05FZ多及元数据分析.pptx

多元数据分析;实数轴上的数据: 经典多元分析内容回顾;经典:主成份分析及因子分析;例5.1 洛杉矶街区(LA.Neighborhoods.csv).} 该数据为美国普查局2000年数据. 一共有110个街区, 15个变量, 变量情况如下表:;主成份分析;(loadings=sweep(a$vec,2,sqrt(a$value),*))-b #计算载荷 par(mfrow=c(1,2)) plot(b[,1:2], type=n, xlab=Component 1 (42%), ylab=Component 2 (17%), xlim=c(-1.2,1.2),ylim=c(-1.2,1.2),main=Loadings) text(b[,1],b[,2],names(u[,-1])) abline(h=0);abline(v=0) plot(b[,3:4], type=n, xlab=Component 3 (11%), ylab=Component 4 (9%), xlim=c(-1.2,1.2), ylim=c(-1.2,1.2),main=Loadings) text(b[,3],b[,4],names(u[,-1])) abline(h=0);abline(v=0) par(mfrow=c(1,1));par(mfrow=c(1,2)) sc=as.matrix(scale(u[,-1]))%*%a$ve[,1:4] #计算得分 plot(sc[,1],sc[,2],type=n,ylim=c(-6,6),xlim=c(-7,6), main=Sample Principal Components, xlab=Component 1, ylab=Component 2) text(sc[,1],sc[,2],u[,1],cex=.4);abline(v=0,col=2);abline(h=0,col=2) plot(sc[,3],sc[,4],type=n,ylim=c(-6,6),xlim=c(-7,6), main=Sample Principal Components, xlab=Component 3, ylab=Component 4) text(sc[,3],sc[,4],u[,1],cex=.4);abline(v=0,col=2);abline(h=0,col=2) par(mfrow=c(1,1));因子分析;#下面因子分析时默认旋转rotation =varimax: (a=factanal(factors=2,scale(u[,-1]),scores=regression)) (a$loadings);(a$scores) par(mfrow=c(1,2)) plot(a$loadings[,1:2],type=n,ylim=c(-1.1,1.1), xlim=c(-1.1,1.2), xlab=Factor 1, ylab=Factor 2, main=Loadings) abline(h=0);abline(v=0) text(a$loadings[,1],a$loadings[,2], labels=row.names(a$loadings),cex=.6) plot(a$loadings[,3:4],type=n,ylim=c(-1.1,1.1),xlim=c(-1.1,1.2), xlab=Factor 3, ylab=Factor 4, main=Loadings) abline(h=0);abline(v=0) text(a$loadings[,3],a$loadings[,4], labels=row.names(a$loadings),cex=.6) plot(a$scores[,1:2],type=n,ylim=c(-2,2.2),xlim=c(-3.5,3), xlab=Factor 1, ylab=Factor 2, main=Factor Scores) abline(h=0);abline(v=0) text(a$scores[,1],a$scores[,2],labels=u[,1],cex=.4) plot(a$scores[,3:4],type=n,ylim=c(-2,4),xlim=c(-5,1.5), xlab=Factor 3, ylab=Factor 4, main=Factor Scores, ) abline(h=0);abline(v=0) text(a$scores[,3],a$scores[,4],labels=u[,1],cex=.4);分层聚类及k均值聚类;K均值聚