LogisticRegression

python 实现logisticRegression

1、实验使用的数据来自http://sci2s.ugr.es/keel/category.php?cat=clas
2、此处并没有考虑正则项，如果需要考虑正则，只需要修改梯度的计算
3、有关具体的推导请参考Andrew Ng.的课程http://cs229.stanford.edu/

#-*- coding=utf-8 -*-import numpy as np"""time 2016.1.31"""class LogisticRegression(object):    "class logistic Regression"    def __init__(self,n,epo=1000,rate=0.001):        self.rate=rate        self.epo=epo        self.weights=np.random.normal(size=(n))    def fit(self,data):        for i in range(self.epo):            for j in range(data.shape[0]):                x=data[j][:-1]                y=data[j][-1]                h=self.predict(x)                self.weights=self.weights+self.rate*(y-h)*x    def sigmoid(self,x):        return 1/(1+np.exp(-x))    def predict(self,x):        g=sum(self.weights*x)        return self.sigmoid(g)    def accuracy(self,data):        num=0        for i in range(data.shape[0]):            x=data[i][:-1]            y=data[i][-1]            h=self.predict(x)            if h>=0.5:                if(y==1):                    num+=1            if h<0.5:                if y==0:                    num+=1        print "predict accuracy is %lf"%(num*1.0/data.shape[0])def loadData(path):    data=np.loadtxt(path,skiprows=10,dtype="int32",delimiter=",")    new_data=np.ones((data.shape[0],data.shape[1]+1))    """"relarge the dataset with x0=1"""    new_data[:,1:]=data    return new_datadata=loadData("D:\\SelfLearning\\Machine Learning\\ClassifyDataSet\\mammographic\\mammographic.dat")train_data=data[:600]test_data=data[600:]lr=LogisticRegression(6,epo=1000)lr.fit(train_data)print lr.weightslr.accuracy(test_data)lr.accuracy(train_data)