Logistic Regression with SciPy

我正在尝试使用 SciPy fmin_bfgs 函数用 Python 编写逻辑回归，但是遇到了一些问题。我为逻辑（sigmoid）变换函数和成本函数编写了函数，并且它们工作正常（我使用可以通过软件包优化找到的参数向量的优化值来测试函数，并且这些值匹配）。我不确定我对梯度函数的实现，但它看起来是合理的。

以下代码：

# purpose: logistic regression 
import numpy as np
import scipy.optimize

# prepare the data
data = np.loadtxt('data.csv', delimiter=',', skiprows=1)
vY = data[:, 0]
mX = data[:, 1:]
intercept = np.ones(mX.shape[0]).reshape(mX.shape[0], 1)
mX = np.concatenate((intercept, mX), axis = 1)
iK = mX.shape[1]
iN = mX.shape[0]

# logistic transformation
def logit(mX, vBeta):
    return((1/(1.0 + np.exp(-np.dot(mX, vBeta)))))

# test function call
vBeta0 = np.array([-.10296645, -.0332327, -.01209484, .44626211, .92554137, .53973828, 
    1.7993371, .7148045  ])
logit(mX, vBeta0)

# cost function
def logLikelihoodLogit(vBeta, mX, vY):
    return(-(np.sum(vY*np.log(logit(mX, vBeta)) + (1-vY)*(np.log(1-logit(mX, vBeta))))))
logLikelihoodLogit(vBeta0, mX, vY) # test function call

# gradient function
def likelihoodScore(vBeta, mX, vY):
    return(np.dot(mX.T, 
                  ((np.dot(mX, vBeta) - vY)/
                   np.dot(mX, vBeta)).reshape(iN, 1)).reshape(iK, 1))

likelihoodScore(vBeta0, mX, vY).shape # test function call

# optimize the function (without gradient)
optimLogit = scipy.optimize.fmin_bfgs(logLikelihoodLogit, 
                                  x0 = np.array([-.1, -.03, -.01, .44, .92, .53,
                                            1.8, .71]), 
                                  args = (mX, vY), gtol = 1e-3)

# optimize the function (with gradient)
optimLogit = scipy.optimize.fmin_bfgs(logLikelihoodLogit, 
                                  x0 = np.array([-.1, -.03, -.01, .44, .92, .53,
                                            1.8, .71]), fprime = likelihoodScore, 
                                  args = (mX, vY), gtol = 1e-3)

第一个优化（没有梯度）以大量有关除以零的信息结束。 第二个优化（带有梯度）以矩阵未对齐错误结束，这可能意味着我搞错了梯度返回方式。

如果有人想尝试一下，数据如下：

low,age,lwt,race,smoke,ptl,ht,ui
0,19,182,2,0,0,0,1
0,33,155,3,0,0,0,0
0,20,105,1,1,0,0,0
0,21,108,1,1,0,0,1
0,18,107,1,1,0,0,1
0,21,124,3,0,0,0,0
0,22,118,1,0,0,0,0
0,17,103,3,0,0,0,0
0,29,123,1,1,0,0,0
0,26,113,1,1,0,0,0
0,19,95,3,0,0,0,0
0,19,150,3,0,0,0,0
0,22,95,3,0,0,1,0
0,30,107,3,0,1,0,1
0,18,100,1,1,0,0,0
0,18,100,1,1,0,0,0
0,15,98,2,0,0,0,0
0,25,118,1,1,0,0,0
0,20,120,3,0,0,0,1
0,28,120,1,1,0,0,0
0,32,121,3,0,0,0,0
0,31,100,1,0,0,0,1
0,36,202,1,0,0,0,0
0,28,120,3,0,0,0,0
0,25,120,3,0,0,0,1
0,28,167,1,0,0,0,0
0,17,122,1,1,0,0,0
0,29,150,1,0,0,0,0
0,26,168,2,1,0,0,0
0,17,113,2,0,0,0,0
0,17,113,2,0,0,0,0
0,24,90,1,1,1,0,0
0,35,121,2,1,1,0,0
0,25,155,1,0,0,0,0
0,25,125,2,0,0,0,0
0,29,140,1,1,0,0,0
0,19,138,1,1,0,0,0
0,27,124,1,1,0,0,0
0,31,215,1,1,0,0,0
0,33,109,1,1,0,0,0
0,21,185,2,1,0,0,0
0,19,189,1,0,0,0,0
0,23,130,2,0,0,0,0
0,21,160,1,0,0,0,0
0,18,90,1,1,0,0,1
0,18,90,1,1,0,0,1
0,32,132,1,0,0,0,0
0,19,132,3,0,0,0,0
0,24,115,1,0,0,0,0
0,22,85,3,1,0,0,0
0,22,120,1,0,0,1,0
0,23,128,3,0,0,0,0
0,22,130,1,1,0,0,0
0,30,95,1,1,0,0,0
0,19,115,3,0,0,0,0
0,16,110,3,0,0,0,0
0,21,110,3,1,0,0,1
0,30,153,3,0,0,0,0
0,20,103,3,0,0,0,0
0,17,119,3,0,0,0,0
0,17,119,3,0,0,0,0
0,23,119,3,0,0,0,0
0,24,110,3,0,0,0,0
0,28,140,1,0,0,0,0
0,26,133,3,1,2,0,0
0,20,169,3