數據挖掘導論[谷風文書]

1、19.對于下面的向量x和y，計算指定的相似性或距離度量。(a)x=(1,1,1,1),y=(2,2,2,2)余弦、相關、歐幾里得。(b)x=(0,1,0,1),y=(1,0,1,0)余弦、相關、歐幾里得、Jaccard 。(c)x=(0,-1,0,1),y=(1,0,-1,0)余弦、相關、歐幾里得。(d)x=(1,1,0,1,0,1),y=(1,1,1,0,0,1)余弦、相關、Jaccard 。(e)x=(2,-1,0,2,0,-3),y=(-1,-1,-1,0,0,-1)余弦、相關。#（a）x=c(1,1,1,1)y=c(2,2,2,2)#歐幾里得s2=sum(y-x)2)p=sqrt(s2

2、)p#余弦相似性xy-sum(x*y)x1=sqrt(sum(x2)y1=sqrt(sum(y2)cosxy=xy/(x1*y1)cosxy#相關性x=c(1,1,1,1)y=c(2,2,2,2)n=length(x) #求x的字符串長度x0=sum(x)/n #計算均值y0=sum(y)/ncovariance-sum(x-x0)*(y-y0)/(n-1)covariancestandardx-sqrt(sum(x-x0)2)/(n-1)standardxstandardy-sqrt(sum(y-y0)2)/(n-1)standardycorrxy=covariance/(standardx

3、*standardy)corrxy#（b）#余弦x-c(0,1,0,1)y-c(1,0,1,0)xy-sum(x*y)x1=sqrt(sum(x2)y1=sqrt(sum(y2)cosxy=xy/(x1*y1)cosxy#相關性x-c(0,1,0,1)y-c(1,0,1,0)n=length(x) #求x的字符串長度x0=sum(x)/n #計算均值y0=sum(y)/ncovariance-sum(x-x0)*(y-y0)/(n-1)covariancestandardx-sqrt(sum(x-x0)2)/(n-1)standardxstandardy-sqrt(sum(y-y0)2)/(n

4、-1)standardycorrxy=covariance/(standardx*standardy)corrxy#歐幾里得x-c(0,1,0,1)y-c(1,0,1,0)s2=sum(y-x)2)p=sqrt(s2)p#Jaccardx-c(0,1,0,1)y-c(1,0,1,0)xy-sum(x*y)x2=sum(x2)y2=sum(y2)EJ=xy/(x2+y2-xy)EJ#(c)#余弦x=c(0,-1,0,1)y=c(1,0,-1,0)xy-sum(x*y)x1=sqrt(sum(x2)y1=sqrt(sum(y2)cosxy=xy/(x1*y1)cosxy#相關x=c(0,-1,0,

5、1)y=c(1,0,-1,0)n=length(x) #求x的字符串長度x0=sum(x)/n #計算均值y0=sum(y)/ncovariance-sum(x-x0)*(y-y0)/(n-1)covariancestandardx-sqrt(sum(x-x0)2)/(n-1)standardxstandardy-sqrt(sum(y-y0)2)/(n-1)standardycorrxy=covariance/(standardx*standardy)corrxy#歐幾里得x=c(0,-1,0,1)y=c(1,0,-1,0)s2=sum(y-x)2)p=sqrt(s2)p#（d)x=c(1,1

6、,0,1,0,1),y=c(1,1,1,0,0,1)）#余弦x=c(1,1,0,1,0,1)y=c(1,1,1,0,0,1)xy-sum(x*y)x1=sqrt(sum(x2)y1=sqrt(sum(y2)cosxy=xy/(x1*y1)cosxy#相關 x=c(1,1,0,1,0,1),y=c(1,1,1,0,0,1)n=length(x) #求x的字符串長度x0=sum(x)/n #計算均值y0=sum(y)/ncovariance-sum(x-x0)*(y-y0)/(n-1)covariancestandardx-sqrt(sum(x-x0)2)/(n-1)standardxstanda

7、rdy-sqrt(sum(y-y0)2)/(n-1)standardycorrxy=covariance/(standardx*standardy)corrxy#Jaccardx=c(1,1,0,1,0,1)y=c(1,1,1,0,0,1)xy-sum(x*y)x2=sum(x2)y2=sum(y2)EJ=xy/(x2+y2-xy)EJ#（e）x=(2,-1,0,2,0,-3),y=(-1,-1,-1,0,0,-1)#余弦x=c(2,-1,0,2,0,-3)y=c(-1,-1,-1,0,0,-1)xy-sum(x*y)x1=sqrt(sum(x2)y1=sqrt(sum(y2)cosxy=xy/(x1*y1)cosxy#相關x=c(2,-1,0,2,0,-3)y=c(-1,-1,-1,0,0,-1)n=length(x) #求x的字符串長度x0=sum(x)/n #計算均值y0=sum(y)/ncovariance-sum(x-x0)*(y-y0)/(n-1)covariancestandardx-sqrt(