplicates()
def time_drop_duplicates_pindex(self):
self.i.drop_duplicates()
def time_value_counts_pseries(self):
self.s.value_counts()
def time_value_counts_pindex(self):
self.i.value_counts()
