本章内容包括：更改时间字段

//input1
import pandas as pd
import numpy as np
columns = ['user_id','order_dt','order_products','order_amount']
df = pd.read_table('CDNOW_master.txt',names = columns,sep = '\s+')
//markdown user_id:用户ID
//markdown order_dt:购买日期
//markdown orderproducts:购买产品数
//markdown order_amount:购买金额
df.head()


//output1
user_id order_dt    order_products  order_amount
0   1   19970101    1   11.77
1   2   19970112    1   12.00
2   2   19970112    5   77.00
3   3   19970102    2   20.76
4   3   19970330    2   20.76








//input2
df.info()



//output2
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 69659 entries, 0 to 69658
Data columns (total 4 columns):
user_id           69659 non-null int64
order_dt          69659 non-null int64
order_products    69659 non-null int64
order_amount      69659 non-null float64
dtypes: float64(1), int64(3)
memory usage: 2.1 MB








//input3
df['order_dt'] = pd.to_datetime(df.order_dt,format='%Y%m%d')
df['month'] = df.order_dt.values.astype('datetime64[M]')
df.info()


//output3
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 69659 entries, 0 to 69658
Data columns (total 5 columns):
user_id           69659 non-null int64
order_dt          69659 non-null datetime64[ns]
order_products    69659 non-null int64
order_amount      69659 non-null float64
month             69659 non-null datetime64[ns]
dtypes: datetime64[ns](2), float64(1), int64(2)
memory usage: 2.7 MB








//input4
df.head()



//output4
    user_id order_dt    order_products  order_amount    month
0   1   1997-01-01  1   11.77   1997-01-01
1   2   1997-01-12  1   12.00   1997-01-01
2   2   1997-01-12  5   77.00   1997-01-01
3   3   1997-01-02  2   20.76   1997-01-01
4   3   1997-03-30  2   20.76   1997-03-01