8 pandas实战-美国大选数据分析

import numpy as np
import pandas as pd
#方便大家操作，将月份和参选人以及所在政党进行定义：
months = {'JAN' : 1, 'FEB' : 2, 'MAR' : 3, 'APR' : 4, 'MAY' : 5, 'JUN' : 6,
          'JUL' : 7, 'AUG' : 8, 'SEP' : 9, 'OCT': 10, 'NOV': 11, 'DEC' : 12}
of_interest = ['Obama, Barack', 'Romney, Mitt', 'Santorum, Rick', 
               'Paul, Ron', 'Gingrich, Newt']
parties = {
  'Bachmann, Michelle': 'Republican',
  'Romney, Mitt': 'Republican',
  'Obama, Barack': 'Democrat',
  "Roemer, Charles E. 'Buddy' III": 'Reform',
  'Pawlenty, Timothy': 'Republican',
  'Johnson, Gary Earl': 'Libertarian',
  'Paul, Ron': 'Republican',
  'Santorum, Rick': 'Republican',
  'Cain, Herman': 'Republican',
  'Gingrich, Newt': 'Republican',
  'McCotter, Thaddeus G': 'Republican',
  'Huntsman, Jon': 'Republican',
  'Perry, Rick': 'Republican'           
 }

需求

加载数据
查看数据的基本信息
指定数据截取，将如下字段的数据进行提取，其他数据舍弃
- cand_nm ：候选人姓名
- contbr_nm ：捐赠人姓名
- contbr_st ：捐赠人所在州
- contbr_employer ：捐赠人所在公司
- contbr_occupation ：捐赠人职业
- contb_receipt_amt ：捐赠数额（美元）
- contb_receipt_dt ：捐款的日期
对新数据进行总览,查看是否存在缺失数据
用统计学指标快速描述数值型属性的概要。
空值处理。可能因为忘记填写或者保密等等原因，相关字段出现了空值，将其填充为NOT PROVIDE
异常值处理。将捐款金额<=0的数据删除
新建一列为各个候选人所在党派party
查看party这一列中有哪些不同的元素
统计party列中各个元素出现次数
查看各个党派收到的政治献金总数contb_receipt_amt
查看具体每天各个党派收到的政治献金总数contb_receipt_amt
将表中日期格式转换为'yyyy-mm-dd'。
查看老兵(捐献者职业)DISABLED VETERAN主要支持谁

df = pd.read_csv('./data/usa_election.txt')
df

/Users/bobo/anaconda3/lib/python3.6/site-packages/IPython/core/interactiveshell.py:2785: DtypeWarning: Columns (6) have mixed types. Specify dtype option on import or set low_memory=False.
  interactivity=interactivity, compiler=compiler, result=result)

	cmte_id	cand_id	cand_nm	contbr_nm	contbr_city	contbr_st	contbr_zip	contbr_employer	contbr_occupation	contb_receipt_amt	contb_receipt_dt	receipt_desc	memo_cd	memo_text	form_tp	file_num
0	C00410118	P20002978	Bachmann, Michelle	HARVEY, WILLIAM	MOBILE	AL	3.6601e+08	RETIRED	RETIRED	250.0	20-JUN-11	NaN	NaN	NaN	SA17A	736166
1	C00410118	P20002978	Bachmann, Michelle	HARVEY, WILLIAM	MOBILE	AL	3.6601e+08	RETIRED	RETIRED	50.0	23-JUN-11	NaN	NaN	NaN	SA17A	736166
2	C00410118	P20002978	Bachmann, Michelle	SMITH, LANIER	LANETT	AL	3.68633e+08	INFORMATION REQUESTED	INFORMATION REQUESTED	250.0	05-JUL-11	NaN	NaN	NaN	SA17A	749073
3	C00410118	P20002978	Bachmann, Michelle	BLEVINS, DARONDA	PIGGOTT	AR	7.24548e+08	NONE	RETIRED	250.0	01-AUG-11	NaN	NaN	NaN	SA17A	749073
4	C00410118	P20002978	Bachmann, Michelle	WARDENBURG, HAROLD	HOT SPRINGS NATION	AR	7.19016e+08	NONE	RETIRED	300.0	20-JUN-11	NaN	NaN	NaN	SA17A	736166
5	C00410118	P20002978	Bachmann, Michelle	BECKMAN, JAMES	SPRINGDALE	AR	7.27647e+08	NONE	RETIRED	500.0	23-JUN-11	NaN	NaN	NaN	SA17A	736166
6	C00410118	P20002978	Bachmann, Michelle	BLEVINS, DARONDA	PIGGOTT	AR	7.24548e+08	INFORMATION REQUESTED	INFORMATION REQUESTED	250.0	21-JUN-11	NaN	NaN	NaN	SA17A	736166
7	C00410118	P20002978	Bachmann, Michelle	BLEVINS, DARONDA	PIGGOTT	AR	7.24548e+08	NONE	RETIRED	250.0	05-JUL-11	NaN	NaN	NaN	SA17A	749073
8	C00410118	P20002978	Bachmann, Michelle	COLLINS, SARAH	MESA	AZ	8.52107e+08	ST. JOSEPH HOSPITAL	RN	250.0	21-JUN-11	NaN	NaN	NaN	SA17A	736166
9	C00410118	P20002978	Bachmann, Michelle	COLEMAN, RONALD	TUCSON	AZ	8.57499e+08	RAYTHEON	ELECTRICAL ENGINEER	250.0	20-JUN-11	NaN	NaN	NaN	SA17A	736166
10	C00410118	P20002978	Bachmann, Michelle	ATCHLEY, JR, KEITH	MESA	AZ	85215	NONE	RETIRED	250.0	22-JUN-11	NaN	NaN	NaN	SA17A	736166
11	C00410118	P20002978	Bachmann, Michelle	FARNSWORTH, ROSS	MESA	AZ	8.52062e+08	FARNSWORTH COMPANIES	LAND DEVELOPER	500.0	22-JUN-11	NaN	NaN	NaN	SA17A	736166
12	C00410118	P20002978	Bachmann, Michelle	PRESTON, CLIFFORD	ORO VALLEY	AZ	8.57379e+08	INFORMATION REQUESTED	INFORMATION REQUESTED	250.0	21-JUN-11	NaN	NaN	NaN	SA17A	736166
13	C00410118	P20002978	Bachmann, Michelle	WILSON, RICHARD	FLAGSTAFF	AZ	8.60011e+08	NONE	RETIRED	500.0	17-JUN-11	NaN	NaN	NaN	SA17A	736166
14	C00410118	P20002978	Bachmann, Michelle	MILLER, WILLIAM	SCOTTSDALE	AZ	8.52513e+08	INFORMATION REQUESTED	INFORMATION REQUESTED	250.0	11-JUL-11	NaN	NaN	NaN	SA17A	749073
15	C00410118	P20002978	Bachmann, Michelle	DOLAN, WILLIAM	PHOENIX	AZ	8.50145e+08	VA MEDICAL CENTER	PHYSICIAN	300.0	08-JUL-11	NaN	NaN	NaN	SA17A	749073
16	C00410118	P20002978	Bachmann, Michelle	REULING, RICHARD	GREEN VALLEY	AZ	8.56225e+08	NONE	RETIRED	1000.0	05-JUL-11	NaN	NaN	NaN	SA17A	749073
17	C00410118	P20002978	Bachmann, Michelle	PETERSEN, W	GILBERT	AZ	85295	INFORMATION REQUESTED	INFORMATION REQUESTED	250.0	27-JUN-11	NaN	NaN	NaN	SA17A	736166
18	C00410118	P20002978	Bachmann, Michelle	ALLUMBAUGH, KATHY	SANTA ANA	CA	9.27051e+08	NONE	RETIRED	250.0	13-JUN-11	NaN	NaN	NaN	SA17A	736166
19	C00410118	P20002978	Bachmann, Michelle	DEL POZO, JOSE	DEL MAR	CA	9.20143e+08	RETIRES	RETIRED	300.0	16-JUN-11	NaN	NaN	NaN	SA17A	736166
20	C00410118	P20002978	Bachmann, Michelle	KIEFFER, PIERRE	SACRAMENTO	CA	9.58257e+08	SELF	OFFICE FURNITURE BROKER	500.0	16-JUN-11	NaN	NaN	NaN	SA17A	736166
21	C00410118	P20002978	Bachmann, Michelle	HANNAH, STEPHEN	SHERMAN OAKS	CA	9.14132e+08	RETIRED	RETIRED	250.0	16-JUN-11	NaN	NaN	NaN	SA17A	736166
22	C00410118	P20002978	Bachmann, Michelle	MINNIS, RITA	MILPITAS	CA	9.50358e+08	MILPITS MATERIALS	MANAGER	2500.0	17-JUN-11	NaN	NaN	NaN	SA17A	736166
23	C00410118	P20002978	Bachmann, Michelle	MINNIS, RITA	MILPITAS	CA	9.50358e+08	MILPITS MATERIALS	MANAGER	2500.0	17-JUN-11	NaN	NaN	NaN	SA17A	736166
24	C00410118	P20002978	Bachmann, Michelle	BOSTON, JOYCE	RANCHO CUCAMONGA	CA	9.17305e+08	INFORMATION REQUESTED	INFORMATION REQUESTED	300.0	18-JUL-11	NaN	NaN	NaN	SA17A	749073
25	C00410118	P20002978	Bachmann, Michelle	MANSFIELD, LORNA	WALNUT CREEK	CA	9.45952e+08	NONE	RETIRED	100.0	18-JUL-11	NaN	NaN	NaN	SA17A	749073
26	C00410118	P20002978	Bachmann, Michelle	EDWARDS, MARK	LA JOLLA	CA	9.20378e+08	NONE	RETIRED	150.0	05-AUG-11	NaN	NaN	NaN	SA17A	749073
27	C00410118	P20002978	Bachmann, Michelle	PECONI, GIANFRANCO	CEDAR GLEN	CA	9.23211e+08	INFORMATION REQUESTED	INFORMATION REQUESTED	250.0	01-JUL-11	NaN	NaN	NaN	SA17A	749073
28	C00410118	P20002978	Bachmann, Michelle	WILSON, CAROL R.	LINCOLN	CA	9.56488e+08	NONE	RETIRED	500.0	05-JUL-11	NaN	NaN	NaN	SA17A	749073
29	C00410118	P20002978	Bachmann, Michelle	CASTAGNOZZI, MARY	PIEDMONT	CA	9.46114e+08	PIEDMONT LAUNGUAGE SCHOOL	MANDARIN TEACHER	250.0	05-JUL-11	NaN	NaN	NaN	SA17A	749073
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
536011	C00500587	P20003281	Perry, Rick	ZATEZALO, DAVID G. MR.	WHEELING	WV	260036639	RHINO RESOURCES	COAL MINER	2500.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536012	C00500587	P20003281	Perry, Rick	THALMAN, FRANK E. MR.	WHEELING	WV	260031672	WARWOOD ARMATURE REPAIR COMPANY	VICE PRESIDENT	2500.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536013	C00500587	P20003281	Perry, Rick	THALMAN, RAYMOND V. MR. III	WHEELING	WV	260030401	WARWOOD ARMATURE REPAIR COMPANY	PRESIDENT	2500.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536014	C00500587	P20003281	Perry, Rick	TEMPLIN, JOE MR.	WHEELING	WV	260034922	THE OHIO VALLEY COAL COMPANY	MANAGER OF INFORMATION SYSTEMS	250.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536015	C00500587	P20003281	Perry, Rick	WOISNET, JILL MRS.	MORGANTOWN	WV	265088649	SWANSON INDUSTRIES INC	VP	2500.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536016	C00500587	P20003281	Perry, Rick	WOISNET, LEX MR.	MORGANTOWN	WV	265088649	SWANSON INDUSTRIES INC.	PURCHASING MANAGER	2500.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536017	C00500587	P20003281	Perry, Rick	WHITT, RICHARD P. MR.	WHEELING	WV	260036021	IVALDET LABORATORIES	EXECUTIVE	300.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536018	C00500587	P20003281	Perry, Rick	WHITESCARVER, IDALEE MRS.	GRAFTON	WV	263549310	QUALITY HYDRAULICS INC.	SECRETARY TO VICE PRESIDENT	2500.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536019	C00500587	P20003281	Perry, Rick	WHITESCARVER, JOHN E. MR.	GRAFTON	WV	263549310	QUALITY HYDRAULICS INC.	PRESIDENT/TREASURER	2500.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536020	C00500587	P20003281	Perry, Rick	FRIESS, STEPHEN MR.	JACKSON	WY	830021655	FRIESS INC.	CONSULTANT	1000.0	29-SEP-11	NaN	NaN	NaN	SA17A	751678
536021	C00500587	P20003281	Perry, Rick	HANSEN, STEVE MR.	CHEYENNE	WY	820013163	TEXAS ENERGY LLC	EXECUTIVE	250.0	15-NOV-11	NaN	X	SEE ATTRIBUTION	SA17A	761750
536022	C00500587	P20003281	Perry, Rick	HARDER, ROBERT	POWELL	WY	824359238	NaN	RETIRED	100.0	29-OCT-11	NaN	NaN	NaN	SA17A	761750
536023	C00500587	P20003281	Perry, Rick	HARDER, ROBERT	POWELL	WY	824359238	NaN	RETIRED	100.0	12-NOV-11	NaN	NaN	NaN	SA17A	761750
536024	C00500587	P20003281	Perry, Rick	HARDER, ROBERT	POWELL	WY	824359238	NaN	RETIRED	100.0	30-NOV-11	NaN	NaN	NaN	SA17A	761750
536025	C00500587	P20003281	Perry, Rick	KINSEY, JOAN	LARAMIE	WY	820709758	RETIRED	RETIRED	1000.0	17-AUG-11	NaN	NaN	NaN	SA17A	751678
536026	C00500587	P20003281	Perry, Rick	SUGDEN, SUSAN MRS.	JACKSON	WY	830010489	SELF-EMPLOYED	INVESTOR	2500.0	26-AUG-11	NaN	NaN	NaN	SA17A	751678
536027	C00500587	P20003281	Perry, Rick	LUCAS, WES	TETON VILLAGE	WY	83025	SIRVA	CEO	2500.0	04-OCT-11	NaN	NaN	NaN	SA17A	761750
536028	C00500587	P20003281	Perry, Rick	LUCAS, ELISABET	TETON VILLAGE	WY	830250824	LUCAS PROPERTIES	OWNER	2500.0	04-OCT-11	NaN	NaN	NaN	SA17A	761750
536029	C00500587	P20003281	Perry, Rick	TEXAS ENERGY L.L.C.	CHEYENNE	WY	820013163	LLC	LLC	250.0	30-SEP-11	NaN	X	SEE ATTRIBUTION BELOW	SA17A	761750
536030	C00500587	P20003281	Perry, Rick	SPENCE, RUSSELL	RIVERTON	WY	825019711	INFORMATION REQUESTED PER BEST EFFORTS	INFORMATION REQUESTED PER BEST EFFORTS	250.0	15-AUG-11	NaN	NaN	NaN	SA17A	751678
536031	C00500587	P20003281	Perry, Rick	TEXAS ENERGY L.L.C.	CHEYENNE	WY	820013163	NaN	NaN	250.0	30-SEP-11	NaN	NaN	ATTRIBUTION TO PARTNERS REQUESTED	SA17A	751678
536032	C00500587	P20003281	Perry, Rick	SUGDEN, RICHARD G. MR.	JACKSON	WY	830010489	FAMILY PRACTICE ASSOCIATES	DOCTOR	2500.0	26-AUG-11	NaN	NaN	NaN	SA17A	751678
536033	C00500587	P20003281	Perry, Rick	HARDER, ROBERT	POWELL	WY	824359238	NaN	RETIRED	100.0	01-OCT-11	NaN	NaN	NaN	SA17A	761750
536034	C00500587	P20003281	Perry, Rick	ELWOOD, MIKE MR.	INFO REQUESTED	XX	99999	AM COAL	ENGINEER	2500.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536035	C00500587	P20003281	Perry, Rick	HEFFERNAN, JILL PRINCE MRS.	INFO REQUESTED	XX	99999	INFORMATION REQUESTED PER BEST EFFORTS	INFORMATION REQUESTED PER BEST EFFORTS	500.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536036	C00500587	P20003281	Perry, Rick	ANDERSON, MARILEE MRS.	INFO REQUESTED	XX	99999	INFORMATION REQUESTED PER BEST EFFORTS	INFORMATION REQUESTED PER BEST EFFORTS	2500.0	31-AUG-11	NaN	NaN	NaN	SA17A	751678
536037	C00500587	P20003281	Perry, Rick	TOLBERT, DARYL MR.	INFO REQUESTED	XX	99999	T.A.C.C.	LONGWALL MAINTENANCE FOREMAN	500.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536038	C00500587	P20003281	Perry, Rick	GRANE, BRYAN F. MR.	INFO REQUESTED	XX	99999	INFORMATION REQUESTED PER BEST EFFORTS	INFORMATION REQUESTED PER BEST EFFORTS	500.0	29-SEP-11	NaN	NaN	NaN	SA17A	751678
536039	C00500587	P20003281	Perry, Rick	DUFFY, DAVID A. MR.	INFO REQUESTED	XX	99999	DUFFY EQUIPMENT COMPANY INC.	BUSINESS OWNER	2500.0	30-SEP-11	NaN	NaN	NaN	SA17A	751678
536040	C00500587	P20003281	Perry, Rick	GORMAN, CHRIS D. MR.	INFO REQUESTED	XX	99999	INFORMATION REQUESTED PER BEST EFFORTS	INFORMATION REQUESTED PER BEST EFFORTS	5000.0	29-SEP-11	REATTRIBUTION / REDESIGNATION REQUESTED (AUTOM...	NaN	REATTRIBUTION / REDESIGNATION REQUESTED (AUTOM...	SA17A	751678

536041 rows × 16 columns

#对新数据进行总览,查看是否存在缺失数据
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 536041 entries, 0 to 536040
Data columns (total 16 columns):
cmte_id              536041 non-null object
cand_id              536041 non-null object
cand_nm              536041 non-null object
contbr_nm            536041 non-null object
contbr_city          536026 non-null object
contbr_st            536040 non-null object
contbr_zip           535973 non-null object
contbr_employer      525088 non-null object
contbr_occupation    530520 non-null object
contb_receipt_amt    536041 non-null float64
contb_receipt_dt     536041 non-null object
receipt_desc         8479 non-null object
memo_cd              49718 non-null object
memo_text            52740 non-null object
form_tp              536041 non-null object
file_num             536041 non-null int64
dtypes: float64(1), int64(1), object(14)
memory usage: 65.4+ MB

#用统计学指标快速描述数值型属性的概要
df.describe()

	contb_receipt_amt	file_num
count	5.360410e+05	536041.000000
mean	3.750373e+02	761472.107800
std	3.564436e+03	5148.893508
min	-3.080000e+04	723511.000000
25%	5.000000e+01	756218.000000
50%	1.000000e+02	763233.000000
75%	2.500000e+02	763621.000000
max	1.944042e+06	767394.000000

#空值处理。可能因为忘记填写或者保密等等原因，相关字段出现了空值，将其填充为NOT PROVIDE
df.fillna(value='NOT PROVIDE',inplace=True)

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 536041 entries, 0 to 536040
Data columns (total 16 columns):
cmte_id              536041 non-null object
cand_id              536041 non-null object
cand_nm              536041 non-null object
contbr_nm            536041 non-null object
contbr_city          536041 non-null object
contbr_st            536041 non-null object
contbr_zip           536041 non-null object
contbr_employer      536041 non-null object
contbr_occupation    536041 non-null object
contb_receipt_amt    536041 non-null float64
contb_receipt_dt     536041 non-null object
receipt_desc         536041 non-null object
memo_cd              536041 non-null object
memo_text            536041 non-null object
form_tp              536041 non-null object
file_num             536041 non-null int64
dtypes: float64(1), int64(1), object(14)
memory usage: 65.4+ MB

#异常值处理。将捐款金额<=0的数据删除
df['contb_receipt_amt'] <= 0 #判断哪些值为小于等于0
df.loc[df['contb_receipt_amt'] <= 0] #捐赠金额小于等于0的行数据
drop_indexs = df.loc[df['contb_receipt_amt'] <= 0].index
df.drop(labels=drop_indexs,axis=0,inplace=True)

#新建一列为各个候选人所在党派party
df['party'] = df['cand_nm'].map(parties)

df.head()

	cmte_id	cand_id	cand_nm	contbr_nm	contbr_city	contbr_st	contbr_zip	contbr_employer	contbr_occupation	contb_receipt_amt	contb_receipt_dt	receipt_desc	memo_cd	memo_text	form_tp	file_num	party
0	C00410118	P20002978	Bachmann, Michelle	HARVEY, WILLIAM	MOBILE	AL	3.6601e+08	RETIRED	RETIRED	250.0	20-JUN-11	NOT PROVIDE	NOT PROVIDE	NOT PROVIDE	SA17A	736166	Republican
1	C00410118	P20002978	Bachmann, Michelle	HARVEY, WILLIAM	MOBILE	AL	3.6601e+08	RETIRED	RETIRED	50.0	23-JUN-11	NOT PROVIDE	NOT PROVIDE	NOT PROVIDE	SA17A	736166	Republican
2	C00410118	P20002978	Bachmann, Michelle	SMITH, LANIER	LANETT	AL	3.68633e+08	INFORMATION REQUESTED	INFORMATION REQUESTED	250.0	05-JUL-11	NOT PROVIDE	NOT PROVIDE	NOT PROVIDE	SA17A	749073	Republican
3	C00410118	P20002978	Bachmann, Michelle	BLEVINS, DARONDA	PIGGOTT	AR	7.24548e+08	NONE	RETIRED	250.0	01-AUG-11	NOT PROVIDE	NOT PROVIDE	NOT PROVIDE	SA17A	749073	Republican
4	C00410118	P20002978	Bachmann, Michelle	WARDENBURG, HAROLD	HOT SPRINGS NATION	AR	7.19016e+08	NONE	RETIRED	300.0	20-JUN-11	NOT PROVIDE	NOT PROVIDE	NOT PROVIDE	SA17A	736166	Republican

#查看party这一列中有哪些不同的元素
df['party'].unique()

array(['Republican', 'Democrat', 'Reform', 'Libertarian'], dtype=object)

#统计party列中各个元素出现次数
df['party'].value_counts()

Democrat       289999
Republican     234300
Reform           5313
Libertarian       702
Name: party, dtype: int64

#查看各个党派收到的政治献金总数contb_receipt_amt
df.groupby(by='party')['contb_receipt_amt'].sum()

party
Democrat       8.259441e+07
Libertarian    4.132769e+05
Reform         3.429658e+05
Republican     1.251181e+08
Name: contb_receipt_amt, dtype: float64

#查看具体每天各个党派收到的政治献金总数contb_receipt_amt
df.groupby(by=['contb_receipt_dt','party'])['contb_receipt_amt'].sum()

contb_receipt_dt  party      
01-APR-11         Reform              50.00
                  Republican       12635.00
01-AUG-11         Democrat        182198.00
                  Libertarian       1000.00
                  Reform            1847.00
                  Republican      268903.02
01-DEC-11         Democrat        651982.82
                  Libertarian        725.00
                  Reform             875.00
                  Republican      505255.96
01-FEB-11         Republican         250.00
01-JAN-11         Republican        8600.00
01-JAN-12         Democrat         74303.80
                  Reform             515.00
                  Republican       76804.72
01-JUL-11         Democrat        175364.00
                  Libertarian       2000.00
                  Reform             100.00
                  Republican      125973.72
01-JUN-11         Democrat        148409.00
                  Libertarian        500.00
                  Reform              50.00
                  Republican      435609.20
01-MAR-11         Republican        1000.00
01-MAY-11         Democrat         82644.00
                  Reform             480.00
                  Republican       28663.87
01-NOV-11         Democrat        129309.87
                  Libertarian       3000.00
                  Reform            1792.00
                                    ...    
30-OCT-11         Reform            3910.00
                  Republican       46413.16
30-SEP-11         Democrat       3409587.24
                  Libertarian        550.00
                  Reform            2050.00
                  Republican     5094824.20
31-AUG-11         Democrat        375487.44
                  Libertarian      10750.00
                  Reform             450.00
                  Republican     1038330.90
31-DEC-11         Democrat       3571793.57
                  Reform             695.00
                  Republican     1165777.72
31-JAN-11         Republican        6000.00
31-JAN-12         Democrat       1421887.31
                  Reform             150.00
                  Republican      963681.41
31-JUL-11         Democrat         20305.00
                  Reform            1066.00
                  Republican       12781.02
31-MAR-11         Reform             200.00
                  Republican       74575.00
31-MAY-11         Democrat        352005.66
                  Libertarian        250.00
                  Reform             100.00
                  Republican      313839.80
31-OCT-11         Democrat        216971.87
                  Libertarian       4250.00
                  Reform            3205.00
                  Republican      751542.36
Name: contb_receipt_amt, Length: 1183, dtype: float64

#将表中日期格式转换为'yyyy-mm-dd
def trandformDate(d):
    day,month,year = d.split('-')
    month = months[month]#将英文形式的月份转换成了数字形式的月份
    return '20'+year+'-'+str(month)+'-'+day
df['contb_receipt_dt'] = df['contb_receipt_dt'].map(trandformDate)

df.head()

	cmte_id	cand_id	cand_nm	contbr_nm	contbr_city	contbr_st	contbr_zip	contbr_employer	contbr_occupation	contb_receipt_amt	contb_receipt_dt	receipt_desc	memo_cd	memo_text	form_tp	file_num	party
0	C00410118	P20002978	Bachmann, Michelle	HARVEY, WILLIAM	MOBILE	AL	3.6601e+08	RETIRED	RETIRED	250.0	2011-6-20	NOT PROVIDE	NOT PROVIDE	NOT PROVIDE	SA17A	736166	Republican
1	C00410118	P20002978	Bachmann, Michelle	HARVEY, WILLIAM	MOBILE	AL	3.6601e+08	RETIRED	RETIRED	50.0	2011-6-23	NOT PROVIDE	NOT PROVIDE	NOT PROVIDE	SA17A	736166	Republican
2	C00410118	P20002978	Bachmann, Michelle	SMITH, LANIER	LANETT	AL	3.68633e+08	INFORMATION REQUESTED	INFORMATION REQUESTED	250.0	2011-7-05	NOT PROVIDE	NOT PROVIDE	NOT PROVIDE	SA17A	749073	Republican
3	C00410118	P20002978	Bachmann, Michelle	BLEVINS, DARONDA	PIGGOTT	AR	7.24548e+08	NONE	RETIRED	250.0	2011-8-01	NOT PROVIDE	NOT PROVIDE	NOT PROVIDE	SA17A	749073	Republican
4	C00410118	P20002978	Bachmann, Michelle	WARDENBURG, HAROLD	HOT SPRINGS NATION	AR	7.19016e+08	NONE	RETIRED	300.0	2011-6-20	NOT PROVIDE	NOT PROVIDE	NOT PROVIDE	SA17A	736166	Republican

查看老兵(捐献者职业)DISABLED VETERAN主要支持谁.给谁捐赠的钱越多表示越支持谁

可以先将源数据中的老兵这个职业对应的行数据取出

df['contbr_occupation'] == 'DISABLED VETERAN'
df_old = df.loc[df['contbr_occupation'] == 'DISABLED VETERAN']

分组：根据候选人分组，对捐赠金额求和

df_old.groupby(by='cand_nm')['contb_receipt_amt'].sum()

posted @ 2021-06-16 13:34 风hua 阅读(137) 评论(0) 编辑收藏举报

刷新页面返回顶部

8 pandas实战-美国大选数据分析

需求

查看老兵(捐献者职业)DISABLED VETERAN主要支持谁.给谁捐赠的钱越多表示越支持谁

可以先将源数据中的老兵这个职业对应的行数据取出

分组：根据候选人分组，对捐赠金额求和

公告