ML之分类预测之ElasticNet之PLoR：在二分类数据集上调用Glmnet库训练PLoR模型(T2)

ML之分类预测之ElasticNet之PLoR：在二分类数据集上调用Glmnet库训练PLoR模型(T2)

目录

输出结果

设计思路

核心代码

输出结果

设计思路

核心代码

  

   

    

     

    
    

     

      for iStep in range(nSteps):
     
    
   

    

     

    
    

     

       lam = lam * lamMult 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       betaIRLS = list(beta)
     
    
   

    

     

    
    

     

       beta0IRLS = beta0
     
    
   

    

     

    
    

     

       distIRLS = 100.0
     
    
   

    

     

    
    

     

       iterIRLS = 0
     
    
   

    

     

    
    

     
 while distIRLS > 0.01:
     
    
   

    

     

    
    

     

       iterIRLS += 1
     
    
   

    

     

    
    

     

       iterInner = 0.0
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       betaInner = list(betaIRLS)
     
    
   

    

     

    
    

     

       beta0Inner = beta0IRLS
     
    
   

    

     

    
    

     

       distInner = 100.0
     
    
   

    

     

    
    

     
 while distInner > 0.01:
     
    
   

    

     

    
    

     

       iterInner += 1
     
    
   

    

     

    
    

     
 if iterInner > 100: break
     
    
   

    

     

    
    

     

       betaStart = list(betaInner)
     
    
   

    

     

    
    

     
 for iCol in range(ncol):
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       sumWxr = 0.0
     
    
   

    

     

    
    

     

       sumWxx = 0.0
     
    
   

    

     

    
    

     

       sumWr = 0.0
     
    
   

    

     

    
    

     

       sumW = 0.0
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 for iRow in range(nrow):
     
    
   

    

     

    
    

     

       x = list(xNormalized[iRow])
     
    
   

    

     

    
    

     

       y = labels[iRow]
     
    
   

    

     

    
    

     

       p = Pr(beta0IRLS, betaIRLS, x)
     
    
   

    

     

    
    

     
 if abs(p) < 1e-5:
     
    
   

    

     

    
    

     

       p = 0.0
     
    
   

    

     

    
    

     

       w = 1e-5
     
    
   

    

     

    
    

     
 elif abs(1.0 - p) < 1e-5:
     
    
   

    

     

    
    

     

       p = 1.0
     
    
   

    

     

    
    

     

       w = 1e-5
     
    
   

    

     

    
    

     
 else:
     
    
   

    

     

    
    

     

       w = p * (1.0 - p)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       z = (y - p) / w + beta0IRLS + sum([x[i] * betaIRLS[i] for i in range(ncol)])
     
    
   

    

     

    
    

     

       r = z - beta0Inner - sum([x[i] * betaInner[i] for i in range(ncol)])
     
    
   

    

     

    
    

     

       sumWxr += w * x[iCol] * r
     
    
   

    

     

    
    

     

       sumWxx += w * x[iCol] * x[iCol]
     
    
   

    

     

    
    

     

       sumWr += w * r
     
    
   

    

     

    
    

     

       sumW += w
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       avgWxr = sumWxr / nrow
     
    
   

    

     

    
    

     

       avgWxx = sumWxx / nrow
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       beta0Inner = beta0Inner + sumWr / sumW
     
    
   

    

     

    
    

     

       uncBeta = avgWxr + avgWxx * betaInner[iCol]
     
    
   

    

     

    
    

     

       betaInner[iCol] = S(uncBeta, lam * alpha) / (avgWxx + lam * (1.0 - alpha))
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       sumDiff = sum([abs(betaInner[n] - betaStart[n]) for n in range(ncol)])
     
    
   

    

     

    
    

     

       sumBeta = sum([abs(betaInner[n]) for n in range(ncol)])
     
    
   

    

     

    
    

     

       distInner = sumDiff/sumBeta
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       a = sum([abs(betaIRLS[i] - betaInner[i]) for i in range(ncol)])
     
    
   

    

     

    
    

     

       b = sum([abs(betaIRLS[i]) for i in range(ncol)])
     
    
   

    

     

    
    

     

       distIRLS = a / (b + 0.0001)
     
    
   

    

     

    
    

     

       dBeta = [betaInner[i] - betaIRLS[i] for i in range(ncol)]
     
    
   

    

     

    
    

     

       gradStep = 1.0
     
    
   

    

     

    
    

     

       temp = [betaIRLS[i] + gradStep * dBeta[i] for i in range(ncol)]
     
    
   

    

     

    
    

     

       betaIRLS = list(temp)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       beta = list(betaIRLS)
     
    
   

    

     

    
    

     

       beta0 = beta0IRLS
     
    
   

    

     

    
    

     

       betaMat.append(list(beta))
     
    
   

    

     

    
    

     

       beta0List.append(beta0)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       nzBeta = [index for index in range(ncol) if beta[index] != 0.0]
     
    
   

    

     

    
    

     
 for q in nzBeta:
     
    
   

    

     

    
    

     
 if not(q in nzList):
     
    
   

    

     

    
    

     

       nzList.append(q)
     
    
  
 

文章来源: yunyaniu.blog.csdn.net，作者：一个处女座的程序猿，版权归原作者所有，如需转载，请联系作者。

原文链接：yunyaniu.blog.csdn.net/article/details/85857823