def slide8():
import pytz
print pytz.common_timezones[-5:]
print 'US/Eastern'
tz = pytz.timezone('US/Eastern')
print tz
rng = pd.date_range('3/9/2012 9:30', periods=6, freq='D')
ts = Series(np.random.randn(len(rng)), index=rng)
print ts.index.tz
print 'date_range utc'
print pd.date_range('3/9/2012 9:30', periods=10, freq='D', tz='UTC')
print 'tz_localize to UTC'
ts_utc = ts.tz_localize('UTC')
print ts_utc
print ts_utc.index
print 'tz_convert to us/Eastern'
print ts_utc.tz_convert('US/Eastern')
print 'tz_localize to us/Eastern'
ts_eastern = ts.tz_localize('US/Eastern')
print ts_eastern.tz_convert('UTC')
print 'tz_convert'
print ts_eastern.tz_convert('Europe/Berlin')
stamp = pd.Timestamp('2011-03-12 04:00')
stamp_utc = stamp.tz_localize('utc')
print 'us/eastern'
print stamp_utc.tz_convert('US/Eastern')
stamp_moscow = pd.Timestamp('2011-03-12 04:00', tz='Europe/Moscow')
print 'moscow'
print stamp_moscow
print 'nano seconds'
print stamp_utc.value
print stamp_utc.tz_convert('US/Eastern').value
from pandas.tseries.offsets import Hour
stamp = pd.Timestamp('2012-03-12 01:30', tz='US/Eastern')
print stamp
print '+hour'
print stamp + Hour()
stamp = pd.Timestamp('2012-11-04 00:30', tz='US/Eastern')
print 'summer time'
print stamp + 2 * Hour()
print 'between different time zones'
rng = pd.date_range('3/7/2012 9:30', periods=10, freq='B')
ts = Series(np.random.randn(len(rng)), index=rng)
print ts
ts1 = ts[:7].tz_localize('Europe/London')
ts2 = ts1[2:].tz_convert('Europe/Moscow')
result = ts1 + ts2
print result.index
def test_tz_localize_nonexistent(self, tz, method, exp):
# GH 8917
n = 60
dti = date_range(start="2015-03-29 02:00:00", periods=n, freq="min")
ser = Series(1, index=dti)
df = ser.to_frame()
if method == "raise":
with tm.external_error_raised(pytz.NonExistentTimeError):
dti.tz_localize(tz, nonexistent=method)
with tm.external_error_raised(pytz.NonExistentTimeError):
ser.tz_localize(tz, nonexistent=method)
with tm.external_error_raised(pytz.NonExistentTimeError):
df.tz_localize(tz, nonexistent=method)
elif exp == "invalid":
with pytest.raises(ValueError, match="argument must be one of"):
dti.tz_localize(tz, nonexistent=method)
with pytest.raises(ValueError, match="argument must be one of"):
ser.tz_localize(tz, nonexistent=method)
with pytest.raises(ValueError, match="argument must be one of"):
df.tz_localize(tz, nonexistent=method)
else:
result = ser.tz_localize(tz, nonexistent=method)
expected = Series(1, index=DatetimeIndex([exp] * n, tz=tz))
tm.assert_series_equal(result, expected)
result = df.tz_localize(tz, nonexistent=method)
expected = expected.to_frame()
tm.assert_frame_equal(result, expected)
def slide8():
import pytz
print pytz.common_timezones[-5:]
print 'US/Eastern'
tz = pytz.timezone('US/Eastern')
print tz
rng = pd.date_range('3/9/2012 9:30', periods=6, freq='D')
ts = Series(np.random.randn(len(rng)), index=rng)
print ts.index.tz
print 'date_range utc'
print pd.date_range('3/9/2012 9:30', periods=10, freq='D', tz='UTC')
print 'tz_localize to UTC'
ts_utc = ts.tz_localize('UTC')
print ts_utc
print ts_utc.index
print 'tz_convert to us/Eastern'
print ts_utc.tz_convert('US/Eastern')
print 'tz_localize to us/Eastern'
ts_eastern = ts.tz_localize('US/Eastern')
print ts_eastern.tz_convert('UTC')
print 'tz_convert'
print ts_eastern.tz_convert('Europe/Berlin')
stamp = pd.Timestamp('2011-03-12 04:00')
stamp_utc = stamp.tz_localize('utc')
print 'us/eastern'
print stamp_utc.tz_convert('US/Eastern')
stamp_moscow = pd.Timestamp('2011-03-12 04:00', tz='Europe/Moscow')
print 'moscow'
print stamp_moscow
print 'nano seconds'
print stamp_utc.value
print stamp_utc.tz_convert('US/Eastern').value
from pandas.tseries.offsets import Hour
stamp = pd.Timestamp('2012-03-12 01:30', tz='US/Eastern')
print stamp
print '+hour'
print stamp + Hour()
stamp = pd.Timestamp('2012-11-04 00:30', tz='US/Eastern')
print 'summer time'
print stamp + 2 * Hour()
print 'between different time zones'
rng = pd.date_range('3/7/2012 9:30', periods=10, freq='B')
ts = Series(np.random.randn(len(rng)), index=rng)
print ts
ts1 = ts[:7].tz_localize('Europe/London')
ts2 = ts1[2:].tz_convert('Europe/Moscow')
result = ts1 + ts2
print result.index
def test_series_tz_localize_empty(self, tzstr):
# GH#2248
ser = Series(dtype=object)
ser2 = ser.tz_localize("utc")
assert ser2.index.tz == pytz.utc
ser2 = ser.tz_localize(tzstr)
timezones.tz_compare(ser2.index.tz, timezones.maybe_get_tz(tzstr))
def test_tz_localize_naive(self, frame_or_series):
# Can't localize if already tz-aware
rng = date_range("1/1/2011", periods=100, freq="H", tz="utc")
ts = Series(1, index=rng)
ts = frame_or_series(ts)
with pytest.raises(TypeError, match="Already tz-aware"):
ts.tz_localize("US/Eastern")
def test_series_tz_localize_empty(self, tzstr):
# GH#2248
ser = Series()
ser2 = ser.tz_localize('utc')
assert ser2.index.tz == pytz.utc
ser2 = ser.tz_localize(tzstr)
timezones.tz_compare(ser2.index.tz, timezones.maybe_get_tz(tzstr))
def test_tz_localize_empty_series(self):
# #2248
ts = Series()
ts2 = ts.tz_localize("utc")
self.assertTrue(ts2.index.tz == pytz.utc)
ts2 = ts.tz_localize(self.tzstr("US/Eastern"))
self.assertTrue(self.cmptz(ts2.index.tz, self.tz("US/Eastern")))
def test_tz_localize_empty_series(self):
# #2248
ts = Series()
ts2 = ts.tz_localize('utc')
self.assertTrue(ts2.index.tz == pytz.utc)
ts2 = ts.tz_localize('US/Eastern')
self.assertTrue(ts2.index.tz == pytz.timezone('US/Eastern'))
def test_tz_localize_empty_series(self):
# #2248
ts = Series()
ts2 = ts.tz_localize('utc')
self.assertTrue(ts2.index.tz == pytz.utc)
ts2 = ts.tz_localize('US/Eastern')
self.assertTrue(ts2.index.tz == pytz.timezone('US/Eastern'))
def test_series_tz_localize(self):
rng = date_range("1/1/2011", periods=100, freq="H")
ts = Series(1, index=rng)
result = ts.tz_localize("utc")
assert result.index.tz.zone == "UTC"
# Can't localize if already tz-aware
rng = date_range("1/1/2011", periods=100, freq="H", tz="utc")
ts = Series(1, index=rng)
with pytest.raises(TypeError, match="Already tz-aware"):
ts.tz_localize("US/Eastern")
def test_series_tz_localize(self):
rng = date_range('1/1/2011', periods=100, freq='H')
ts = Series(1, index=rng)
result = ts.tz_localize('utc')
assert result.index.tz.zone == 'UTC'
# Can't localize if already tz-aware
rng = date_range('1/1/2011', periods=100, freq='H', tz='utc')
ts = Series(1, index=rng)
with pytest.raises(TypeError, match='Already tz-aware'):
ts.tz_localize('US/Eastern')
def test_series_tz_localize(self):
rng = date_range('1/1/2011', periods=100, freq='H')
ts = Series(1, index=rng)
result = ts.tz_localize('utc')
assert result.index.tz.zone == 'UTC'
# Can't localize if already tz-aware
rng = date_range('1/1/2011', periods=100, freq='H', tz='utc')
ts = Series(1, index=rng)
with pytest.raises(TypeError, match='Already tz-aware'):
ts.tz_localize('US/Eastern')
def test_series_tz_localize_nonexistent(self, tz, method, exp):
# GH 8917
n = 60
dti = date_range(start='2015-03-29 02:00:00', periods=n, freq='min')
s = Series(1, dti)
if method == 'raise':
with pytest.raises(pytz.NonExistentTimeError):
s.tz_localize(tz, nonexistent=method)
elif exp == 'invalid':
with pytest.raises(ValueError):
dti.tz_localize(tz, nonexistent=method)
else:
result = s.tz_localize(tz, nonexistent=method)
expected = Series(1, index=DatetimeIndex([exp] * n, tz=tz))
tm.assert_series_equal(result, expected)
def test_series_tz_localize_nonexistent(self, tz, method, exp):
# GH 8917
n = 60
dti = date_range(start="2015-03-29 02:00:00", periods=n, freq="min")
s = Series(1, dti)
if method == "raise":
with pytest.raises(pytz.NonExistentTimeError):
s.tz_localize(tz, nonexistent=method)
elif exp == "invalid":
with pytest.raises(ValueError):
dti.tz_localize(tz, nonexistent=method)
else:
result = s.tz_localize(tz, nonexistent=method)
expected = Series(1, index=DatetimeIndex([exp] * n, tz=tz))
tm.assert_series_equal(result, expected)
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_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_resample_tz_localized(self):
dr = date_range(start="2012-4-13", end="2012-5-1")
ts = Series(lrange(len(dr)), dr)
ts_utc = ts.tz_localize("UTC")
ts_local = ts_utc.tz_convert("America/Los_Angeles")
result = ts_local.resample("W")
ts_local_naive = ts_local.copy()
ts_local_naive.index = [x.replace(tzinfo=None) for x in ts_local_naive.index.to_pydatetime()]
exp = ts_local_naive.resample("W").tz_localize("America/Los_Angeles")
assert_series_equal(result, exp)
# it works
result = ts_local.resample("D")
# #2245
idx = date_range("2001-09-20 15:59", "2001-09-20 16:00", freq="T", tz="Australia/Sydney")
s = Series([1, 2], index=idx)
result = s.resample("D", closed="right", label="right")
ex_index = date_range("2001-09-21", periods=1, freq="D", tz="Australia/Sydney")
expected = Series([1.5], index=ex_index)
assert_series_equal(result, expected)
# for good measure
result = s.resample("D", kind="period")
ex_index = period_range("2001-09-20", periods=1, freq="D")
expected = Series([1.5], index=ex_index)
assert_series_equal(result, expected)
def filter_series(ds: pd.Series, first_date: datetime.date, last_date: datetime.date) -> pd.DataFrame:
if not isinstance(first_date, datetime.datetime) and not isinstance(last_date, datetime.datetime):
return ds[list(
filter(lambda x: last_date + datetime.timedelta(days=1) > x > first_date - datetime.timedelta(days=1),
ds.index))]
if ds.index.tz == first_date.tz and ds.index.tz == last_date.tz:
return ds[list(
filter(lambda x: last_date + datetime.timedelta(days=1) > x > first_date - datetime.timedelta(days=1),
ds.index))]
if isinstance(first_date, datetime.datetime):
if first_date.tzinfo != datetime.timezone.utc:
first_date_utc = first_date.replace(tzinfo=datetime.timezone.utc)
return filter_series(ds, first_date_utc, last_date)
if isinstance(last_date, datetime.datetime):
if last_date.tzinfo != datetime.timezone.utc:
last_date_utc = last_date.replace(tzinfo=datetime.timezone.utc)
return filter_series(ds, first_date, last_date_utc)
if hasattr(ds.index.tz, 'zone'):
if ds.index.tz.zone != "UTC":
ds = ds.tz_localize(datetime.timezone.utc)
return ds[list(
filter(lambda x: last_date + datetime.timedelta(days=1) > x > first_date - datetime.timedelta(days=1),
ds.index))]
def part4():
"""时区处理"""
import pytz
# print(pytz.common_timezones[-5:]) # 时区名
# print(pytz.timezone('US/Eastern')) # 时区对象
# 1、本地化和转换
# 默认，pandas中德时间序列是naive时区,也就是没有时区的
rng = pd.date_range('3/9/2012 9:30', periods=6, freq='D')
ts = Series(np.random.randn(len(rng)), index=rng)
# print(ts.index.tz)
rng = pd.date_range('3/9/2012 9:30', periods=6, freq='D', tz='UTC')
ts_utc = Series(np.random.randn(len(rng)), index=rng)
# print(ts_utc.index.tz)
# 通过tz_localize方法可以为没有时区的时间序列赋予时区
ts_utc = ts.tz_localize('UTC')
# print(ts_utc)
# 一旦时间序列被本地化到某个特定时区，就可以用tz_convert将其转换到别的时区了
# print(ts_utc.tz_convert('US/Eastern'))
# 2、操作时区意识型Timestamp对象
stamp = pd.Timestamp('2022-03-12 04:00')
stamp_utc = stamp.tz_localize('utc')
stamp_utc.tz_convert('US/Eastern')
def test_resample_tz_localized(self):
dr = date_range(start="2012-4-13", end="2012-5-1")
ts = Series(range(len(dr)), index=dr)
ts_utc = ts.tz_localize("UTC")
ts_local = ts_utc.tz_convert("America/Los_Angeles")
result = ts_local.resample("W").mean()
ts_local_naive = ts_local.copy()
ts_local_naive.index = [
x.replace(tzinfo=None) for x in ts_local_naive.index.to_pydatetime()
]
exp = ts_local_naive.resample("W").mean().tz_localize("America/Los_Angeles")
exp.index = pd.DatetimeIndex(exp.index, freq="W")
tm.assert_series_equal(result, exp)
# it works
result = ts_local.resample("D").mean()
# #2245
idx = date_range(
"2001-09-20 15:59", "2001-09-20 16:00", freq="T", tz="Australia/Sydney"
)
s = Series([1, 2], index=idx)
result = s.resample("D", closed="right", label="right").mean()
ex_index = date_range("2001-09-21", periods=1, freq="D", tz="Australia/Sydney")
expected = Series([1.5], index=ex_index)
tm.assert_series_equal(result, expected)
# for good measure
result = s.resample("D", kind="period").mean()
ex_index = period_range("2001-09-20", periods=1, freq="D")
expected = Series([1.5], index=ex_index)
tm.assert_series_equal(result, expected)
# GH 6397
# comparing an offset that doesn't propagate tz's
rng = date_range("1/1/2011", periods=20000, freq="H")
rng = rng.tz_localize("EST")
ts = DataFrame(index=rng)
ts["first"] = np.random.randn(len(rng))
ts["second"] = np.cumsum(np.random.randn(len(rng)))
expected = DataFrame(
{
"first": ts.resample("A").sum()["first"],
"second": ts.resample("A").mean()["second"],
},
columns=["first", "second"],
)
result = (
ts.resample("A")
.agg({"first": np.sum, "second": np.mean})
.reindex(columns=["first", "second"])
)
tm.assert_frame_equal(result, expected)
def test_join_naive_with_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)
def test_join_naive_with_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)
def test_resample_tz_localized(self):
dr = date_range(start='2012-4-13', end='2012-5-1')
ts = Series(lrange(len(dr)), dr)
ts_utc = ts.tz_localize('UTC')
ts_local = ts_utc.tz_convert('America/Los_Angeles')
result = ts_local.resample('W').mean()
ts_local_naive = ts_local.copy()
ts_local_naive.index = [x.replace(tzinfo=None)
for x in ts_local_naive.index.to_pydatetime()]
exp = ts_local_naive.resample(
'W').mean().tz_localize('America/Los_Angeles')
assert_series_equal(result, exp)
# it works
result = ts_local.resample('D').mean()
# #2245
idx = date_range('2001-09-20 15:59', '2001-09-20 16:00', freq='T',
tz='Australia/Sydney')
s = Series([1, 2], index=idx)
result = s.resample('D', closed='right', label='right').mean()
ex_index = date_range('2001-09-21', periods=1, freq='D',
tz='Australia/Sydney')
expected = Series([1.5], index=ex_index)
assert_series_equal(result, expected)
# for good measure
result = s.resample('D', kind='period').mean()
ex_index = period_range('2001-09-20', periods=1, freq='D')
expected = Series([1.5], index=ex_index)
assert_series_equal(result, expected)
# GH 6397
# comparing an offset that doesn't propagate tz's
rng = date_range('1/1/2011', periods=20000, freq='H')
rng = rng.tz_localize('EST')
ts = DataFrame(index=rng)
ts['first'] = np.random.randn(len(rng))
ts['second'] = np.cumsum(np.random.randn(len(rng)))
expected = DataFrame(
{
'first': ts.resample('A').sum()['first'],
'second': ts.resample('A').mean()['second']},
columns=['first', 'second'])
result = ts.resample(
'A').agg({'first': np.sum,
'second': np.mean}).reindex(columns=['first', 'second'])
assert_frame_equal(result, expected)
def test_resample_tz_localized(self):
dr = date_range(start='2012-4-13', end='2012-5-1')
ts = Series(lrange(len(dr)), dr)
ts_utc = ts.tz_localize('UTC')
ts_local = ts_utc.tz_convert('America/Los_Angeles')
result = ts_local.resample('W').mean()
ts_local_naive = ts_local.copy()
ts_local_naive.index = [x.replace(tzinfo=None)
for x in ts_local_naive.index.to_pydatetime()]
exp = ts_local_naive.resample(
'W').mean().tz_localize('America/Los_Angeles')
assert_series_equal(result, exp)
# it works
result = ts_local.resample('D').mean()
# #2245
idx = date_range('2001-09-20 15:59', '2001-09-20 16:00', freq='T',
tz='Australia/Sydney')
s = Series([1, 2], index=idx)
result = s.resample('D', closed='right', label='right').mean()
ex_index = date_range('2001-09-21', periods=1, freq='D',
tz='Australia/Sydney')
expected = Series([1.5], index=ex_index)
assert_series_equal(result, expected)
# for good measure
result = s.resample('D', kind='period').mean()
ex_index = period_range('2001-09-20', periods=1, freq='D')
expected = Series([1.5], index=ex_index)
assert_series_equal(result, expected)
# GH 6397
# comparing an offset that doesn't propagate tz's
rng = date_range('1/1/2011', periods=20000, freq='H')
rng = rng.tz_localize('EST')
ts = DataFrame(index=rng)
ts['first'] = np.random.randn(len(rng))
ts['second'] = np.cumsum(np.random.randn(len(rng)))
expected = DataFrame(
{
'first': ts.resample('A').sum()['first'],
'second': ts.resample('A').mean()['second']},
columns=['first', 'second'])
result = ts.resample(
'A').agg({'first': np.sum,
'second': np.mean}).reindex(columns=['first', 'second'])
assert_frame_equal(result, expected)
def test_series_add_aware_naive_raises(self):
rng = date_range('1/1/2011', periods=10, freq='H')
ser = Series(np.random.randn(len(rng)), index=rng)
ser_utc = ser.tz_localize('utc')
with pytest.raises(Exception):
ser + ser_utc
with pytest.raises(Exception):
ser_utc + ser
def test_series_add_aware_naive_raises(self):
rng = date_range("1/1/2011", periods=10, freq="H")
ser = Series(np.random.randn(len(rng)), index=rng)
ser_utc = ser.tz_localize("utc")
with pytest.raises(Exception):
ser + ser_utc
with pytest.raises(Exception):
ser_utc + ser
def test_series_add_aware_naive_raises(self):
rng = date_range("1/1/2011", periods=10, freq="H")
ser = Series(np.random.randn(len(rng)), index=rng)
ser_utc = ser.tz_localize("utc")
msg = "Cannot join tz-naive with tz-aware DatetimeIndex"
with pytest.raises(Exception, match=msg):
ser + ser_utc
with pytest.raises(Exception, match=msg):
ser_utc + ser
def test_localized_at_time(self, tzstr):
tz = timezones.maybe_get_tz(tzstr)
rng = date_range("4/16/2012", "5/1/2012", freq="H")
ts = Series(np.random.randn(len(rng)), index=rng)
ts_local = ts.tz_localize(tzstr)
result = ts_local.at_time(time(10, 0))
expected = ts.at_time(time(10, 0)).tz_localize(tzstr)
tm.assert_series_equal(result, expected)
assert timezones.tz_compare(result.index.tz, tz)
def test_localized_between_time(self, tzstr, frame_or_series):
tz = timezones.maybe_get_tz(tzstr)
rng = date_range("4/16/2012", "5/1/2012", freq="H")
ts = Series(np.random.randn(len(rng)), index=rng)
if frame_or_series is DataFrame:
ts = ts.to_frame()
ts_local = ts.tz_localize(tzstr)
t1, t2 = time(10, 0), time(11, 0)
result = ts_local.between_time(t1, t2)
expected = ts.between_time(t1, t2).tz_localize(tzstr)
tm.assert_equal(result, expected)
assert timezones.tz_compare(result.index.tz, tz)
def test_resample_tz_localized(self):
dr = date_range(start="2012-4-13", end="2012-5-1")
ts = Series(lrange(len(dr)), dr)
ts_utc = ts.tz_localize("UTC")
ts_local = ts_utc.tz_convert("America/Los_Angeles")
result = ts_local.resample("W")
ts_local_naive = ts_local.copy()
ts_local_naive.index = [x.replace(tzinfo=None) for x in ts_local_naive.index.to_pydatetime()]
exp = ts_local_naive.resample("W").tz_localize("America/Los_Angeles")
assert_series_equal(result, exp)
# it works
result = ts_local.resample("D")
# #2245
idx = date_range("2001-09-20 15:59", "2001-09-20 16:00", freq="T", tz="Australia/Sydney")
s = Series([1, 2], index=idx)
result = s.resample("D", closed="right", label="right")
ex_index = date_range("2001-09-21", periods=1, freq="D", tz="Australia/Sydney")
expected = Series([1.5], index=ex_index)
assert_series_equal(result, expected)
# for good measure
result = s.resample("D", kind="period")
ex_index = period_range("2001-09-20", periods=1, freq="D")
expected = Series([1.5], index=ex_index)
assert_series_equal(result, expected)
# GH 6397
# comparing an offset that doesn't propogate tz's
rng = date_range("1/1/2011", periods=20000, freq="H")
rng = rng.tz_localize("EST")
ts = DataFrame(index=rng)
ts["first"] = np.random.randn(len(rng))
ts["second"] = np.cumsum(np.random.randn(len(rng)))
expected = DataFrame(
{"first": ts.resample("A", how=np.sum)["first"], "second": ts.resample("A", how=np.mean)["second"]},
columns=["first", "second"],
)
result = ts.resample("A", how={"first": np.sum, "second": np.mean}).reindex(columns=["first", "second"])
assert_frame_equal(result, expected)
def test_resample_tz_localized(self):
dr = date_range(start='2012-4-13', end='2012-5-1')
ts = Series(range(len(dr)), dr)
ts_utc = ts.tz_localize('UTC')
ts_local = ts_utc.tz_convert('America/Los_Angeles')
result = ts_local.resample('W')
ts_local_naive = ts_local.copy()
ts_local_naive.index = [x.replace(tzinfo=None)
for x in ts_local_naive.index.to_pydatetime()]
exp = ts_local_naive.resample('W').tz_localize('America/Los_Angeles')
assert_series_equal(result, exp)
def test_resample_nonexistent_time_bin_edge(self):
# GH 19375
index = date_range('2017-03-12', '2017-03-12 1:45:00', freq='15T')
s = Series(np.zeros(len(index)), index=index)
expected = s.tz_localize('US/Pacific')
result = expected.resample('900S').mean()
tm.assert_series_equal(result, expected)
# GH 23742
index = date_range(start='2017-10-10', end='2017-10-20', freq='1H')
index = index.tz_localize('UTC').tz_convert('America/Sao_Paulo')
df = DataFrame(data=list(range(len(index))), index=index)
result = df.groupby(pd.Grouper(freq='1D')).count()
expected = date_range(start='2017-10-09', end='2017-10-20', freq='D',
tz="America/Sao_Paulo",
nonexistent='shift_forward', closed='left')
tm.assert_index_equal(result.index, expected)
def test_resample_nonexistent_time_bin_edge(self):
# GH 19375
index = date_range('2017-03-12', '2017-03-12 1:45:00', freq='15T')
s = Series(np.zeros(len(index)), index=index)
expected = s.tz_localize('US/Pacific')
result = expected.resample('900S').mean()
tm.assert_series_equal(result, expected)
# GH 23742
index = date_range(start='2017-10-10', end='2017-10-20', freq='1H')
index = index.tz_localize('UTC').tz_convert('America/Sao_Paulo')
df = DataFrame(data=list(range(len(index))), index=index)
result = df.groupby(pd.Grouper(freq='1D')).count()
expected = date_range(start='2017-10-09', end='2017-10-20', freq='D',
tz="America/Sao_Paulo",
nonexistent='shift_forward', closed='left')
tm.assert_index_equal(result.index, expected)
def test_series_frame_tz_localize(self):
rng = date_range('1/1/2011', periods=100, freq='H')
ts = Series(1, index=rng)
result = ts.tz_localize('utc')
self.assert_(result.index.tz.zone == 'UTC')
df = DataFrame({'a': 1}, index=rng)
result = df.tz_localize('utc')
expected = DataFrame({'a': 1}, rng.tz_localize('UTC'))
self.assert_(result.index.tz.zone == 'UTC')
assert_frame_equal(result, expected)
df = df.T
result = df.tz_localize('utc', axis=1)
self.assert_(result.columns.tz.zone == 'UTC')
assert_frame_equal(result, expected.T)
def test_series_frame_tz_localize(self):
rng = date_range('1/1/2011', periods=100, freq='H')
ts = Series(1, index=rng)
result = ts.tz_localize('utc')
self.assert_(result.index.tz.zone == 'UTC')
df = DataFrame({'a': 1}, index=rng)
result = df.tz_localize('utc')
expected = DataFrame({'a': 1}, rng.tz_localize('UTC'))
self.assert_(result.index.tz.zone == 'UTC')
assert_frame_equal(result, expected)
df = df.T
result = df.tz_localize('utc', axis=1)
self.assert_(result.columns.tz.zone == 'UTC')
assert_frame_equal(result, expected.T)
def test_resample_tz_localized(self):
dr = date_range(start='2012-4-13', end='2012-5-1')
ts = Series(range(len(dr)), dr)
ts_utc = ts.tz_localize('UTC')
ts_local = ts_utc.tz_convert('America/Los_Angeles')
result = ts_local.resample('W')
ts_local_naive = ts_local.copy()
ts_local_naive.index = [
x.replace(tzinfo=None)
for x in ts_local_naive.index.to_pydatetime()
]
exp = ts_local_naive.resample('W').tz_localize('America/Los_Angeles')
assert_series_equal(result, exp)
def test_localized_at_time_between_time(self):
from datetime import time
rng = date_range('4/16/2012', '5/1/2012', freq='H')
ts = Series(np.random.randn(len(rng)), index=rng)
ts_local = ts.tz_localize('US/Eastern')
result = ts_local.at_time(time(10, 0))
expected = ts.at_time(time(10, 0)).tz_localize('US/Eastern')
assert_series_equal(result, expected)
self.assert_(result.index.tz.zone == 'US/Eastern')
t1, t2 = time(10, 0), time(11, 0)
result = ts_local.between_time(t1, t2)
expected = ts.between_time(t1, t2).tz_localize('US/Eastern')
assert_series_equal(result, expected)
self.assert_(result.index.tz.zone == 'US/Eastern')
def test_localized_at_time_between_time(self):
from datetime import time
rng = date_range('4/16/2012', '5/1/2012', freq='H')
ts = Series(np.random.randn(len(rng)), index=rng)
ts_local = ts.tz_localize('US/Eastern')
result = ts_local.at_time(time(10, 0))
expected = ts.at_time(time(10, 0)).tz_localize('US/Eastern')
assert_series_equal(result, expected)
self.assert_(result.index.tz.zone == 'US/Eastern')
t1, t2 = time(10, 0), time(11, 0)
result = ts_local.between_time(t1, t2)
expected = ts.between_time(t1, t2).tz_localize('US/Eastern')
assert_series_equal(result, expected)
self.assert_(result.index.tz.zone == 'US/Eastern')
def test_localized_at_time_between_time(self):
from datetime import time
rng = date_range("4/16/2012", "5/1/2012", freq="H")
ts = Series(np.random.randn(len(rng)), index=rng)
ts_local = ts.tz_localize(self.tzstr("US/Eastern"))
result = ts_local.at_time(time(10, 0))
expected = ts.at_time(time(10, 0)).tz_localize(self.tzstr("US/Eastern"))
tm.assert_series_equal(result, expected)
self.assertTrue(self.cmptz(result.index.tz, self.tz("US/Eastern")))
t1, t2 = time(10, 0), time(11, 0)
result = ts_local.between_time(t1, t2)
expected = ts.between_time(t1, t2).tz_localize(self.tzstr("US/Eastern"))
tm.assert_series_equal(result, expected)
self.assertTrue(self.cmptz(result.index.tz, self.tz("US/Eastern")))
def test_localized_at_time_between_time(self, tzstr):
from datetime import time
tz = timezones.maybe_get_tz(tzstr)
rng = date_range('4/16/2012', '5/1/2012', freq='H')
ts = Series(np.random.randn(len(rng)), index=rng)
ts_local = ts.tz_localize(tzstr)
result = ts_local.at_time(time(10, 0))
expected = ts.at_time(time(10, 0)).tz_localize(tzstr)
tm.assert_series_equal(result, expected)
assert timezones.tz_compare(result.index.tz, tz)
t1, t2 = time(10, 0), time(11, 0)
result = ts_local.between_time(t1, t2)
expected = ts.between_time(t1, t2).tz_localize(tzstr)
tm.assert_series_equal(result, expected)
assert timezones.tz_compare(result.index.tz, tz)
def test_resample_tz_localized(self):
dr = date_range(start='2012-4-13', end='2012-5-1')
ts = Series(range(len(dr)), dr)
ts_utc = ts.tz_localize('UTC')
ts_local = ts_utc.tz_convert('America/Los_Angeles')
result = ts_local.resample('W')
ts_local_naive = ts_local.copy()
ts_local_naive.index = [
x.replace(tzinfo=None)
for x in ts_local_naive.index.to_pydatetime()
]
exp = ts_local_naive.resample('W').tz_localize('America/Los_Angeles')
assert_series_equal(result, exp)
# it works
result = ts_local.resample('D')
# #2245
idx = date_range('2001-09-20 15:59',
'2001-09-20 16:00',
freq='T',
tz='Australia/Sydney')
s = Series([1, 2], index=idx)
result = s.resample('D', closed='right', label='right')
ex_index = date_range('2001-09-21',
periods=1,
freq='D',
tz='Australia/Sydney')
expected = Series([1.5], index=ex_index)
assert_series_equal(result, expected)
# for good measure
result = s.resample('D', kind='period')
ex_index = period_range('2001-09-20', periods=1, freq='D')
expected = Series([1.5], index=ex_index)
assert_series_equal(result, expected)
def test_localized_at_time_between_time(self, tzstr):
from datetime import time
tz = timezones.maybe_get_tz(tzstr)
rng = date_range('4/16/2012', '5/1/2012', freq='H')
ts = Series(np.random.randn(len(rng)), index=rng)
ts_local = ts.tz_localize(tzstr)
result = ts_local.at_time(time(10, 0))
expected = ts.at_time(time(10, 0)).tz_localize(tzstr)
tm.assert_series_equal(result, expected)
assert timezones.tz_compare(result.index.tz, tz)
t1, t2 = time(10, 0), time(11, 0)
result = ts_local.between_time(t1, t2)
expected = ts.between_time(t1, t2).tz_localize(tzstr)
tm.assert_series_equal(result, expected)
assert timezones.tz_compare(result.index.tz, tz)
def test_resample_nonexistent_time_bin_edge(self):
# GH 19375
index = date_range("2017-03-12", "2017-03-12 1:45:00", freq="15T")
s = Series(np.zeros(len(index)), index=index)
expected = s.tz_localize("US/Pacific")
result = expected.resample("900S").mean()
tm.assert_series_equal(result, expected)
# GH 23742
index = date_range(start="2017-10-10", end="2017-10-20", freq="1H")
index = index.tz_localize("UTC").tz_convert("America/Sao_Paulo")
df = DataFrame(data=list(range(len(index))), index=index)
result = df.groupby(pd.Grouper(freq="1D")).count()
expected = date_range(
start="2017-10-09",
end="2017-10-20",
freq="D",
tz="America/Sao_Paulo",
nonexistent="shift_forward",
closed="left",
)
tm.assert_index_equal(result.index, expected)
def test_series_frame_tz_localize(self):
rng = date_range('1/1/2011', periods=100, freq='H')
ts = Series(1, index=rng)
result = ts.tz_localize('utc')
self.assert_(result.index.tz.zone == 'UTC')
df = DataFrame({'a': 1}, index=rng)
result = df.tz_localize('utc')
expected = DataFrame({'a': 1}, rng.tz_localize('UTC'))
self.assert_(result.index.tz.zone == 'UTC')
assert_frame_equal(result, expected)
df = df.T
result = df.tz_localize('utc', axis=1)
self.assert_(result.columns.tz.zone == 'UTC')
assert_frame_equal(result, expected.T)
# Can't localize if already tz-aware
rng = date_range('1/1/2011', periods=100, freq='H', tz='utc')
ts = Series(1, index=rng)
self.assertRaises(Exception, ts.tz_localize, 'US/Eastern')
def test_series_frame_tz_localize(self):
rng = date_range('1/1/2011', periods=100, freq='H')
ts = Series(1, index=rng)
result = ts.tz_localize('utc')
self.assert_(result.index.tz.zone == 'UTC')
df = DataFrame({'a': 1}, index=rng)
result = df.tz_localize('utc')
expected = DataFrame({'a': 1}, rng.tz_localize('UTC'))
self.assert_(result.index.tz.zone == 'UTC')
assert_frame_equal(result, expected)
df = df.T
result = df.tz_localize('utc', axis=1)
self.assert_(result.columns.tz.zone == 'UTC')
assert_frame_equal(result, expected.T)
# Can't localize if already tz-aware
rng = date_range('1/1/2011', periods=100, freq='H', tz='utc')
ts = Series(1, index=rng)
self.assertRaises(Exception, ts.tz_localize, 'US/Eastern')
def test_series_frame_tz_localize(self):
rng = date_range("1/1/2011", periods=100, freq="H")
ts = Series(1, index=rng)
result = ts.tz_localize("utc")
self.assertEqual(result.index.tz.zone, "UTC")
df = DataFrame({"a": 1}, index=rng)
result = df.tz_localize("utc")
expected = DataFrame({"a": 1}, rng.tz_localize("UTC"))
self.assertEqual(result.index.tz.zone, "UTC")
assert_frame_equal(result, expected)
df = df.T
result = df.tz_localize("utc", axis=1)
self.assertEqual(result.columns.tz.zone, "UTC")
assert_frame_equal(result, expected.T)
# Can't localize if already tz-aware
rng = date_range("1/1/2011", periods=100, freq="H", tz="utc")
ts = Series(1, index=rng)
tm.assertRaisesRegexp(TypeError, "Already tz-aware", ts.tz_localize, "US/Eastern")
def test_resample_tz_localized(self):
dr = date_range(start='2012-4-13', end='2012-5-1')
ts = Series(range(len(dr)), dr)
ts_utc = ts.tz_localize('UTC')
ts_local = ts_utc.tz_convert('America/Los_Angeles')
result = ts_local.resample('W')
ts_local_naive = ts_local.copy()
ts_local_naive.index = [x.replace(tzinfo=None)
for x in ts_local_naive.index.to_pydatetime()]
exp = ts_local_naive.resample('W').tz_localize('America/Los_Angeles')
assert_series_equal(result, exp)
# it works
result = ts_local.resample('D')
# #2245
idx = date_range('2001-09-20 15:59', '2001-09-20 16:00', freq='T',
tz='Australia/Sydney')
s = Series([1, 2], index=idx)
result = s.resample('D', closed='right', label='right')
ex_index = date_range('2001-09-21', periods=1, freq='D',
tz='Australia/Sydney')
expected = Series([1.5], index=ex_index)
assert_series_equal(result, expected)
# for good measure
result = s.resample('D', kind='period')
ex_index = period_range('2001-09-20', periods=1, freq='D')
expected = Series([1.5], index=ex_index)
assert_series_equal(result, expected)
print(pytz.common_timezones[:])
# 获得pytz的时区对象，可使用pytz。timezone
tz = pytz.timezone('America/New_York')
print("This is tz", tz)
# 11.4.1时区的本地化和转换
rng = pd.date_range('3/9/2012 9:30', periods=6, freq='D')
ts = pd.Series(np.random.randn(len(rng)), index=rng)
print(ts)
print(ts.index.tz)
print(pd.date_range('3/9/2012 9:30', periods=10, freq='D', tz='UTC'))
# 使用tz_localize方法可从简单时区转换到本地化时区
print("This is ts", ts)
ts_utc = ts.tz_localize('UTC')
print("This is us_utc", ts_utc)
print(ts_utc.index)
print(ts_utc.tz_convert('America/New_York'))
# 将其本地化到EST并转换为UTC或柏林时间
ts_eastern = ts.tz_localize('America/New_York')
print(ts_eastern.tz_convert('UTC'))
print(ts_eastern.tz_convert('Europe/Berlin'))
print("Asia shanghai")
print(ts.index.tz_localize('Asia/Shanghai'))
print(ts)
# 11.4.2时区感知时间戳对象的操作
stamp = pd.Timestamp('2011-03-12 04:00')
stamp_utc = stamp.tz_localize('utc')
ts2 = Series(np.random.randn(20),
index=pd.date_range('1/15/2000', periods=20, freq='4d'))
#计算当月的平均值并赋给当月最后一个日期
ts2.groupby(offset.rollforward).mean()
#时区处理
#查看所有时区
pytz.common_timezones
#本地化和转换
#生成时间序列
rng = pd.date_range('3/9/2012 9:30', periods=6, freq='D')
#以时间序列rng作为index构建Series
ts3 = Series(np.random.randn(len(rng)), index=rng)
#时区化、本地化
#将'3/9/2012 9:30'及后面的6个时间赋给UTC时区，UTC默认永远是0时区
ts3_utc = ts3.tz_localize('UTC')
#转化到别的时区
ts3_utc.tz_convert('US/Eastern')
#将'3/9/2012 9:30'及后面的6个时间赋给美国东部时区，但UTC仍为0时区
ts3_eastern = ts3.tz_localize('US/Eastern')
#验证UTC仍为0时区
ts3_eastern.tz_convert('UTC')
#操作时区意识型Timestamp对象
stamp = pd.Timestamp('2011-03-12 04:00')
#Timestamp对象也可以时区化
stamp_utc = stamp.tz_localize('utc')
#查看美国东部时间
stamp_utc.tz_convert('US/Eastern')
#创建Timestamp时还可以传入一个时区信息，此时仍是以UTC作为0时区
stamp_moscow = pd.Timestamp('2011-03-12 04:00', tz='Europe/Moscow')
rng = pd.date_range('1/2/2011 9:30', periods=6, freq='D')
ts = Series(np.random.randn(6), index=rng)
ts
# In[5]:
print(ts.index.tz)
# In[6]:
pd.date_range('1/2/2011 9:30', periods=6, freq='D', tz='UTC')
# In[7]:
ts_utc = ts.tz_localize('UTC')
# In[8]:
ts_utc
# In[9]:
ts_utc.tz_convert('US/Eastern')
# In[10]:
ts_eastern = ts.tz_localize('US/Eastern')
ts_eastern.tz_convert('Europe/Berlin')
# ### 操作时区意识型TimeStamp对象
# pandas中方法既可以接受时区名, 也可以接受时区对象, 建议只用时区名
# 本地化和转化
# pandas中时间序列默认是 单纯的(naive)时区
rng = pd.date_range('3/9/2012 9:30', periods=6, freq='D')
ts = Series(np.random.randn(len(rng)), index=rng)
# tz字段索引为None
print ts.index.tz
# 在生成日期范围的时候可以加上一个时区集
print pd.date_range('3/9/2012 9:30', periods=10, freq='D', tz='UTC')
# 从单纯(naive)到本地化的转换是通过tz_localize方法
ts_utc = ts.tz_localize('UTC')
print ts_utc
print ts_utc.index
# 被本地化后, 可以通过tz_convert转换到别的时区
print ts_utc.tz_convert('US/Eastern')
# 对于跨越夏令时转变期, 我们可以先本地化到EST,然后在转换到UTC或者柏林时间
ts_eastern = ts.tz_localize('US/Eastern')
print ts_eastern.tz_convert('UTC')
print ts_eastern.tz_convert('Europe/Berlin')
# 下面的也是DatetimeIndex的实例方法
print ts.index.tz_localize('Asia/Shanghai')
