Pandas的时间序列处理

创建



from datetime import datetime
import pandas as pd
import numpy as np

# 指定index为datetime的list
date_list = [datetime(2017, 2, 18), datetime(2017, 2, 19), 
             datetime(2017, 2, 25), datetime(2017, 2, 26), 
             datetime(2017, 3, 4), datetime(2017, 3, 5)]
time_s = pd.Series(np.random.randn(6), index=date_list)
print(time_s)
print(type(time_s.index))

2017-02-18   -0.543551
2017-02-19   -0.759103
2017-02-25    0.058956
2017-02-26    0.275448
2017-03-04   -0.957346
2017-03-05   -1.143108
dtype: float64
<class 'pandas.tseries.index.DatetimeIndex'>
<class 'pandas.core.series.Series'>



索引







过滤



生成日期范围







频率与偏移量



print(pd.date_range('2017/02/18', '2017/03/18', freq='2D'))

# 偏移量通过加法连接
sum_offset = pd.tseries.offsets.Week(2) + pd.tseries.offsets.Hour(12)
print(sum_offset)

print(pd.date_range('2017/02/18', '2017/03/18', freq=sum_offset))

DatetimeIndex(['2017-02-18', '2017-02-20', '2017-02-22', '2017-02-24',
               '2017-02-26', '2017-02-28', '2017-03-02', '2017-03-04',
               '2017-03-06', '2017-03-08', '2017-03-10', '2017-03-12',
               '2017-03-14', '2017-03-16', '2017-03-18'],
              dtype='datetime64[ns]', freq='2D')
              
14 days 12:00:00
DatetimeIndex(['2017-02-18 00:00:00', '2017-03-04 12:00:00'], dtype='datetime64[ns]', freq='348H')





移动数据




时间周期计算