分析2012年美国选举数据---映射map/透视表pivot_table/聚合groupby/apply

import pandas as pdfrom matplotlib import pyplot as pltfec = pd.read_csv('D:\python program\pydata-book-2nd-edition\datasets\\fec\P00000001-ALL.csv')'''获取全部候选人名单unique_cands = fec.cand_nm.unique()'''#利用字典添加党派关系parties = {    'Bachmann, Michelle':'Republican',    'Romney, Mitt':'Republican',    'Obama, Barack':'Democrat',    "Roemer, Charles E. 'Buddy' III":'Republican',    'Pawlenty, Timothy' : 'Republican',    'Johnson, Gary Earl' : 'Republican',    'Paul, Ron' : 'Republican',    'Santorum, Rick' : 'Republican',    'Cain, Herman' : 'Republican',    'Gingrich, Newt' : 'Republican',    'McCotter, Thaddeus G' : 'Republican',    'Huntsman, Jon' : 'Republican',    'Perry, Rick' : 'Republican'}#将党派添加为一个新列fec['party'] = fec.cand_nm.map(parties)#名字映射党派#只显示赞助的及出资额为正的数据fec = fec[fec.contb_receipt_amt > 0]#只包含重要信息的子集，即obama和romney的竞选信息fec_sub = fec[fec.cand_nm.isin(['Obama, Barack','Romney, Mitt'])]'''根据职业和雇主统计赞助信息。基于职业的赞助信息统计''''''获取赞助的职业及数量fec.contbr_occupation.value_counts()'''#许多职业涉及相同的基本工作类型，清理数据occ_mapping = {    'INFORMATION REQUESTED' : 'NOT PROVIDED',    'INFORMATION REQUESTED PER BEST EFFORTS' : 'NOT PROVIDED',    'INFORMATION REQUESTED (BEST EFFORTS)' : 'NOT PROVIDED',    'C.E.O.' : 'CEO'}#dict.get允许没有映射关系的也能通过，如果没有提供相关映射，则返回xf = lambda x: occ_mapping.get(x,x)fec.contbr_occupation = fec.contbr_occupation.map(f)#同理清理雇主数据emp_mapping = {    'INFORMATION REQUESTED PER BEST EFFORTS' : 'NOT PROVIDED',    'INFORMATION REQUESTED' : 'NOT PROVIDED',    'SELF' : 'SELF-EMPLOYED',    'SELF EMPLOYED' : 'SELF-EMPLOYED'}f = lambda x: emp_mapping.get(x,x)fec.contbr_employer = fec.contbr_employer.map(f)#根据党派和职业对数据进行聚合by_occupation = fec.pivot_table('contb_receipt_amt',index='contbr_occupation',columns='party',aggfunc='sum')#过滤掉总出资额低于200万美元的数据over_2mm = by_occupation[by_occupation.sum(1) > 2000000]#柱状图over_2mm.plot(kind='barh',title='occ_receipt for party')plt.show()

'''分析对Obama和Romney总出资额最高的职业和企业'''#求取最大值def get_top_amounts(group,key,n=5):    totals = group.groupby(key)['contb_receipt_amt'].sum()    #根据key对totals降序    return totals.sort_values(ascending=False)[:n]#根据雇主和职业聚合grouped = fec_sub.groupby('cand_nm')#职业，前7个occ_receipt_group = grouped.apply(get_top_amounts,'contbr_occupation',n=7)#雇主，前7个emp_receipt_group = grouped.apply(get_top_amounts,'contbr_employer',n=7)#画图fig,axes = plt.subplots(2,1)occ_receipt_group.plot(kind='barh',ax=axes[0],title='occ_receipt_group')emp_receipt_group.plot(kind='barh',ax=axes[1],title='emp_receipt_group.')plt.show()

'''对出资额分组
分析两位候选人各种赞助额的比例
'''#利用cut函数根据出资额的大小将数据离散化到多个面元中bins = np.array([0,1,10,100,1000,10000,100000,1000000,10000000])labels = pd.cut(fec_sub.contb_receipt_amt,bins)    #面元标签#根据候选人和面元标签对数据分组grouped = fec_sub.groupby(['cand_nm',labels])print(grouped.size().unstack(0))

#对出资额求和，并在面元内规格化bucket_sums = grouped.contb_receipt_amt.sum().unstack(0)#print(bucket_sums)#将得到的数据按比例normed_sums = bucket_sums.div(bucket_sums.sum(axis=1),axis=0)#print(normed_sums)#排除两个最大的normed_sums[:-2].plot(kind='barh',stacked=True)plt.show()

'''根据州统计赞助信息'''#根据候选人和州对数据聚合grouped = fec_sub.groupby(['cand_nm','contbr_st'])totals = grouped.contb_receipt_amt.sum().unstack(0).fillna(0)totals = totals[totals.sum(1) > 100000]#print(totals)#各行除以总赞助额，得到各候选人在各州的总赞助额比例percent = totals.div(totals.sum(1),axis=0)    #跟sum(axis=1)一样print(percent)