def test_to_period(self):
rng = date_range("1/1/2000", "1/1/2001", freq="D")
ts = Series(np.random.randn(len(rng)), index=rng)
pts = ts.to_period()
exp = ts.copy()
exp.index = period_range("1/1/2000", "1/1/2001")
tm.assert_series_equal(pts, exp)
pts = ts.to_period("M")
exp.index = exp.index.asfreq("M")
tm.assert_index_equal(pts.index, exp.index.asfreq("M"))
tm.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 = 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
tm.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
tm.assert_frame_equal(df.to_period(), expected)
expected = df.copy()
expected.columns = exp_idx
tm.assert_frame_equal(df.to_period(axis=1), expected)
def test_to_period_raises(self, index):
# https://github.com/pandas-dev/pandas/issues/33327
ser = Series(index=index, dtype=object)
if not isinstance(index, DatetimeIndex):
msg = f"unsupported Type {type(index).__name__}"
with pytest.raises(TypeError, match=msg):
ser.to_period()
def periodTs():
rng = Series(np.random.randn(365),index= pd.date_range('1/1/2000', periods=365, freq='D'))
print (rng.index)
tsQ = rng.to_period(freq='Q-DEC')
tsM = rng.to_period(freq='M')
tsW = rng.to_period(freq='W')
print (tsQ)
print (tsM)
print (tsW)
def test_append_concat(self):
# #1815
d1 = date_range('12/31/1990', '12/31/1999', freq='A-DEC')
d2 = date_range('12/31/2000', '12/31/2009', freq='A-DEC')
s1 = Series(np.random.randn(10), d1)
s2 = Series(np.random.randn(10), d2)
s1 = s1.to_period()
s2 = s2.to_period()
# drops index
result = pd.concat([s1, s2])
assert isinstance(result.index, PeriodIndex)
assert result.index[0] == s1.index[0]
def test_append_concat(self):
# #1815
d1 = date_range("12/31/1990", "12/31/1999", freq="A-DEC")
d2 = date_range("12/31/2000", "12/31/2009", freq="A-DEC")
s1 = Series(np.random.randn(10), d1)
s2 = Series(np.random.randn(10), d2)
s1 = s1.to_period()
s2 = s2.to_period()
# drops index
result = pd.concat([s1, s2])
assert isinstance(result.index, PeriodIndex)
assert result.index[0] == s1.index[0]
def test_append_concat(self):
# #1815
d1 = date_range('12/31/1990', '12/31/1999', freq='A-DEC')
d2 = date_range('12/31/2000', '12/31/2009', freq='A-DEC')
s1 = Series(np.random.randn(10), d1)
s2 = Series(np.random.randn(10), d2)
s1 = s1.to_period()
s2 = s2.to_period()
# drops index
result = pd.concat([s1, s2])
tm.assertIsInstance(result.index, PeriodIndex)
self.assertEqual(result.index[0], s1.index[0])
def test_to_period(self):
from pandas.core.indexes.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")
tm.assert_series_equal(pts, exp)
pts = ts.to_period("M")
exp.index = exp.index.asfreq("M")
tm.assert_index_equal(pts.index, exp.index.asfreq("M"))
tm.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
tm.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
tm.assert_frame_equal(df.to_period(), expected)
expected = df.copy()
expected.columns = exp_idx
tm.assert_frame_equal(df.to_period(axis=1), expected)
def maybe_resample(series: Series, ax: Axes, kwargs):
# resample against axes freq if necessary
freq, ax_freq = _get_freq(ax, series)
if freq is None: # pragma: no cover
raise ValueError("Cannot use dynamic axis without frequency info")
# Convert DatetimeIndex to PeriodIndex
if isinstance(series.index, ABCDatetimeIndex):
series = series.to_period(freq=freq)
if ax_freq is not None and freq != ax_freq:
if is_superperiod(freq, ax_freq): # upsample input
series = series.copy()
# error: "Index" has no attribute "asfreq"
series.index = series.index.asfreq( # type: ignore[attr-defined]
ax_freq, how="s")
freq = ax_freq
elif _is_sup(freq, ax_freq): # one is weekly
how = kwargs.pop("how", "last")
series = getattr(series.resample("D"), how)().dropna()
series = getattr(series.resample(ax_freq), how)().dropna()
freq = ax_freq
elif is_subperiod(freq, ax_freq) or _is_sub(freq, ax_freq):
_upsample_others(ax, freq, kwargs)
else: # pragma: no cover
raise ValueError("Incompatible frequency conversion")
return freq, series
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')
tm.assert_index_equal(pts.index, 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_to_period(self):
from pandas.core.indexes.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')
tm.assert_index_equal(pts.index, 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_resample_basic(self):
# GH3609
s = Series(range(100), index=date_range(
'20130101', freq='s', periods=100, name='idx'), dtype='float')
s[10:30] = np.nan
index = PeriodIndex([
Period('2013-01-01 00:00', 'T'),
Period('2013-01-01 00:01', 'T')], name='idx')
expected = Series([34.5, 79.5], index=index)
result = s.to_period().resample('T', kind='period').mean()
assert_series_equal(result, expected)
result2 = s.resample('T', kind='period').mean()
assert_series_equal(result2, expected)
def test_resample_basic(self):
# GH3609
s = Series(range(100), index=date_range(
'20130101', freq='s', periods=100, name='idx'), dtype='float')
s[10:30] = np.nan
index = PeriodIndex([
Period('2013-01-01 00:00', 'T'),
Period('2013-01-01 00:01', 'T')], name='idx')
expected = Series([34.5, 79.5], index=index)
result = s.to_period().resample('T', kind='period').mean()
assert_series_equal(result, expected)
result2 = s.resample('T', kind='period').mean()
assert_series_equal(result2, expected)
def slide11():
rng = pd.date_range('1/1/2000', periods=3, freq='M')
ts = Series(np.random.randn(3), index=rng)
pts = ts.to_period()
print ts
print pts
rng = pd.date_range('1/29/2000', periods=6, freq='D')
ts2 = Series(np.random.randn(6), index=rng)
print ts2.to_period('M')
print 'convert back'
pts = ts.to_period()
print pts
print pts.to_timestamp(how='end')
print 'macrodata'
data = pd.read_csv('../pydata-book/ch08/macrodata.csv')
print data
print data.year
print data.quarter
index = pd.PeriodIndex(year=data.year, quarter=data.quarter, freq='Q-DEC')
print index
data.index = index
print data.infl
def slide11():
rng = pd.date_range('1/1/2000', periods=3, freq='M')
ts = Series(np.random.randn(3), index=rng)
pts = ts.to_period()
print ts
print pts
rng = pd.date_range('1/29/2000', periods=6, freq='D')
ts2 = Series(np.random.randn(6), index=rng)
print ts2.to_period('M')
print 'convert back'
pts = ts.to_period()
print pts
print pts.to_timestamp(how='end')
print 'macrodata'
data = pd.read_csv('../pydata-book/ch08/macrodata.csv')
print data
print data.year
print data.quarter
index = pd.PeriodIndex(year=data.year, quarter=data.quarter, freq='Q-DEC')
print index
data.index = index
print data.infl
def test_resample_basic(self):
# GH3609
s = Series(
range(100),
index=date_range("20130101", freq="s", periods=100, name="idx"),
dtype="float",
)
s[10:30] = np.nan
index = PeriodIndex(
[Period("2013-01-01 00:00", "T"), Period("2013-01-01 00:01", "T")],
name="idx",
)
expected = Series([34.5, 79.5], index=index)
result = s.to_period().resample("T", kind="period").mean()
tm.assert_series_equal(result, expected)
result2 = s.resample("T", kind="period").mean()
tm.assert_series_equal(result2, expected)
p
p.asfreq('D', 'start')
p.asfreq('D', 'end')
p4pm = (p.asfreq('B', 'e') - 1).asfreq('T', 's') + 16 * 60
p4pm
p4pm.to_timestamp()
rng = pd.period_range('2011Q3', '2012Q4', freq='Q-JAN')
ts = Series(np.arange(len(rng)), index=rng)
ts
new_rng = (rng.asfreq('B', 'e') - 1).asfreq('T', 's') + 16 * 60
ts.index = new_rng.to_timestamp()
ts
rng = pd.date_range('1/1/2000', periods=3, freq='M')
from numpy.random import randn
ts = Series(randn(3), index=rng)
pts = ts.to_period()
ts
pts
rng = pd.date_range('1/29/2000', periods=6, freq='D')
ts2 = Series(randn(6), index=rng)
ts2.to_period('M')
pts = ts.to_period()
pts
pts.to_timestamp(how='end')
#重抽样
rng = pd.date_range('1/1/2000', periods=100, freq='D')
ts = Series(randn(len(rng)), index=rng)
ts.resample('M', how='mean')
ts.resample('M', how='mean', kind='period')
# print pd.date_range('1/1/2000', '1/3/2000 23:59', freq='4h')
# print pd.date_range('1/1/2000', periods=10, freq='1h30min')
ts = Series(np.random.randn(4),
index=pd.date_range('1/1/2000', periods=4, freq='M'))
# print ts.shift(1) - 1
# print pytz.common_timezones[-5:]
rng = pd.period_range('1/1/2000', '6/30/2000', freq='M')
# print rng
rng = pd.period_range('2010Q3', '2012Q4', freq='Q-JAN')
rng = pd.date_range('1/1/2000', periods=3, freq='M')
ts = Series(randn(3), index=rng)
pts = ts.to_period()
# print pts
data = pd.read_csv('ch06/macrodata.csv')
index = pd.PeriodIndex(year=data.year, quarter=data.quarter, freq='Q-DEC')
data.index = index
# print data.infl
rng = pd.date_range('1/1/2000', periods=100, freq='D')
ts = Series(randn(len(rng)), index=rng)
# print ts
# print ts.resample('M', how='mean')
rng = pd.date_range('1/1/2000', periods=12, freq='T')
ts = Series(np.arange(12), index=rng)
# print ts.resample('5min', closed='left', label='left').sum()
p.asfreq('D', 'start')
# In[39]:
p4pm = (p.asfreq('B', 'e') - 1).asfreq('T', 's') + 16 * 60
p4pm
# In[40]:
p4pm.to_timestamp()
# In[41]:
rng = pd.date_range('1/29/2000', periods=6, freq='D')
ts2 = Series(np.random.randn(6), index=rng)
ts2.to_period('M')
# In[42]:
macrodata_file = open('F:/电影/数据分析/pydata-book-master/ch08/macrodata.csv')
data = pd.read_csv(macrodata_file)
# In[44]:
data.head()
# In[45]:
index = pd.PeriodIndex(year=data.year, quarter=data.quarter, freq='Q-DEC')
data.index = index
ts = Series(np.arange(len(rngb)), index=rngb)
print(ts)
#频率变成分钟,再加16小时
#最后一个工作日减1的下午4点
new_rngb = (rngb.asfreq('B', 'e') - 1).asfreq('T', 's') + 16 * 60
ts.index = new_rngb.to_timestamp()
print(ts)
#将Timestamp转换为Period(及其反向过程)
#通过使用to_period方法，可以将时间戳索引的Series和DataFrame对象
#转换为以时期索引
rngc = pd.date_range('1/1/2000', periods=3, freq='M')
print(rngc)
tsc = Series(np.random.randn(3), index=rngc)
print(tsc)
pts = tsc.to_period()
print(pts)
rngd = pd.date_range('1/29/2000', periods=6, freq="D")
ts3 = Series(np.random.randn(6), index=rngd)
print(ts3.to_period('M'))
#要转换为时间戳，使用to_timestamp即可
pts = ts3.to_period()
print(pts)
print(pts.to_timestamp(how='end'))
data = pd.read_csv('/home/jethro/文档/pydata-book-master/data/macrodata.csv')
print(data.year)
print(data.quarter)
#将这两个数组以及一个频率传入PeriodIndex，就可以将它们合并成DataFrame的一个索引
index = pd.PeriodIndex(year=data.year, quarter=data.quarter, freq='Q-DEC')
p4pm = (p.asfreq('B', 'e') - 1).asfreq('T', 's') + 16 * 60
print(p4pm)
rng = pd.period_range('2011Q3', '2012Q4', freq='Q-JAN')
ts = Series(np.arange(len(rng)), index=rng)
print(ts)
new_rng = (rng.asfreq('B', 'e') - 1).asfreq('T', 's') + 16 * 60
ts.index = new_rng.to_timestamp()
print("This is ts", ts)
# 11.5.3将时间戳转换为区间（以及逆转换）
rng = pd.date_range('2000-01-01', periods=3, freq='M')
ts = Series(np.random.randn(len(rng)), index=rng)
print(ts)
pts = ts.to_period()
print(pts)
rng = pd.date_range('1/29/2000', periods=6, freq='D')
ts2 = Series(np.random.randn(6), index=rng)
print(ts2)
print(ts2.to_period('M'))
pts = ts2.to_period()
print(pts)
print(pts.to_timestamp(how='end'))
# 11.5.4从数组生成PeriodIndex
data = pd.read_csv(
'D:\\test\\pydata-book-2nd-edition\\examples\\macrodata.csv')
pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)
from pandas import DataFrame,Series
import pandas as pd
import numpy as np
res = pd.read_table('equity_funds_ret.txt',sep='\s+',skiprows=[1,2])
funds = list(pd.value_counts(res['wficn']).index)
# funds.remove(100218)
min_date = 20160331
max_date = 20160331
# for fundID in funds:
# temp = res[res['wficn']==fundID].values[0,1] #这里索引不太对
# if temp < min_date:
# min_date = temp
min_date = 19611229
date_index = pd.period_range(start=str(int(min_date)),end=str(int(max_date)),freq='M')
data = DataFrame(None,index = date_index,columns=funds)
for fundID in funds:
temp = res[res['wficn']==fundID]
temp = temp.dropna()
temp_dateIndex = pd.to_datetime(temp['date'],format = '%Y%m%d')
temp_series = Series(temp['ret'].values,index = temp_dateIndex)
temp_series = temp_series.to_period(freq='M')
data[fundID] = temp_series
data.to_csv('fund_return.csv')
#按季度计算的时期频率
#表示该财年以2012年的1月作为结尾，所以第四季度2012Q4是从2011年11月到2012年1月
p3 = pd.Period('2012Q4', freq='Q-JAN')
#获取该季度倒是第二个工作日下午4点的时间戳
p4pm = (p.asfreq('B', 'e') - 1).asfreq('T', 's') + 16 * 60
#转为Timestamp
p4pm.to_timestamp()
#生成季度性范围
pr1 = pd.period_range('2011Q3', '2012Q4', freq='Q-JAN')
ts4 = Series(np.arange(len(pr1)), index=pr1)
#将Timestamp转为Period
pr2 = pd.date_range('1/1/2000', periods=3, freq='M')
ts5 = Series(np.random.randn(3), index=pr2)
#将由时间戳作为索引的Series或DataFrame转换为以时期索引
ts5.to_period()
#转为时间戳
ts5.to_timestamp()
#频率由日变为月
pr3 = pd.date_range('1/29/2000', periods=6, freq='D')
ts6 = Series(np.random.randn(6), index=pr3)
#新的频率默认由时间戳推断而来，所以会出现重复的时期
ts6.to_period('M')
#通过数组创建PeriodIndex
#这个数据集中年度和季度被存放在不同列中，现在要把这两列合并
data = pd.read_csv('macrodata.csv')
#将这两个数组以及一个频率传入PeriodIndex，就可以合成DataFrame的一个索引
index9 = pd.PeriodIndex(year=data.year, quarter=data.quarter, freq='Q-DEC')
data.index = index9
# In[180]:
rng
# In[181]:
ts = Series(np.random.randn(3), index=rng)
# In[182]:
ts
# In[183]:
pts = ts.to_period()
# In[184]:
pts
# 时期指的是非重叠区间，因此对于给定的频率，一个时间戳只能属于一个时期
# In[185]:
rng = pd.date_range('1/29/2000', periods=6, freq='D')
# In[186]:
rng
# * to_period() <==> to_timestamp()
# In[ ]:
rng = pd.date_range('1/1/2000', periods=3, freq='M')
ts = Series(randn(3), index=rng)
ts
# #### # to_period()에 의해 변환되는 빈도(freq.)는 추정된다
# In[ ]:
pts = ts.to_period()
pts
# #### # 빈도를 지정할 수도 있음
# * 중복되는 시간 인덱스가 나타날 수 있음
# In[ ]:
rng = pd.date_range('1/29/2000', periods=6, freq='D')
ts2 = Series(randn(6), index=rng)
ts2
ts2.to_period('M')
print(now + MonthEnd())
print(now + MonthEnd(2))
offset = MonthEnd()
print(offset.rollforward(now))
print(offset.rollback(now))
ts = Series(np.random.randn(20),
index=pd.date_range('1/15/2000', periods=20, freq='4d'))
print(ts)
print(ts.groupby(offset.rollforward).mean())
print(ts.resample('M').mean())
rng = pd.date_range('1/1/2000', periods=3, freq='M')
ts = Series(np.random.randn(3), index=rng)
pts = ts.to_period()
print(ts)
print(pts)
rng = pd.date_range('1/29/2000', periods=6, freq='D')
ts2 = Series(np.random.randn(6), index=rng)
print(ts2.to_period('M'))
pts = ts.to_period()
print(pts)
print(pts.to_timestamp(how='end'))
data = pd.read_csv('macrodata.csv')
print(data.year)
print(data.quarter)
index = pd.PeriodIndex(year=data.year, quarter=data.quarter, freq='Q-DEC')
