Titled Machine Learning Watermelon Book Chapter 3 after-school exercises, programming to achieve logarithmic regression, the data set is the data on page 89 of the book
# coding=utf-8 # import flatten import tensorflow as tf from numpy import * import numpy as np import matplotlib.pyplot as plt def LDA(c1,c2): m1=mean(c1,axis=0) m2=mean(c2,axis=0) c=vstack((c1,c2)) m=mean(c,axis=0) n1=c1.shape[0] n2=c2.shape[0] s1 = 0 s2=0 for i in range(n1): s1+=(c1[i,:]-m1).T*(c1[i,:]-m1) for i in range(n2): s2+= (c2[i, :] - m2).T * (c2[i, :] - m2) sw=(n1*s1+n2*s2)/(n1+n2) sb=((n1*(m-m1).T*(m-m1))+(n2*(m-m2)).T*(m-m2))/(n1+n2) a,b=np.linalg.eig(mat(sw).I*sb) index=np.argsort(-a) maxIndex=index[:1] w=b[:,maxIndex] return w data = array([[0.697,0.460,1], [0.774,0.376,1], [0.634,0.264,1], [0.608,0.318,1], [0.556,0.215,1], [0.403,0.237,1], [0.481,0.149,1], [0.437,0.211,1], [0.666,0.091,0], [0.243,0.267,0], [0.245,0.057,0], [0.343,0.099,0], [0.639,0.161,0], [0.657,0.198,0], [0.360,0.370,0], [0.593,0.042,0], [0.719,0.103,0]]) x_train1=data[0:8,0:2] a1=x_train1[:,0] b1=x_train1[:,1] print(a1) x_train2=data[8:,0:2] a2=x_train2[:,0] b2 =x_train2[:,1 ] #before sample projection plt.scatter(a1,b1,label= ' + ' , color= ' g ' , s=25, marker= ' o ' ) plt.scatter(a2,b2,label=' - ', color='r', s=25, marker='o') W=LDA(x_train1,x_train2) print("w=",W) k=W[1,0]/W[0,0] plt.plot ([0, 1.5], [0,1.5 * k]) # print (k) # new1 = (a1 * W [0,0]) # new2 = (b1 * W [0,0]) # new3 = (a2 * W [1,0]) # new4 = (b2 * W [1,0]) new1 = (a1 + k * b1) / (k * k + 1 ) new2 = k * new1 plt.plot(new1,new2,'*r') new3=(a2+k*b2)/(k*k+1) new4=k*new3 plt.plot(new3,new4,'*g') plt.legend() #Set the legend plt.show()
operation result:
