Data Analysis with Python——09

[hsipeng]

Data Analysis with Python——09

GroupBy 实例

import pandas as pd
from pandas import DataFrame, Series
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

fec = pd.read_csv('code/pydata-book/datasets/fec/P00000001-ALL.csv')

fec
fec.loc[123456]
#fec.ix[123456]

unique_cands = fec.cand_nm.unique()
unique_cands

parties={'Bachmann, Michelle':'Republican','Cain, Herman':'Republican','Gingrich, Newt':'Republican','Huntsman, Jon':'Republican','Johnson, GaryEarl':'Republican','McCotter, ThaddeusG':'Republican','Obama, Barack':'Democrat','Paul, Ron':'Republican','Pawlenty, Timothy':'Republican','Perry, Rick':'Republican',"Roemer, CharlesE. 'Buddy' III":'Republican','Romney, Mitt':'Republican','Santorum, Rick':'Republican'}

fec.cand_nm[123456:123461].map(parties)


# 加入'party' 属性
fec['party'] = fec.cand_nm.map(parties)

fec['party'].value_counts()


(fec.contb_receipt_amt > 0).value_counts()
fec = fec[fec.contb_receipt_amt > 0]

fec_mrbo = fec[fec.cand_nm.isin(['Obama, Barack', 'Romney, Mitt'])]

fec_mrbo



fec.contbr_occupation.value_counts()[:10]


# 职业转换
occ_mapping={'INFORMATION REQUESTED PER BEST EFFORTS':'NOT PROVIDED','INFORMATION REQUESTED':'NOT PROVIDED','INFORMATION REQUESTED (BEST EFFORTS)':'NOTPROVIDED','C.E.O.':'CEO'}

f = lambda x: occ_mapping.get(x, x)

fec.contbr_occupation = fec.contbr_occupation.map(f)

emp_mapping={'INFORMATION REQUESTED PER BEST EFFORTS':'NOT PROVIDED','INFORMATION REQUESTED':'NOT PROVIDED','SELF':'SELF EMPLOYED','SELF-EMPLOYED':'SELF-EMPLOYED',}

f2 = lambda x: emp_mapping.get(x, x)

fec.contbr_employer = fec.contbr_employer.map(f2)

by_occupation = fec.pivot_table('contb_receipt_amt', index='contbr_occupation', columns='party',aggfunc='sum')
#对各党派总出资额最高的职业
over_2mm = by_occupation[by_occupation.sum(1) > 2000000]
over_2mm



over_2mm.plot(kind='barh')
#对各党派总出资额最高的职业

[hsipeng]

资料集

• https://github.com/wesm/pydata-book