数据分析项目3-美国大选献金分析

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:捐赠人所在州
     contbr_employer：捐赠人所在公司
     contbr_occupation:捐赠人职业
     contbr_receipt_amt:捐赠数额（美元）
     contbr_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

import numpy as np
import pandas as pd

df = pd.read_csv("./data/usa_election-Copy1.txt")

# 方便操作,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',
}


df.info()

RangeIndex: 536041 entries, 0 to 536040
Data columns (total 16 columns):
 #   Column             Non-Null Count   Dtype  
---  ------             --------------   -----  
 0   cmte_id            536041 non-null  object 
 1   cand_id            536041 non-null  object 
 2   cand_nm            536041 non-null  object 
 3   contbr_nm          536041 non-null  object 
 4   contbr_city        536026 non-null  object 
 5   contbr_st          536040 non-null  object 
 6   contbr_zip         535973 non-null  object 
 7   contbr_employer    525088 non-null  object 
 8   contbr_occupation  530520 non-null  object 
 9   contb_receipt_amt  536041 non-null  float64
 10  contb_receipt_dt   536041 non-null  object 
 11  receipt_desc       8479 non-null    object 
 12  memo_cd            49718 non-null   object 
 13  memo_text          52740 non-null   object 
 14  form_tp            536041 non-null  object 
 15  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()

# 异常处理。将捐款金额<=0 的数据删除
df['contb_receipt_amt']<=0
df[df["contb_receipt_amt"]<=0]
drop_indexs = df[df["contb_receipt_amt"]<=0].index
df.drop(labels=drop_indexs,inplace=True)
df.info()

df_need = df[["cand_nm","contbr_nm","contbr_employer","contbr_occupation","contb_receipt_amt","contb_receipt_dt"]]
df_need


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

df_need.head()

# 查看party这一列中有哪些不同的元素
df_need["party"].unique()
array(['Republican', 'Democrat', 'Reform', 'Libertarian'], dtype=object)

# 统计party列中各个元素出现次数
df_need["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_need.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contb_receipt_amt
df_need.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
                                   ...    
31-MAY-11         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 transform(d):
    day,month,year = d.split("-")
    month = months[month]
    return "20"+year+"-"+str(month)+"-"+day
df_need["contb_receipt_dt"]= df_need["contb_receipt_dt"].map(transform)
df_need


# 查看老兵（捐献者职业）DISABLED VETERAN主要支持谁. 给谁捐赠的钱越多
# 将源数据的老兵这个职业的行数据取出

df_need["contbr_occupation"] == "DISABLED VETERAN"
df_old = df_need[df_need["contbr_occupation"] == "DISABLED VETERAN"]
df_old

df_old.groupby(by="cand_nm")["contb_receipt_amt"].sum()
cand_nm
Cain, Herman       300.00
Obama, Barack     4205.00
Paul, Ron         2425.49
Santorum, Rick     250.00
Name: contb_receipt_amt, dtype: float64