Hi, No problem. There are a couple of other libraries which deal with summary statistics: library(pastecs) ?stat.desc() #
library(matrixStats) #Using the functions from package: matrixStats fun1<-function(x){ res<-rbind(colMins(x),colQuantiles(x)[,2],colMedians(x),colMeans(x),colSds(x),colQuantiles(x)[,4],colIQRs(x),colMaxs(x)) row.names(res)<-c("Min.","1st Qu.","Median","Mean","sd","3rd Qu.","IQR","Max.") res} set.seed(125) x <- matrix(sample(1:80),nrow=8) colnames(x)<- paste("Col",1:ncol(x),sep="") fun1(x) # Col1 Col2 Col3 Col4 Col5 Col6 Col7 Col8 #Min. 10.00000 1.00000 17.00000 3.00000 18.00000 11.00000 13.00000 15.00000 #1st Qu. 24.75000 29.50000 26.00000 7.75000 40.00000 17.25000 27.50000 34.75000 #Median 34.00000 46.00000 42.50000 35.50000 49.50000 23.50000 51.50000 51.50000 #Mean 42.50000 42.75000 41.75000 35.75000 44.87500 26.87500 44.75000 50.12500 #sd 25.05993 27.77846 19.57221 28.40397 16.39196 16.60841 21.97239 25.51995 #3rd Qu. 67.75000 58.50000 50.00000 63.25000 54.25000 30.25000 56.25000 70.50000 #IQR 43.00000 29.00000 24.00000 55.50000 14.25000 13.00000 28.75000 35.75000 #Max. 74.00000 77.00000 76.00000 70.00000 65.00000 63.00000 79.00000 80.00000 # Col9 Col10 #Min. 2.00000 6.00000 #1st Qu. 24.50000 12.50000 #Median 33.50000 48.00000 #Mean 34.87500 40.75000 #sd 24.39811 28.21727 #3rd Qu. 45.25000 63.00000 #IQR 20.75000 50.50000 #Max. 71.00000 72.00000 I thought this could be faster than the previous methods. But, it was the slowest. set.seed(125) x1 <- matrix(sample(1:800000),nrow=1000) colnames(x)<- paste("Col",1:ncol(x1),sep="") system.time(fun1(x1)) # user system elapsed # 0.968 0.000 0.956 A.K. ________________________________ From: Fares Said <frespi...@hotmail.com> To: arun <smartpink...@yahoo.com> Cc: Pete Brecknock <peter.breckn...@bp.com>; R help <r-help@r-project.org> Sent: Friday, November 23, 2012 10:23 AM Subject: Re: [R] Summary statistics for matrix columns Thank you all Sent from my iPhone On 2012-11-23, at 10:19, "arun" <smartpink...@yahoo.com> wrote: > HI, > You are right. > It is slower when compared to Pete's solution: > set.seed(125) > x <- matrix(sample(1:800000),nrow=1000) > colnames(x)<- paste("Col",1:ncol(x),sep="") > > system.time({ > res<-sapply(data.frame(x),function(x) c(summary(x),sd=sd(x),IQR=IQR(x))) > res1<-as.matrix(res) > res2<-res1[c(1:4,7,5,8,6),] }) > # user system elapsed > # 0.596 0.000 0.597 > > system.time({ > res<-apply(x,2,function(x) c(Min=min(x), > "1st Qu" =quantile(x, 0.25,names=FALSE), > Median = quantile(x, 0.5, names=FALSE), > Mean= mean(x), > Sd=sd(x), > "3rd Qu" = quantile(x,0.75,names=FALSE), > IQR=IQR(x), > Max = max(x))) }) > # user system elapsed > # 0.384 0.000 0.384 > > > A.K. > > > > ----- Original Message ----- > From: Pete Brecknock <peter.breckn...@bp.com> > To: r-help@r-project.org > Cc: > Sent: Friday, November 23, 2012 8:42 AM > Subject: Re: [R] Summary statistics for matrix columns > > frespider wrote >> Hi, >> >> it is possible. but don't you think it will slow the code if you convert >> to data.frame? >> >> Thanks >> >> Date: Thu, 22 Nov 2012 18:31:35 -0800 >> From: > >> ml-node+s789695n4650500h51@.nabble > >> To: > >> frespider@ > >> Subject: RE: Summary statistics for matrix columns >> >> >> >> HI, >> >> Is it possible to use as.matrix()? >> >> res<-sapply(data.frame(x),function(x) c(summary(x),sd=sd(x),IQR=IQR(x))) >> >> res1<-as.matrix(res) >> >> is.matrix(res1) >> >> #[1] TRUE >> >> res1[c(1:4,7,5,8,6),] >> >> # Col1 Col2 Col3 Col4 Col5 Col6 Col7 >> Col8 >> >> #Min. 10.00000 1.00000 17.00000 3.00000 18.00000 11.00000 13.00000 >> 15.00000 >> >> #1st Qu. 24.75000 29.50000 26.00000 7.75000 40.00000 17.25000 27.50000 >> 34.75000 >> >> #Median 34.00000 46.00000 42.50000 35.50000 49.50000 23.50000 51.50000 >> 51.50000 >> >> #Mean 42.50000 42.75000 41.75000 35.75000 44.88000 26.88000 44.75000 >> 50.12000 >> >> #sd 25.05993 27.77846 19.57221 28.40397 16.39196 16.60841 21.97239 >> 25.51995 >> >> #3rd Qu. 67.75000 58.50000 50.00000 63.25000 54.25000 30.25000 56.25000 >> 70.50000 >> >> #IQR 43.00000 29.00000 24.00000 55.50000 14.25000 13.00000 28.75000 >> 35.75000 >> >> #Max. 74.00000 77.00000 76.00000 70.00000 65.00000 63.00000 79.00000 >> 80.00000 >> >> # Col9 Col10 >> >> #Min. 2.00000 6.00000 >> >> #1st Qu. 24.50000 12.50000 >> >> #Median 33.50000 48.00000 >> >> #Mean 34.88000 40.75000 >> >> #sd 24.39811 28.21727 >> >> #3rd Qu. 45.25000 63.00000 >> >> #IQR 20.75000 50.50000 >> >> #Max. 71.00000 72.00000 >> >> Solves the order and the matrix output! >> >> A.K. >> >> >> >> >> >> >> >> >> >> >> >> >> >> >> If you reply to this email, your message will be added to the >>discussion >> below: >> >> http://r.789695.n4.nabble.com/Summary-statistics-for-matrix-columns-tp4650489p4650500.html >> >> >> >> To unsubscribe from Summary statistics for matrix columns, click >>here. >> >> NAML > > Then maybe .... > > x <- matrix(sample(1:8000),nrow=100) > colnames(x)<- paste("Col",1:ncol(x),sep="") > > apply(x,2,function(x) c(Min=min(x), > "1st Qu" =quantile(x, 0.25,names=FALSE), > Median = quantile(x, 0.5, names=FALSE), > Mean= mean(x), > Sd=sd(x), > "3rd Qu" = quantile(x,0.75,names=FALSE), > IQR=IQR(x), > Max = max(x))) > > HTH > > Pete > > > > -- > View this message in context: > http://r.789695.n4.nabble.com/Summary-statistics-for-matrix-columns-tp4650489p4650547.html > Sent from the R help mailing list archive at Nabble.com. > > ______________________________________________ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. > ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.