没有正则化项的时候的二分类
#-*-coding=utf-8-*-
from numpy import loadtxt,where, transpose
import matplotlib.pyplot as plt
from ipykernel.pylab.backend_inline import show
import numpy as np
from scipy.optimize import minimize
def sigmoid(x):
return 1.0/(1+np.e**(-1.0*x))
def cost(theat,x,y):
m=len(x)
J=-(1.0/m)*(transpose(y).dot(np.log(sigmoid(x.dot(theat))))+transpose(1-y).dot(np.log(1-sigmoid(x.dot(theat)))));
if np.isnan(J):
return(np.inf)
return J
def gradient(theat,x,y):
m=len(x)
h=sigmoid(x.dot(transpose(theat)))
grad=(1.0/m)*(h-y).dot(x)
return grad
def gradient_two(theat,x,y,alpha=0.0001,iteration=40000000):
m=len(x)
for i in xrange(iteration):
h=sigmoid(x.dot(theat))
grad1=theat[0]-alpha*(1.0/m)*transpose(h-y).dot(x[:,0]);
grad2=theat[1]-alpha*(1.0/m)*transpose(h-y).dot(x[:,1]);
grad3=theat[2]-alpha*(1.0/m)*transpose(h-y).dot(x[:,2]);
theat[0],theat[1],theat[2]=grad1,grad2,grad3
print 'cost',cost(theat,x,y)
print 'grad',grad1,grad2,grad3
return theat
if __name__=="__main__":
data=loadtxt(r'D:/机器学习/【批量下载】data1等/数据挖掘/ml_data/data1.txt',delimiter=',');
x=np.c_[np.ones((len(data),1)),data[:,0:2]];
y=data[:,2]
theat=np.zeros(x.shape[1]);
theat=transpose(theat);
theat=gradient_two(theat,x,y);
#res = minimize(cost, theat, args=(x,y), jac=gradient, options={'maxiter':400})
#print res
'''最后结果
theat[0]=-22.3021297062;
theat[1]=0.183373208731;
theat[2]=0.178329470851;
'''
x1=[20,100]
y1=[-(theat[0]+theat[1]*x1[0])*1.0/theat[2],-(theat[0]+theat[1]*x1[1])*1.0/theat[2]]
plt.plot(x1,y1)
pos=where(y==1)
neg=where(y==0)
plt.scatter(x[pos,1],x[pos,2],marker='o',c='b')
plt.scatter(x[neg,1],x[neg,2],marker='x',c='r')
plt.show()
加上正则化后的损失函数和公式(不想再写代码了,意会就可以了 ,逃。。。。