#coding:utf-8
import sys
import os
from numpy import *#配置UTF-8的输出环境
reload(sys)
sys.setdefaultencoding('utf-8')#数据文件转矩阵
#path：数据文件路径
#delimiter：行内字段分隔符
def file2matrix(path,delimiter):recordlist = []fp         = open(path,"rb")#读取文件内容content    = fp.read()fp.close()rowlist    = content.splitlines()#按行转化为一维表#逐行遍历，结果按分割符分割为行向量recordlist = [map(eval,row.split(delimiter)) for row in rowlist if row.strip()] #eval字符串str当成有效的表达式来求值并返回计算结果return  mat(recordlist)#返回转换后的矩阵形式

Input  = file2matrix("testSet.txt","\t") #导入数据并转换为矩阵
target = Input[:,-1]                       #获取分类的标签数据
(m,n)  = shape(Input)

def drawScatterbyLabel(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')plt.show()

def buildMat(dataSet):m,n     = shape(dataSet)dataMat = zeros((m,n))dataMat[:,0]  = 1               #矩阵的第一列全部设置为1dataMat[:,1:] = dataSet[:,:-1]  #第一列和倒数第二列保持源数据不变，删除最后一列return dataMat

alpha = 0.001                       #步长
steps = 500                         #迭代次数
weight = ones((n,1))                #初始化权重向量

def logistic(wTx):return 1.0/(1.0+exp(-wTx))

for k in xrange(steps):gradient = dataMat*mat(weight)  #计算梯度output   = logistic(gradient)   #Logistic函数errors   = target - output      #计算误差weights  = weights + alpha*dataMat.T*errors #修正误差，进行迭代

[[ 1.20770866][-0.13220832][-0.28097863]]

X = np.linspace(-5,5,100)
#y = w*x+b:b:weight[0]/weight[2];w:weights[1]/weight[2]
Y = -(double(weights[0])+X*(double(weights[1])))/double(weights[2])
plt.plot(X,X)
plt.show()

def classifier(testData,weights):prob = logistic(sum(testData*weights))  #求取概率-判别算法if prob > 0.5:return 1.0else:return 0.0

def classifier(testData,weights):prob = logistic(sum(testData*weights))  #求取概率-判别算法if prob > 0.5:return 1.0else:return 0.0weights = mat([[ 1.20770866],[-0.13220832],[-0.28097863]])  #载入之前生成的权重
testdata = mat([-0.147324,2.874846])                        #测试数据
m,n      = shape(testdata)                                  #构建测试数据矩阵
testmat  = zeros((m,n+1))
testmat[:,0] = 1
testmat[:,1:] = testdata
print classifier(testmat,weights)