Logistic回归编程实战

Logistic回归编程实战

上一节学习了Logistic回归，这一节就针对该算法进行编程实战，所使用的是python2.7。

---

以下是本项目的全部代码

# -*- coding:utf-8 -*-
from numpy import *
import matplotlib.pyplot as plt

class Logister(object):
    def __init__(self,path):
        self.path=path
    #将导入的文件转换为矩阵形式
    def file2matrix(self,delimiter):
        recordlist = []
        fp = open(self.path,"rb")   # 读取文件内容
        content = fp.read()
        fp.close()
        rowlist = content.splitlines()  # 按行转换为一维表
        # 逐行遍历      # 结果按分隔符分割为行向量
        recordlist=[map(eval, row.split(delimiter)) for row in rowlist if row.strip()]
        return mat(recordlist)  # 返回转换后的矩阵形式

    # 绘制分类点
    def drawScatterbyLabel(self,plt,Input):
        m,n=shape(Input)
        target = Input[:,-1]
        for i in xrange(m):
            if target[i]==0:
                plt.scatter(Input[i,0],Input[i,1],c='blue',marker='o')
            else:
                plt.scatter(Input[i,0],Input[i,1],c='red',marker='s')

    #Logistic函数
    def logistic(self,wTx):
        return 1.0/(1.0+exp(-wTx))

    def buildMat(self,dataSet):
        m,n=shape(dataSet)
        dataMat = zeros((m,n))
        dataMat[:,0] = 1
        dataMat[:,1:] = dataSet[:,:-1]
        return  dataMat

    # 分类函数
    def classifier(self,testData, weights):
        prob = self.logistic(sum(testData*weights)) # 求取概率--判别算法
        if prob > 0.5:
            return 1.0  # prob>0.5 返回为1
        else:
            return 0.0  # prob<=0.5 返回为0

if __name__ == "__main__":
    logis = Logister("testSet.txt")
    input_data = logis.file2matrix("\t")
    target = input_data[:,-1]
    [m,n] = shape(input_data)
    #print input_data
    #print m,n
    logis.drawScatterbyLabel(plt,input_data)
    dataMat = logis.buildMat(input_data)
    #print dataMat

    #main()
    alpha = 0.001  #梯度下降的参数
    steps = 500  #迭代次数
    weights = ones((n,1))  #初始化权重向量

    for k in xrange(steps):
        gradient = dataMat*mat(weights)
        output = logis.logistic(gradient)
        errors = target-output
        weights = weights + alpha*dataMat.T*errors  #梯度下降
    #print weights

    #应用模型到测试数据中
    testdata = mat([-0.147324,2.874846])  #测试数据
    m,n = shape(testdata)
    testmat = zeros((m,n+1))
    testmat[:,0] = 1
    testmat[:,1:] = testdata
    print logis.classifier(testmat,weights)  #weights为前面训练得出的

    #绘制决策边界
    X = linspace(-5,5,100)
    Y = -(double(weights[0])+X*(double(weights[1])))/double(weights[2])
    plt.plot(X,Y)
    plt.show()

运行结果:

1.0

---

代码中设计的数据集文件”testSet.txt”,可在http://download.csdn.net/detail/louishao/9747154下载查看。