python回归分析

目录

含定性变量的线性回归

非线性回归 

 

含定性变量的线性回归

# 1.treatment包实现dummy
from patsy.contrasts import Treatment
contrast = Treatment(reference=3).code_without_intercept([1,2,3])
#分类变量有三个属性分别可以用1，2，3表示，参考属性设置为3（表现为0，0）
>> ContrastMatrix(array([[1., 0.],
                      [0., 1.],
                      [0., 0.]]), ['[T.1]', '[T.2]'])
formula='Current_Salary~Education+Begin_Salary+Experience-Age+C(position,Treatment(reference=3))+C(Gender)'
model1=old(formula,data=salary).fit()

#get_dummies实现dummy
dm=pd.get_dummies(salary['position_valuelabel'],prefix='postion_')
salary=salary.join(dm)

from statsmodels.formula.api import ols
formula='Current_Salary~Education+Begin_Salary+Experience-Age+position1+postion2+Gender'
model1=old(formula,data=salary).fit()

#查看类似r的结果
model.summary2()
#qq图
sm.qqplot(model.resid,fit=True,line='45')
plt.show()
#自变