CH06 -Pandas 【综合练习】

• 时间紧张，先搞这么多吧，后便继续

import numpy as np
import pandas as pd

df = pd.read_csv('C:/Users/admin/Desktop/joyful-pandas-master/数据集/2002年-2018年上海机动车拍照拍卖.csv')
df.head()

	Date	Total number of license issued	lowest price	avg price	Total number of applicants
0	2-Jan	1400	13600	14735	3718
1	2-Feb	1800	13100	14057	4590
2	2-Mar	2000	14300	14662	5190
3	2-Apr	2300	16000	16334	4806
4	2-May	2350	17800	18357	4665

s = pd.Series(df['Total number of license issued']/df['Total number of applicants'])
df_assign=df.assign(Quali=s)
df_assign

	Date	Total number of license issued	lowest price	avg price	Total number of applicants	Quali
0	2-Jan	1400	13600	14735	3718	0.376547
1	2-Feb	1800	13100	14057	4590	0.392157
2	2-Mar	2000	14300	14662	5190	0.385356
3	2-Apr	2300	16000	16334	4806	0.478568
4	2-May	2350	17800	18357	4665	0.503751
...	...	...	...	...	...	...
198	18-Aug	10402	88300	88365	192755	0.053965
199	18-Sep	12712	87300	87410	189142	0.067209
200	18-Oct	10728	88000	88070	181861	0.058990
201	18-Nov	11766	87300	87374	177355	0.066342
202	18-Dec	12850	87400	87508	165442	0.077671

203 rows × 6 columns

df_assign.loc[df_assign['Quali']>0.5].head(1).Date

4    2-May
Name: Date, dtype: object

df_1 = df.copy()
df_1

	Date	Total number of license issued	lowest price	avg price	Total number of applicants
0	2-Jan	1400	13600	14735	3718
1	2-Feb	1800	13100	14057	4590
2	2-Mar	2000	14300	14662	5190
3	2-Apr	2300	16000	16334	4806
4	2-May	2350	17800	18357	4665
...	...	...	...	...	...
198	18-Aug	10402	88300	88365	192755
199	18-Sep	12712	87300	87410	189142
200	18-Oct	10728	88000	88070	181861
201	18-Nov	11766	87300	87374	177355
202	18-Dec	12850	87400	87508	165442

203 rows × 5 columns

df_1['Year'] = df_1['Date'].apply(lambda x : 2000+int(x.split('-')[0]))
df_1['Month'] = df_1['Date'].apply(lambda x : x.split('-')[1])

col_name=df_1.columns.tolist()
col_name

['Date',
 'Total number of license issued',
 'lowest price ',
 'avg price',
 'Total number of applicants',
 'Year',
 'Month']

df_1 =