首先测试一下如何用python进行基本的数据处理,用的是pandas模块
import pandas as pd
import os
path=os.path.join("datasets","lifesat","")
path_oecd=path+"oecd_bli_2015.csv"
path_gdp=path+'gdp_per_capita.csv'
oecd_bli=pd.read_csv(path_oecd, thousands=',')
oecd_bli=oecd_bli[life_sat["INEQUALITY"]=="TOT"]
#此处已经将OECD数据的索引index设置为Country
oecd_bli=oecd_bli.pivot(index="Country",columns="Indicator",values="Value")
gdp_per_capita=pd.read_csv(path_gdp,thousands=',',delimiter='\t',encoding='latin1',na_values="n/a")
gdp_per_capita.rename(columns={
"2015":"GDP per capita"},inplace