爬虫 美国政治献金案例分析

美国2012年总统候选人政治献金数据分析

 

导入包

In [4]:

 

 

 

 

 

import numpy as np

import pandas as pd

from pandas import Series,DataFrame

 

 

 

方便大家操作，将月份和参选人以及所在政党进行定义

In [1]:

 

 

 

 

 

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'           

 }

 

 

 

读取文件

In [5]:

 

 

 

 

 

# 读文件

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

df.head(2)

 

 

 

D:\Anaconda\lib\site-packages\IPython\core\interactiveshell.py:2728: DtypeWarning: Columns (6) have mixed types. Specify dtype option on import or set low_memory=False.
  interactivity=interactivity, compiler=compiler, result=result)

Out[5]:

	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

In [7]:

 

 

 

 

 

#新建一列各个候选人所在党派party

# 参看上面的parties 字典

​

df['party']=df['cand_nm'].map(parties)

df.head(2)

​

 

 

Out[7]:

	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	NaN	NaN	NaN	SA17A	736166	Republican
1	C00410118	P20002978	Bachmann, Michelle	HARVEY, WILLIAM	MOBILE	AL	3.6601e+08	RETIRED	RETIRED	50.0	23-JUN-11	NaN	NaN	NaN	SA17A	736166	Republican

In [8]:

 

 

 

 

 

#party这一列中有哪些元素

df['party'].unique()

​

 

 

Out[8]:

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

In [9]:

 

 

 

 

 

#统计party列中各个元素出现次数

​

df['party'].value_counts()

 

 

Out[9]:

Democrat       292400
Republican     237575
Reform           5364
Libertarian       702
Name: party, dtype: int64

In [10]:

 

 

 

 

 

#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()

​

 

 

Out[10]:

party
Democrat       8.105758e+07
Libertarian    4.132769e+05
Reform         3.390338e+05
Republican     1.192255e+08
Name: contb_receipt_amt, dtype: float64

In [11]:

 

 

 

 

 

df.head(2)

 

 

Out[11]:

	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	NaN	NaN	NaN	SA17A	736166	Republican
1	C00410118	P20002978	Bachmann, Michelle	HARVEY, WILLIAM	MOBILE	AL	3.6601e+08	RETIRED	RETIRED	50.0	23-JUN-11	NaN	NaN	NaN	SA17A	736166	Republican

In [14]:

 

 

 

 

 

#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()

 

. . .

In [15]:

 

 

 

 

 

def transform_date(d):

    day,month,year=d.split('-')

    month=months[month]

    return '20'+year+'-'+str(month)+'-'+day

 

 

In [16]:

 

 

 

 

 

#将表中日期格式转换为'yyyy-mm-dd'

df['contb_receipt_dt'] = df['contb_receipt_dt'].map(transform_date)

 

 

In [18]:

 

 

 

 

 

df.head(1)

 

 

Out[18]:

	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	NaN	NaN	NaN	SA17A	736166	Republican

In [19]:

 

 

 

 

 

#查看老兵(捐献者职业)DISABLED VETERAN主要支持谁

#1.找出老兵对应的行数据

df['contbr_occupation'] == 'DISABLED VETERAN'

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

​

#对候选人分组对金额做聚合

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

 

 

Out[19]:

cand_nm
Cain, Herman       300.00
Obama, Barack     4205.00
Paul, Ron         2425.49
Santorum, Rick     250.00
Name: contb_receipt_amt, dtype: float64

In [ ]:

 

 

 

 

 

#捐赠金额最大的人的职业以及捐献额  .通过query("查询条件来查找捐献人职业")

 

 

In [22]:

 

 

 

 

 

df['contb_receipt_amt'].max()

 

 

Out[22]:

1944042.43

In [23]:

 

 

 

 

 

df.query('contb_receipt_amt == 1944042.43')

 

 

Out[23]:

	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
176127	C00431445	P80003338	Obama, Barack	OBAMA VICTORY FUND 2012 - UNITEMIZED	CHICAGO	IL	60680	NaN	NaN	1944042.43	2011-12-31	NaN	X	*	SA18	763233	Democrat