# 六、日期时间预处理

## 把日期和时间拆成多个特征

``````# 加载库
import pandas as pd

# 创建数据帧
df = pd.DataFrame()

# 创建五个日期
df['date'] = pd.date_range('1/1/2001', periods=150, freq='W')

# 为年月日，时分秒创建特征
df['year'] = df['date'].dt.year
df['month'] = df['date'].dt.month
df['day'] = df['date'].dt.day
df['hour'] = df['date'].dt.hour
df['minute'] = df['date'].dt.minute

# 展示三行
``````
date year month day hour minute
0 2001-01-07 2001 1 7 0 0
1 2001-01-14 2001 1 14 0 0
2 2001-01-21 2001 1 21 0 0

## 计算日期时间之间的差

``````# 加载库
import pandas as pd

# 创建数据帧
df = pd.DataFrame()

# 创建两个 datetime 特征
df['Arrived'] = [pd.Timestamp('01-01-2017'), pd.Timestamp('01-04-2017')]
df['Left'] = [pd.Timestamp('01-01-2017'), pd.Timestamp('01-06-2017')]

# 计算特征之间的间隔
df['Left'] - df['Arrived']

'''
0   0 days
1   2 days
dtype: timedelta64[ns]
'''

# 计算特征之间的间隔
pd.Series(delta.days for delta in (df['Left'] - df['Arrived']))

'''
0    0
1    2
dtype: int64
'''
``````

## 将字符串转换为日期

``````# 加载库
import numpy as np
import pandas as pd

# 创建字符串
date_strings = np.array(['03-04-2005 11:35 PM',
'23-05-2010 12:01 AM',
'04-09-2009 09:09 PM'])
``````

`%Y` 整年 `2001`
`%m` 零填充的月份 `04`
`%d` 零填充的日期 `09`
`%I` 零填充的小时（12 小时） `02`
`%p` AM 或 PM `AM`
`%M` 零填充的分钟 `05`
`%S` 零填充的秒钟 `09`
``````# 转换为 datetime
[pd.to_datetime(date, format="%d-%m-%Y %I:%M %p", errors="coerce") for date in date_strings]

'''
[Timestamp('2005-04-03 23:35:00'),
Timestamp('2010-05-23 00:01:00'),
Timestamp('2009-09-04 21:09:00')]
'''
``````

## 转换 pandas 列的时区

``````# 加载库
import pandas as pd
from pytz import all_timezones

# 展示十个时区
all_timezones[0:10]

'''
['Africa/Abidjan',
'Africa/Accra',
'Africa/Algiers',
'Africa/Asmara',
'Africa/Asmera',
'Africa/Bamako',
'Africa/Bangui',
'Africa/Banjul',
'Africa/Bissau']
'''

# 创建十个日期
dates = pd.Series(pd.date_range('2/2/2002', periods=10, freq='M'))

# 设置时区
dates_with_abidjan_time_zone = dates.dt.tz_localize('Africa/Abidjan')

# 查看 pandas 序列
dates_with_abidjan_time_zone

'''
0   2002-02-28 00:00:00+00:00
1   2002-03-31 00:00:00+00:00
2   2002-04-30 00:00:00+00:00
3   2002-05-31 00:00:00+00:00
4   2002-06-30 00:00:00+00:00
5   2002-07-31 00:00:00+00:00
6   2002-08-31 00:00:00+00:00
7   2002-09-30 00:00:00+00:00
8   2002-10-31 00:00:00+00:00
9   2002-11-30 00:00:00+00:00
dtype: datetime64[ns, Africa/Abidjan]
'''

# 转换时区
dates_with_london_time_zone = dates_with_abidjan_time_zone.dt.tz_convert('Europe/London')

# 查看 pandas 序列
dates_with_london_time_zone

'''
0   2002-02-28 00:00:00+00:00
1   2002-03-31 00:00:00+00:00
2   2002-04-30 01:00:00+01:00
3   2002-05-31 01:00:00+01:00
4   2002-06-30 01:00:00+01:00
5   2002-07-31 01:00:00+01:00
6   2002-08-31 01:00:00+01:00
7   2002-09-30 01:00:00+01:00
8   2002-10-31 00:00:00+00:00
9   2002-11-30 00:00:00+00:00
dtype: datetime64[ns, Europe/London]
'''
``````

## 编码星期

``````# 加载库
import pandas as pd

# 创建数据集
dates = pd.Series(pd.date_range('2/2/2002', periods=3, freq='M'))

# 查看数据
dates

'''
0   2002-02-28
1   2002-03-31
2   2002-04-30
dtype: datetime64[ns]
'''

# 查看星期
dates.dt.weekday_name

'''
0    Thursday
1      Sunday
2     Tuesday
dtype: object
'''
``````

## 处理时间序列中的缺失值

``````# 加载库
import pandas as pd
import numpy as np

# 创建日期
time_index = pd.date_range('01/01/2010', periods=5, freq='M')

# 创建数据帧，设置索引
df = pd.DataFrame(index=time_index)

# 创建带有一些缺失值的特征
df['Sales'] = [1.0,2.0,np.nan,np.nan,5.0]

# 对缺失值执行插值
df.interpolate()
``````
Sales
2010-01-31 1.0
2010-02-28 2.0
2010-03-31 3.0
2010-04-30 4.0
2010-05-31 5.0
``````# 前向填充
df.ffill()
``````
Sales
2010-01-31 1.0
2010-02-28 2.0
2010-03-31 2.0
2010-04-30 2.0
2010-05-31 5.0
``````# 后向填充
df.bfill()
``````
Sales
2010-01-31 1.0
2010-02-28 2.0
2010-03-31 5.0
2010-04-30 5.0
2010-05-31 5.0
``````# 对缺失值执行插值
df.interpolate(limit=1, limit_direction='forward')
``````
Sales
2010-01-31 1.0
2010-02-28 2.0
2010-03-31 3.0
2010-04-30 NaN
2010-05-31 5.0

## 处理时区

``````# 加载库
import pandas as pd
from pytz import all_timezones

# 展示十个时区
all_timezones[0:10]

'''
['Africa/Abidjan',
'Africa/Accra',
'Africa/Algiers',
'Africa/Asmara',
'Africa/Asmera',
'Africa/Bamako',
'Africa/Bangui',
'Africa/Banjul',
'Africa/Bissau']
'''

# 创建 datetime
pd.Timestamp('2017-05-01 06:00:00', tz='Europe/London')

# Timestamp('2017-05-01 06:00:00+0100', tz='Europe/London')

# 创建 datetime
date = pd.Timestamp('2017-05-01 06:00:00')

# 设置时区
date_in_london = date.tz_localize('Europe/London')

# 修改时区
date_in_london.tz_convert('Africa/Abidjan')

# Timestamp('2017-05-01 05:00:00+0000', tz='Africa/Abidjan')
``````

## 平移时间特征

``````# 加载库
import pandas as pd

# 创建数据帧
df = pd.DataFrame()

# 创建数据
df['dates'] = pd.date_range('1/1/2001', periods=5, freq='D')
df['stock_price'] = [1.1,2.2,3.3,4.4,5.5]

# 将值平移一行
df['previous_days_stock_price'] = df['stock_price'].shift(1)

# 展示数据帧
df
``````
dates stock_price previous_days_stock_price
0 2001-01-01 1.1 NaN
1 2001-01-02 2.2 1.1
2 2001-01-03 3.3 2.2
3 2001-01-04 4.4 3.3
4 2001-01-05 5.5 4.4

## 滑动时间窗口

``````# 加载库
import pandas as pd

# 创建 datetime
time_index = pd.date_range('01/01/2010', periods=5, freq='M')

# 创建数据帧，设置索引
df = pd.DataFrame(index=time_index)

# 创建特征
df['Stock_Price'] = [1,2,3,4,5]

# 计算滑动均值
df.rolling(window=2).mean()
``````
Stock_Price
2010-01-31 NaN
2010-02-28 1.5
2010-03-31 2.5
2010-04-30 3.5
2010-05-31 4.5
``````# 识别滑动时间窗口中的最大值
df.rolling(window=2).max()
``````
Stock_Price
2010-01-31 NaN
2010-02-28 2.0
2010-03-31 3.0
2010-04-30 4.0
2010-05-31 5.0

## 选择日期时间范围

``````# 加载库
import pandas as pd

# 创建数据帧
df = pd.DataFrame()

# 创建 datetime
df['date'] = pd.date_range('1/1/2001', periods=100000, freq='H')
``````

``````# 选择两个日期时间之间的观测
df[(df['date'] > '2002-1-1 01:00:00') & (df['date'] <= '2002-1-1 04:00:00')]
``````
date
8762 2002-01-01 02:00:00
8763 2002-01-01 03:00:00
8764 2002-01-01 04:00:00

``````# 设置索引
df = df.set_index(df['date'])

# 选择两个日期时间之间的观测
df.loc['2002-1-1 01:00:00':'2002-1-1 04:00:00']
``````
date
date
2002-01-01 01:00:00 2002-01-01 01:00:00
2002-01-01 02:00:00 2002-01-01 02:00:00
2002-01-01 03:00:00 2002-01-01 03:00:00
2002-01-01 04:00:00 2002-01-01 04:00:00