【数据分析可视化】时间序列操作基础

import numpy as np
import pandas as pd
from pandas import Series,DataFrame

# 引入 创建时间序列
from datetime import datetime
t1 = datetime(2009, 10, 20)
t1

datetime.datetime(2009, 10, 20, 0, 0)

# 列表创建时间序列
date_list = [
    datetime(2016,2,4),
    datetime(2016,9,4),
    datetime(2016,10,4),
    datetime(2017,7,4),
    datetime(2017,9,4),
    datetime(2017,10,4)
]
date_list

[datetime.datetime(2016, 2, 4, 0, 0),
 datetime.datetime(2016, 9, 4, 0, 0),
 datetime.datetime(2016, 10, 4, 0, 0),
 datetime.datetime(2017, 7, 4, 0, 0),
 datetime.datetime(2017, 9, 4, 0, 0),
 datetime.datetime(2017, 10, 4, 0, 0)]

# 将时间变为索引
s1 = Series(np.random.rand(6), index=date_list)
s1

2016-02-04    0.971295
2016-09-04    0.085970
2016-10-04    0.117683
2017-07-04    0.891225
2017-09-04    0.922458
2017-10-04    0.346875
dtype: float64

s1.values

array([0.97129488, 0.08596965, 0.11768269, 0.89122463, 0.92245809,
       0.34687534])

s1.index

DatetimeIndex(['2016-02-04', '2016-09-04', '2016-10-04', '2017-07-04',
               '2017-09-04', '2017-10-04'],
              dtype='datetime64[ns]', freq=None)

# 通过index位置 返回数据值
s1[1]

0.08596964757361214

# 通过datetime 数据类型 返回信息
s1[datetime(2016,2,4)]

0.9712948753332638

s1['2016-2-4']

0.9712948753332638

s1['20160204']

0.9712948753332638

s1['2016-02']

2016-02-04    0.971295
dtype: float64

s1['2016']

2016-02-04    0.971295
2016-09-04    0.085970
2016-10-04    0.117683
dtype: float64

# 能够产生一段时间以内的datetime的方法(起止 间隔 步长默认d天W。周日开始周一结束,W-MON变为正常周)
date_list_new = pd.date_range('2016-02-04',periods=100, freq='W-MON')
date_list_new

DatetimeIndex(['2016-02-08', '2016-02-15', '2016-02-22', '2016-02-29',
               '2016-03-07', '2016-03-14', '2016-03-21', '2016-03-28',
               '2016-04-04', '2016-04-11', '2016-04-18', '2016-04-25',
               '2016-05-02', '2016-05-09', '2016-05-16', '2016-05-23',
               '2016-05-30', '2016-06-06', '2016-06-13', '2016-06-20',
               '2016-06-27', '2016-07-04', '2016-07-11', '2016-07-18',
               '2016-07-25', '2016-08-01', '2016-08-08', '2016-08-15',
               '2016-08-22', '2016-08-29', '2016-09-05', '2016-09-12',
               '2016-09-19', '2016-09-26', '2016-10-03', '2016-10-10',
               '2016-10-17', '2016-10-24', '2016-10-31', '2016-11-07',
               '2016-11-14', '2016-11-21', '2016-11-28', '2016-12-05',
               '2016-12-12', '2016-12-19', '2016-12-26', '2017-01-02',
               '2017-01-09', '2017-01-16', '2017-01-23', '2017-01-30',
               '2017-02-06', '2017-02-13', '2017-02-20', '2017-02-27',
               '2017-03-06', '2017-03-13', '2017-03-20', '2017-03-27',
               '2017-04-03', '2017-04-10', '2017-04-17', '2017-04-24',
               '2017-05-01', '2017-05-08', '2017-05-15', '2017-05-22',
               '2017-05-29', '2017-06-05', '2017-06-12', '2017-06-19',
               '2017-06-26', '2017-07-03', '2017-07-10', '2017-07-17',
               '2017-07-24', '2017-07-31', '2017-08-07', '2017-08-14',
               '2017-08-21', '2017-08-28', '2017-09-04', '2017-09-11',
               '2017-09-18', '2017-09-25', '2017-10-02', '2017-10-09',
               '2017-10-16', '2017-10-23', '2017-10-30', '2017-11-06',
               '2017-11-13', '2017-11-20', '2017-11-27', '2017-12-04',
               '2017-12-11', '2017-12-18', '2017-12-25', '2018-01-01'],
              dtype='datetime64[ns]', freq='W-MON')

s2 = Series(np.random.rand(100),index=date_list_new)
s2

2016-02-08    0.828582
2016-02-15    0.348196
2016-02-22    0.012437
2016-02-29    0.148311
2016-03-07    0.021719
                ...   
2017-12-04    0.345226
2017-12-11    0.945203
2017-12-18    0.069342
2017-12-25    0.134574
2018-01-01    0.975369
Freq: W-MON, Length: 100, dtype: float64