Python pandas 模块，period_range() 实例源码
我们从Python开源项目中，提取了以下50个代码示例，用于说明如何使用pandas.period_range()。
def test_period_resample_with_local_timezone_pytz(self):
# GH5430
tm._skip_if_no_pytz()
import pytz
local_timezone = pytz.timezone('America/Los_Angeles')
start = datetime(year=2013, month=11, day=1, hour=0, minute=0,
tzinfo=pytz.utc)
# 1 day later
end = datetime(year=2013, month=11, day=2, hour=0, minute=0,
tzinfo=pytz.utc)
index = pd.date_range(start, end, freq='H')
series = pd.Series(1, index=index)
series = series.tz_convert(local_timezone)
result = series.resample('D', kind='period').mean()
# Create the expected series
# Index is moved back a day with the timezone conversion from UTC to
# Pacific
expected_index = (pd.period_range(start=start, end=end, freq='D') - 1)
expected = pd.Series(1, index=expected_index)
assert_series_equal(result, expected)
def test_period_resample_with_local_timezone_dateutil(self):
# GH5430
tm._skip_if_no_dateutil()
import dateutil
local_timezone = 'dateutil/America/Los_Angeles'
start = datetime(year=2013, month=11, day=1, hour=0, minute=0,
tzinfo=dateutil.tz.tzutc())
# 1 day later
end = datetime(year=2013, month=11, day=2, hour=0, minute=0,
tzinfo=dateutil.tz.tzutc())
index = pd.date_range(start, end, freq='H')
series = pd.Series(1, index=index)
series = series.tz_convert(local_timezone)
result = series.resample('D', kind='period').mean()
# Create the expected series
# Index is moved back a day with the timezone conversion from UTC to
# Pacific
expected_index = (pd.period_range(start=start, end=end, freq='D') - 1)
expected = pd.Series(1, index=expected_index)
assert_series_equal(result, expected)
def test_resample_timestamp_to_period(self):
ts = _simple_ts('1/1/1990', '1/1/2000')
result = ts.resample('A-DEC', kind='period').mean()
expected = ts.resample('A-DEC').mean()
expected.index = period_range('1990', '2000', freq='a-dec')
assert_series_equal(result, expected)
result = ts.resample('A-JUN', kind='period').mean()
expected = ts.resample('A-JUN').mean()
expected.index = period_range('1990', '2000', freq='a-jun')
assert_series_equal(result, expected)
result = ts.resample('M', kind='period').mean()
expected = ts.resample('M').mean()
expected.index = period_range('1990-01', '2000-01', freq='M')
assert_series_equal(result, expected)
result = ts.resample('M', kind='period').mean()
expected = ts.resample('M').mean()
expected.index = period_range('1990-01', '2000-01', freq='M')
assert_series_equal(result, expected)
def test_annual_upsample(self):
ts = _simple_pts('1/1/1990', '12/31/1995', freq='A-DEC')
df = DataFrame({'a': ts})
rdf = df.resample('D').ffill()
exp = df['a'].resample('D').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').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_resample_bms_2752(self):
# GH2753
foo = pd.Series(index=pd.bdate_range('20000101', '20000201'))
res1 = foo.resample("BMS").mean()
res2 = foo.resample("BMS").mean().resample("B").mean()
self.assertEqual(res1.index[0], Timestamp('20000103'))
self.assertEqual(res1.index[0], res2.index[0])
# def test_monthly_convention_span(self):
# rng = period_range('2000-01', periods=3, freq='M')
# ts = Series(np.arange(3), index=rng)
# # hacky way to get same thing
# exp_index = period_range('2000-01-01', '2000-03-31', freq='D')
# expected = ts.asfreq('D', how='end').reindex(exp_index)
# expected = expected.fillna(method='bfill')
# result = ts.resample('D', convention='span').mean()
# assert_series_equal(result, expected)
def test_dti_to_period(self):
dti = DatetimeIndex(start='1/1/2005', end='12/1/2005', freq='M')
pi1 = dti.to_period()
pi2 = dti.to_period(freq='D')
pi3 = dti.to_period(freq='3D')
self.assertEqual(pi1[0], Period('Jan 2005', freq='M'))
self.assertEqual(pi2[0], Period('1/31/2005', freq='D'))
self.assertEqual(pi3[0], Period('1/31/2005', freq='3D'))
self.assertEqual(pi1[-1], Period('Nov 2005', freq='M'))
self.assertEqual(pi2[-1], Period('11/30/2005', freq='D'))
self.assertEqual(pi3[-1], Period('11/30/2005', freq='3D'))
tm.assert_index_equal(pi1, period_range('1/1/2005', '11/1/2005',
freq='M'))
tm.assert_index_equal(pi2, period_range('1/1/2005', '11/1/2005',
freq='M').asfreq('D'))
tm.assert_index_equal(pi3, period_range('1/1/2005', '11/1/2005',
freq='M').asfreq('3D'))
def test_pindex_multiples(self):
pi = PeriodIndex(start='1/1/11', end='12/31/11', freq='2M')
expected = PeriodIndex(['2011-01', '2011-03', '2011-05', '2011-07',
'2011-09', '2011-11'], freq='M')
tm.assert_index_equal(pi, expected)
self.assertEqual(pi.freq, offsets.MonthEnd(2))
self.assertEqual(pi.freqstr, '2M')
pi = period_range(start='1/1/11', end='12/31/11', freq='2M')
tm.assert_index_equal(pi, expected)
self.assertEqual(pi.freq, offsets.MonthEnd(2))
self.assertEqual(pi.freqstr, '2M')
pi = period_range(start='1/1/11', periods=6, freq='2M')
tm.assert_index_equal(pi, expected)
self.assertEqual(pi.freq, offsets.MonthEnd(2))
self.assertEqual(pi.freqstr, '2M')
def test_align_series(self):
rng = period_range('1/1/2000', '1/1/2010', freq='A')
ts = Series(np.random.randn(len(rng)), index=rng)
result = ts + ts[::2]
expected = ts + ts
expected[1::2] = np.nan
assert_series_equal(result, expected)
result = ts + _permute(ts[::2])
assert_series_equal(result, expected)
# it works!
for kind in ['inner', 'outer', 'left', 'right']:
ts.align(ts[::2], join=kind)
msg = "Input has different freq=D from PeriodIndex\\(freq=A-DEC\\)"
with assertRaisesRegexp(ValueError, msg):
ts + ts.asfreq('D', how="end")
def test_union(self):
index = period_range('1/1/2000', '1/20/2000', freq='D')
result = index[:-5].union(index[10:])
self.assertTrue(result.equals(index))
# not in order
result = _permute(index[:-5]).union(_permute(index[10:]))
self.assertTrue(result.equals(index))
# raise if different frequencies
index = period_range('1/1/2000', '1/20/2000', freq='D')
index2 = period_range('1/1/2000', '1/20/2000', freq='W-WED')
self.assertRaises(ValueError, index.union, index2)
self.assertRaises(ValueError, index.join, index.to_timestamp())
index3 = period_range('1/1/2000', '1/20/2000', freq='2D')
self.assertRaises(ValueError, index.join, index3)
def test_nested_dict_frame_constructor(self):
rng = pd.period_range('1/1/2000', periods=5)
df = DataFrame(randn(10, 5), columns=rng)
data = {}
for col in df.columns:
for row in df.index:
data.setdefault(col, {})[row] = df.get_value(row, col)
result = DataFrame(data, columns=rng)
assert_frame_equal(result, df)
data = {}
for col in df.columns:
for row in df.index:
data.setdefault(row, {})[col] = df.get_value(row, col)
result = DataFrame(data, index=rng).T
assert_frame_equal(result, df)
def test_reset_index_period(self):
# GH 7746
idx = pd.MultiIndex.from_product([pd.period_range('20130101',
periods=3, freq='M'),
['a', 'b', 'c']],
names=['month', 'feature'])
df = pd.DataFrame(np.arange(9, dtype='int64')
.reshape(-1, 1),
index=idx, columns=['a'])
expected = pd.DataFrame({
'month': ([pd.Period('2013-01', freq='M')] * 3 +
[pd.Period('2013-02', freq='M')] * 3 +
[pd.Period('2013-03', freq='M')] * 3),
'feature': ['a', 'b', 'c'] * 3,
'a': np.arange(9, dtype='int64')
}, columns=['month', 'feature', 'a'])
assert_frame_equal(df.reset_index(), expected)
def test_set_index_period(self):
# GH 6631
df = DataFrame(np.random.random(6))
idx1 = pd.period_range('2011-01-01', periods=3, freq='M')
idx1 = idx1.append(idx1)
idx2 = pd.period_range('2013-01-01 09:00', periods=2, freq='H')
idx2 = idx2.append(idx2).append(idx2)
idx3 = pd.period_range('2005', periods=6, freq='A')
df = df.set_index(idx1)
df = df.set_index(idx2, append=True)
df = df.set_index(idx3, append=True)
expected1 = pd.period_range('2011-01-01', periods=3, freq='M')
expected2 = pd.period_range('2013-01-01 09:00', periods=2, freq='H')
self.assertTrue(df.index.levels[0].equals(expected1))
self.assertTrue(df.index.levels[1].equals(expected2))
self.assertTrue(df.index.levels[2].equals(idx3))
self.assertTrue(df.index.get_level_values(0).equals(idx1))
self.assertTrue(df.index.get_level_values(1).equals(idx2))
self.assertTrue(df.index.get_level_values(2).equals(idx3))
def test_categorical_series_repr_period(self):
idx = pd.period_range('2011-01-01 09:00', freq='H', periods=5)
s = pd.Series(pd.Categorical(idx))
exp = """0 2011-01-01 09:00
1 2011-01-01 10:00
2 2011-01-01 11:00
3 2011-01-01 12:00
4 2011-01-01 13:00
dtype: category
Categories (5, period): [2011-01-01 09:00, 2011-01-01 10:00, 2011-01-01 11:00, 2011-01-01 12:00,
2011-01-01 13:00]"""
self.assertEqual(repr(s), exp)
idx = pd.period_range('2011-01', freq='M', periods=5)
s = pd.Series(pd.Categorical(idx))
exp = """0 2011-01
1 2011-02
2 2011-03
3 2011-04
4 2011-05
dtype: category
Categories (5, period): [2011-01, 2011-02, 2011-03, 2011-04, 2011-05]"""
self.assertEqual(repr(s), exp)
def test_categorical_series_repr_period_ordered(self):
idx = pd.period_range('2011-01-01 09:00', freq='H', periods=5)
s = pd.Series(pd.Categorical(idx, ordered=True))
exp = """0 2011-01-01 09:00
1 2011-01-01 10:00
2 2011-01-01 11:00
3 2011-01-01 12:00
4 2011-01-01 13:00
dtype: category
Categories (5, period): [2011-01-01 09:00 < 2011-01-01 10:00 < 2011-01-01 11:00 < 2011-01-01 12:00 <
2011-01-01 13:00]"""
self.assertEqual(repr(s), exp)
idx = pd.period_range('2011-01', freq='M', periods=5)
s = pd.Series(pd.Categorical(idx, ordered=True))
exp = """0 2011-01
1 2011-02
2 2011-03
3 2011-04
4 2011-05
dtype: category
Categories (5, period): [2011-01 < 2011-02 < 2011-03 < 2011-04 < 2011-05]"""
self.assertEqual(repr(s), exp)
def test_f_f_research(self):
results = web.DataReader("F-F_Research_Data_Factors", "famafrench",
start='2010-01-01', end='2010-12-01')
self.assertTrue(isinstance(results, dict))
self.assertEqual(len(results), 3)
exp = pd.DataFrame({'Mkt-RF': [-3.36, 3.4, 6.31, 2., -7.89, -5.56,
6.93, -4.77, 9.54, 3.88, 0.6, 6.82],
'SMB': [0.2, 1.44, 1.57, 4.92, -0.09, -2.15,
0.24, -3.03, 3.84, 1.01, 3.69, 0.85],
'HML': [0.61, 2.74, 2.01, 3.12, -2.32, -4.27,
0.04, -1.51, -2.94, -2.23, -0.58, 3.47],
'RF': [0., 0., 0.01, 0.01, 0.01, 0.01, 0.01,
0.01, 0.01, 0.01, 0.01, 0.01]},
index=pd.period_range('2010-01-01', '2010-12-01', freq='M', name='Date'),
columns=['Mkt-RF', 'SMB', 'HML', 'RF'])
tm.assert_frame_equal(results[0], exp)
def get_quarts(start, end):
idx = pd.period_range('Q'.join(year_qua(start)), 'Q'.join(year_qua(end)),
freq='Q-JAN')
return [str(d).split('Q') for d in idx][::-1]
def get_quarts(start, end):
idx = pd.period_range('Q'.join(year_qua(start)), 'Q'.join(year_qua(end)),
freq='Q-JAN')
return [str(d).split('Q') for d in idx][::-1]
def test_to_period(self):
from pandas.tseries.period import period_range
ts = _simple_ts('1/1/2000', '1/1/2001')
pts = ts.to_period()
exp = ts.copy()
exp.index = period_range('1/1/2000', '1/1/2001')
assert_series_equal(pts, exp)
pts = ts.to_period('M')
exp.index = exp.index.asfreq('M')
self.assertTrue(pts.index.equals(exp.index.asfreq('M')))
assert_series_equal(pts, exp)
# GH 7606 without freq
idx = DatetimeIndex(['2011-01-01', '2011-01-02', '2011-01-03',
'2011-01-04'])
exp_idx = pd.PeriodIndex(['2011-01-01', '2011-01-02', '2011-01-03',
'2011-01-04'], freq='D')
s = Series(np.random.randn(4), index=idx)
expected = s.copy()
expected.index = exp_idx
assert_series_equal(s.to_period(), expected)
df = DataFrame(np.random.randn(4, 4), index=idx, columns=idx)
expected = df.copy()
expected.index = exp_idx
assert_frame_equal(df.to_period(), expected)
expected = df.copy()
expected.columns = exp_idx
assert_frame_equal(df.to_period(axis=1), expected)
def test_frame_to_period(self):
K = 5
from pandas.tseries.period import period_range
dr = date_range('1/1/2000', '1/1/2001')
pr = period_range('1/1/2000', '1/1/2001')
df = DataFrame(randn(len(dr), K), index=dr)
df['mix'] = 'a'
pts = df.to_period()
exp = df.copy()
exp.index = pr
assert_frame_equal(pts, exp)
pts = df.to_period('M')
self.assertTrue(pts.index.equals(exp.index.asfreq('M')))
df = df.T
pts = df.to_period(axis=1)
exp = df.copy()
exp.columns = pr
assert_frame_equal(pts, exp)
pts = df.to_period('M', axis=1)
self.assertTrue(pts.columns.equals(exp.columns.asfreq('M')))
self.assertRaises(ValueError, df.to_period, axis=2)
def test_asobject_tolist(self):
idx = pd.period_range(start='2013-01-01', periods=4, freq='M',
name='idx')
expected_list = [pd.Period('2013-01-31', freq='M'),
pd.Period('2013-02-28', freq='M'),
pd.Period('2013-03-31', freq='M'),
pd.Period('2013-04-30', freq='M')]
expected = pd.Index(expected_list, dtype=object, name='idx')
result = idx.asobject
self.assertTrue(isinstance(result, Index))
self.assertEqual(result.dtype, object)
self.assertTrue(result.equals(expected))
self.assertEqual(result.name, expected.name)
self.assertEqual(idx.tolist(), expected_list)
idx = PeriodIndex(['2013-01-01', '2013-01-02', 'NaT',
'2013-01-04'], freq='D', name='idx')
expected_list = [pd.Period('2013-01-01', freq='D'),
pd.Period('2013-01-02', freq='D'),
pd.Period('NaT', freq='D'),
pd.Period('2013-01-04', freq='D')]
expected = pd.Index(expected_list, dtype=object, name='idx')
result = idx.asobject
self.assertTrue(isinstance(result, Index))
self.assertEqual(result.dtype, object)
for i in [0, 1, 3]:
self.assertTrue(result[i], expected[i])
self.assertTrue(result[2].ordinal, pd.tslib.iNaT)
self.assertTrue(result[2].freq, 'D')
self.assertEqual(result.name, expected.name)
result_list = idx.tolist()
for i in [0, 1, 3]:
self.assertTrue(result_list[i], expected_list[i])
self.assertTrue(result_list[2].ordinal, pd.tslib.iNaT)
self.assertTrue(result_list[2].freq, 'D')
def test_resolution(self):
for freq, expected in zip(['A', 'Q', 'M', 'D', 'H',
'T', 'S', 'L', 'U'],
['day', 'day', 'day', 'day',
'hour', 'minute', 'second',
'millisecond', 'microsecond']):
idx = pd.period_range(start='2013-04-01', periods=30, freq=freq)
self.assertEqual(idx.resolution, expected)
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_drop_duplicates_metadata(self):
# GH 10115
idx = pd.period_range('2011-01-01', '2011-01-31', freq='D', name='idx')
result = idx.drop_duplicates()
self.assert_index_equal(idx, result)
self.assertEqual(idx.freq, result.freq)
idx_dup = idx.append(idx) # freq will not be reset
result = idx_dup.drop_duplicates()
self.assert_index_equal(idx, result)
self.assertEqual(idx.freq, result.freq)
def test_nat_new(self):
idx = pd.period_range('2011-01', freq='M', periods=5, name='x')
result = idx._nat_new()
exp = pd.PeriodIndex([pd.NaT] * 5, freq='M', name='x')
tm.assert_index_equal(result, exp)
result = idx._nat_new(box=False)
exp = np.array([tslib.iNaT] * 5, dtype=np.int64)
tm.assert_numpy_array_equal(result, exp)
def test_resample_to_period_monthly_buglet(self):
# GH #1259
rng = date_range('1/1/2000', '12/31/2000')
ts = Series(np.random.randn(len(rng)), index=rng)
result = ts.resample('M', kind='period').mean()
exp_index = period_range('Jan-2000', 'Dec-2000', freq='M')
self.assertTrue(result.index.equals(exp_index))
def test_period_with_agg(self):
# aggregate a period resampler with a lambda
s2 = pd.Series(np.random.randint(0, 5, 50),
index=pd.period_range('2012-01-01',
freq='H',
periods=50),
dtype='float64')
expected = s2.to_timestamp().resample('D').mean().to_period()
result = s2.resample('D').agg(lambda x: x.mean())
assert_series_equal(result, expected)
def test_basic_downsample(self):
ts = _simple_pts('1/1/1990', '6/30/1995', freq='M')
result = ts.resample('a-dec').mean()
expected = ts.groupby(ts.index.year).mean()
expected.index = period_range('1/1/1990', '6/30/1995', freq='a-dec')
assert_series_equal(result, expected)
# this is ok
assert_series_equal(ts.resample('a-dec').mean(), result)
assert_series_equal(ts.resample('a').mean(), result)
def test_upsample_with_limit(self):
rng = period_range('1/1/2000', periods=5, freq='A')
ts = Series(np.random.randn(len(rng)), rng)
result = ts.resample('M', convention='end').ffill(limit=2)
expected = ts.asfreq('M').reindex(result.index, method='ffill',
limit=2)
assert_series_equal(result, expected)
def test_resample_to_quarterly(self):
for month in MONTHS:
ts = _simple_pts('1990', '1992', freq='A-%s' % month)
quar_ts = ts.resample('Q-%s' % month).ffill()
stamps = ts.to_timestamp('D', how='start')
qdates = period_range(ts.index[0].asfreq('D', 'start'),
ts.index[-1].asfreq('D', 'end'),
freq='Q-%s' % month)
expected = stamps.reindex(qdates.to_timestamp('D', 's'),
method='ffill')
expected.index = qdates
assert_series_equal(quar_ts, expected)
# conforms, but different month
ts = _simple_pts('1990', '1992', freq='A-JUN')
for how in ['start', 'end']:
result = ts.resample('Q-MAR', convention=how).ffill()
expected = ts.asfreq('Q-MAR', how=how)
expected = expected.reindex(result.index, method='ffill')
# .to_timestamp('D')
# expected = expected.resample('Q-MAR').ffill()
assert_series_equal(result, expected)
def test_resample_5minute(self):
rng = period_range('1/1/2000', '1/5/2000', freq='T')
ts = Series(np.random.randn(len(rng)), index=rng)
result = ts.resample('5min').mean()
expected = ts.to_timestamp().resample('5min').mean()
assert_series_equal(result, expected)
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').mean()
exp = ts.to_timestamp().resample('A').mean().to_period()
assert_series_equal(result, exp)
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").mean()
tm.assert_almost_equal(result[0], s.mean())
def test_hash_error(self):
index = period_range('20010101', periods=10)
with tm.assertRaisesRegexp(TypeError, "unhashable type: %r" %
type(index).__name__):
hash(index)
def test_constructor_field_arrays(self):
# GH #1264
years = np.arange(1990, 2010).repeat(4)[2:-2]
quarters = np.tile(np.arange(1, 5), 20)[2:-2]
index = PeriodIndex(year=years, quarter=quarters, freq='Q-DEC')
expected = period_range('1990Q3', '2009Q2', freq='Q-DEC')
self.assertTrue(index.equals(expected))
index2 = PeriodIndex(year=years, quarter=quarters, freq='2Q-DEC')
tm.assert_numpy_array_equal(index.asi8, index2.asi8)
index = PeriodIndex(year=years, quarter=quarters)
self.assertTrue(index.equals(expected))
years = [2007, 2007, 2007]
months = [1, 2]
self.assertRaises(ValueError, PeriodIndex, year=years, month=months,
freq='M')
self.assertRaises(ValueError, PeriodIndex, year=years, month=months,
freq='2M')
self.assertRaises(ValueError, PeriodIndex, year=years, month=months,
freq='M', start=Period('2007-01', freq='M'))
years = [2007, 2007, 2007]
months = [1, 2, 3]
idx = PeriodIndex(year=years, month=months, freq='M')
exp = period_range('2007-01', periods=3, freq='M')
self.assertTrue(idx.equals(exp))
def test_constructor_U(self):
# U was used as undefined period
self.assertRaises(ValueError, period_range, '2007-1-1', periods=500,
freq='X')
def test_constructor_corner(self):
self.assertRaises(ValueError, PeriodIndex, periods=10, freq='A')
start = Period('2007', freq='A-JUN')
end = Period('2010', freq='A-DEC')
self.assertRaises(ValueError, PeriodIndex, start=start, end=end)
self.assertRaises(ValueError, PeriodIndex, start=start)
self.assertRaises(ValueError, PeriodIndex, end=end)
result = period_range('2007-01', periods=10.5, freq='M')
exp = period_range('2007-01', periods=10, freq='M')
self.assertTrue(result.equals(exp))
def test_constructor_fromarraylike(self):
idx = period_range('2007-01', periods=20, freq='M')
self.assertRaises(ValueError, PeriodIndex, idx.values)
self.assertRaises(ValueError, PeriodIndex, list(idx.values))
self.assertRaises(ValueError, PeriodIndex,
data=Period('2007', freq='A'))
result = PeriodIndex(iter(idx))
self.assertTrue(result.equals(idx))
result = PeriodIndex(idx)
self.assertTrue(result.equals(idx))
result = PeriodIndex(idx, freq='M')
self.assertTrue(result.equals(idx))
result = PeriodIndex(idx, freq=offsets.MonthEnd())
self.assertTrue(result.equals(idx))
self.assertTrue(result.freq, 'M')
result = PeriodIndex(idx, freq='2M')
self.assertTrue(result.equals(idx))
self.assertTrue(result.freq, '2M')
result = PeriodIndex(idx, freq=offsets.MonthEnd(2))
self.assertTrue(result.equals(idx))
self.assertTrue(result.freq, '2M')
result = PeriodIndex(idx, freq='D')
exp = idx.asfreq('D', 'e')
self.assertTrue(result.equals(exp))
def test_constructor_simple_new(self):
idx = period_range('2007-01', name='p', periods=20, freq='M')
result = idx._simple_new(idx, 'p', freq=idx.freq)
self.assertTrue(result.equals(idx))
result = idx._simple_new(idx.astype('i8'), 'p', freq=idx.freq)
self.assertTrue(result.equals(idx))
def test_constructor_freq_mult(self):
# GH #7811
for func in [PeriodIndex, period_range]:
# must be the same, but for sure...
pidx = func(start='2014-01', freq='2M', periods=4)
expected = PeriodIndex(
['2014-01', '2014-03', '2014-05', '2014-07'], freq='M')
tm.assert_index_equal(pidx, expected)
pidx = func(start='2014-01-02', end='2014-01-15', freq='3D')
expected = PeriodIndex(['2014-01-02', '2014-01-05',
'2014-01-08', '2014-01-11',
'2014-01-14'], freq='D')
tm.assert_index_equal(pidx, expected)
pidx = func(end='2014-01-01 17:00', freq='4H', periods=3)
expected = PeriodIndex(['2014-01-01 09:00', '2014-01-01 13:00',
'2014-01-01 17:00'], freq='4H')
tm.assert_index_equal(pidx, expected)
msg = ('Frequency must be positive, because it'
' represents span: -1M')
with tm.assertRaisesRegexp(ValueError, msg):
PeriodIndex(['2011-01'], freq='-1M')
msg = ('Frequency must be positive, because it' ' represents span: 0M')
with tm.assertRaisesRegexp(ValueError, msg):
PeriodIndex(['2011-01'], freq='0M')
msg = ('Frequency must be positive, because it' ' represents span: 0M')
with tm.assertRaisesRegexp(ValueError, msg):
period_range('2011-01', periods=3, freq='0M')
def test_comp_period(self):
idx = period_range('2007-01', periods=20, freq='M')
result = idx < idx[10]
exp = idx.values < idx.values[10]
self.assert_numpy_array_equal(result, exp)
def test_getitem_ndim2(self):
idx = period_range('2007-01', periods=3, freq='M')
result = idx[:, None]
# MPL kludge
tm.assertIsInstance(result, PeriodIndex)
def test_getitem_partial(self):
rng = period_range('2007-01', periods=50, freq='M')
ts = Series(np.random.randn(len(rng)), rng)
self.assertRaises(KeyError, ts.__getitem__, '2006')
result = ts['2008']
self.assertTrue((result.index.year == 2008).all())
result = ts['2008':'2009']
self.assertEqual(len(result), 24)
result = ts['2008-1':'2009-12']
self.assertEqual(len(result), 24)
result = ts['2008Q1':'2009Q4']
self.assertEqual(len(result), 24)
result = ts[:'2009']
self.assertEqual(len(result), 36)
result = ts['2009':]
self.assertEqual(len(result), 50 - 24)
exp = result
result = ts[24:]
assert_series_equal(exp, result)
ts = ts[10:].append(ts[10:])
self.assertRaisesRegexp(KeyError,
"left slice bound for non-unique "
"label: '2008'",
ts.__getitem__, slice('2008', '2009'))
def test_getitem_datetime(self):
rng = period_range(start='2012-01-01', periods=10, freq='W-MON')
ts = Series(lrange(len(rng)), index=rng)
dt1 = datetime(2011, 10, 2)
dt4 = datetime(2012, 4, 20)
rs = ts[dt1:dt4]
assert_series_equal(rs, ts)
def test_slice_with_zero_step_raises(self):
ts = Series(np.arange(20),
period_range('2014-01', periods=20, freq='M'))
self.assertRaisesRegexp(ValueError, 'slice step cannot be zero',
lambda: ts[::0])
self.assertRaisesRegexp(ValueError, 'slice step cannot be zero',
lambda: ts.loc[::0])
self.assertRaisesRegexp(ValueError, 'slice step cannot be zero',
lambda: ts.ix[::0])
def test_contains(self):
rng = period_range('2007-01', freq='M', periods=10)
self.assertTrue(Period('2007-01', freq='M') in rng)
self.assertFalse(Period('2007-01', freq='D') in rng)
self.assertFalse(Period('2007-01', freq='2M') in rng)
def test_sub(self):
rng = period_range('2007-01', periods=50)
result = rng - 5
exp = rng + (-5)
self.assertTrue(result.equals(exp))
def test_periods_number_check(self):
self.assertRaises(ValueError, period_range, '2011-1-1', '2012-1-1',
'B')
def test_as_frame_columns(self):
rng = period_range('1/1/2000', periods=5)
df = DataFrame(randn(10, 5), columns=rng)
ts = df[rng[0]]
assert_series_equal(ts, df.ix[:, 0])
# GH # 1211
repr(df)
ts = df['1/1/2000']
assert_series_equal(ts, df.ix[:, 0])
def test_frame_setitem(self):
rng = period_range('1/1/2000', periods=5)
rng.name = 'index'
df = DataFrame(randn(5, 3), index=rng)
df['Index'] = rng
rs = Index(df['Index'])
self.assertTrue(rs.equals(rng))
rs = df.reset_index().set_index('index')
tm.assertIsInstance(rs.index, PeriodIndex)
self.assertTrue(rs.index.equals(rng))
def test_period_set_index_reindex(self):
# GH 6631
df = DataFrame(np.random.random(6))
idx1 = period_range('2011/01/01', periods=6, freq='M')
idx2 = period_range('2013', periods=6, freq='A')
df = df.set_index(idx1)
self.assertTrue(df.index.equals(idx1))
df = df.set_index(idx2)
self.assertTrue(df.index.equals(idx2))