similar to: same key row merge in dataframe

Hi, dat1<- read.table(text=" id??????????????? t???????????????????? scores 2???????????????? 0??????????????????????? 1.2 2???????????????? 2???????????????????????? 2.3 2???????????????? 3??????????????????????? 3.6 2???????????????? 4??????????????????????? 5.6 2???????????????? 6??????????????????????? 7.8 3???????????????? 0??????????????????????? 1.6 3????????????????

Hi, May be you can try this: dat1New<-? dat1[!(duplicated(dat1$gene)|duplicated(dat1$gene,fromLast=TRUE)),] dat2<-dat1[duplicated(dat1$gene)|duplicated(dat1$gene,fromLast=TRUE),] ?lst1<-split(dat2,dat2$gene) dat3<-unsplit(lapply(lst1,function(x) {x1<- sum(apply(x[,6:32],2,function(y) y[1]>=y[2]));x2<- sum(apply(x[,6:32],2, function(y) y[1]<=y[2])); if(x1>x2) x[1,] else

Hi, Assuming that your dataset is similar to the one below: set.seed(25) dat1<- data.frame(Algae.Mass=sample(40:50,10,replace=TRUE),Seagrass.Mass=sample(30:70,10,replace=TRUE),Terrestrial.Mass=sample(80:100,10,replace=TRUE),Other.Mass=sample(40:60,10,replace=TRUE),Site.X.Treatment=rep(c("ALA1A","ALA1U"),each=5),stringsAsFactors=FALSE) library(reshape2)

Hi, You may need ?split(), or ?aggregate() or ?ddply() from library(plyr) dat1 <- read.table(tex="1 2 4 7 8 9 1 4 5 8 9 1 4 5 6 9 2 3 4 8 3 6 7 8 1 5 6 9 2 5 7 9",header=FALSE,sep="",fill=TRUE)? ## ?res1 <- do.call(rbind,lapply(split(dat1,dat1[,1]),function(x) c(V1=x[1,1],colSums(x[,-1],na.rm=TRUE))))

Ira, obj_name<- load("arun.RData") Pred1<- get(obj_name[1]) Actual1<- get(obj_name[2]) dat2<- data.frame(S1=rep(Pred1[,1],ncol(Pred1)-1),variable=rep(colnames(Pred1)[-1],each=nrow(Pred1)),Predict=unlist(Pred1[,-1],use.names=FALSE),Actual=unlist(Actual1[,-1],use.names=FALSE),stringsAsFactors=FALSE) dat2New<- dat2[!(is.na(dat2$Predict)|is.na(dat2$Actual)),] ?dat3<-

Hi, May be this helps: dat1<- read.table(text=" pbnr??????? dat? dep? dys? sop? ago? mis age female 1 10023 1994-02-21 0.75 1.00 0.50 0.50 0.75? 35????? 1 2 10023 1994-05-25 0.75 1.00 0.50 0.50 0.75? 35????? 1 3 10028 1994-02-01 2.00 1.75 3.00 0.50 1.50? 42????? 1 4 10028 1999-01-15 1.25 0.75 2.25 0.50 0.25? 42????? 1 5 10053 1994-03-16 2.50 0.75 1.25 0.50 1.25? 22????? 1 6 10053

Dear Elisa, Try this: vec1<-c(33,18,13,47,30,10,6,21,39,25,40,29,14,16,44,1,41,4,15,20,46,32,38,5,31,12,48,27,36,24,34,2,35,11,42,9,8,7,26,22,43,17,19,28,23,3,49,37,50,45) vec2<-vec1[1:26] names(vec2)<-LETTERS[1:26] label1<-unlist(lapply(mapply(c,lapply(seq(0,45,5),function(x) x),lapply(seq(5,50,5),function(x) x),SIMPLIFY=FALSE),function(i)

Hi, (Please use ?dput() to share the example dataset. Avoid using images to show dataset. Also, please read the posting guide esp. regarding home work, assignments etc.) res <- sapply(Gene[,-1],function(x) tapply(x,list(Gene$Genotype),mean)) #or res2 <-? aggregate(.~Genotype, data=Gene,mean) #or library(plyr) ?res3 <- ddply(Gene,.(Genotype),numcolwise(mean)) identical(res2,res3)

Hello, I was wandering if it is possible to perform on a dataframe called 'all' a shapiro wilk normality test for COUNTS by variable Group ACTIVITY? Could it be done using plyer? I saw an eg that applies to an array but not to a dataframe: lapply(split(dataset1$Height,dataset1$Group),shapiro.test) Any thoughts would be much appreciated. My dataframe is in shape: dat ACTIVIT

Hello R community, I am trying to combine two CSV files that look like this: File A Row_ID_CR, Data1, Data2, Data3 1, aa, bb, cc 2, dd, ee, ff File B Row_ID_N, Src_Row_ID, DataN1 1a, 1, This is comment 1 2a, 1, This is comment 2 3a,

Hi, Your question is still not clear. May be this helps: dat2<- read.table(text=" patient_id????? t???????? scores 1????????????????????? 0??????????????? 1.6 1????????????????????? 1??????????????? 2.6 1????????????????????? 2???????????????? 2.2 1????????????????????? 3???????????????? 1.8 2????????????????????? 0????????????????? 2.3 2?????????????????????? 2???????????????? 2.5

Hi, Try: dat1 <- read.csv("precipitationRglimclim.csv",header=TRUE,stringsAsFactors=FALSE,sep="\t") library(reshape2) dat2M <- melt(dat1,id.var=c("year","month","day")) dat2M1 <- dat2M[with(dat2M,order(year,month,day,variable)),] ?dim(dat2M1) #[1] 1972320?????? 5 ?row.names(dat2M1) <- 1:nrow(dat2M1) ?colnames(dat2M1)[4:5] <-

Hello, Apologies for a similar earlier post. I didn't include enough details in that one. I am having a little trouble subsetting some data based on a grouping variable. I am using an instrument that does depth profiles of a water column. The instrument records on the way down as well as the way up. So thanks to an off-list reply I can subset the data so that all data collected at the

Hi Jakob, dat1<-read.table(text=" TIME, Value1, Value2 01.08.2011 02:30:00, 4.4, 4.7 01.09.2011 03:00:00, 4.2, 4.3 01.11.2011 01:00:00, 3.5, 4.3 01.12.2011 01:40:00, 3.4, 4.5 01.01.2012 02:00:00, 4.8, 5.3 01.02.2012 02:30:00, 4.9, 5.2 01.08.2012 02:30:00, 4.1, 4.7 01.12.2012 03:00:00, 4.7, 4.3 01.01.2013 01:00:00, 3, 4.3 01.01.2013 01:30:00, 3.8, 4.1 01.01.2013 02:00:00, 3.8,

Hi, I am not sure I understand your question correctly. dat1<- read.table(text=" id??????????? responsed_at???????????????? number_of_connection????????????????? scores 1????????????????? 12-01-2010?????????????????????????????????? 1????????????????????????????????????????????? 2 1????????????????? 15-02-2010??????????????????????????????????

Hi, I guess you meant this: dat2<- read.table(text=" patient_id????? t???????? scores 1????????????????????? 0??????????????? 1.6 1????????????????????? 1??????????????? 2.6 1????????????????????? 2???????????????? 2.2 1????????????????????? 3???????????????? 1.8 2????????????????????? 0????????????????? 2.3 2?????????????????????? 2???????????????? 2.5 2?????????????????????

Hi, May be you can try this: obj_name<- load("arun.RData") Pred1<- get(obj_name[1]) Actual1<- get(obj_name[2]) library(reshape2) dat<-cbind(melt(Pred1,id.vars="S1"),value2=melt(Actual1,id.vars="S1")[,3])? # to reshape to long form colnames(dat)[3:4]<- c("Predict","Actual") dat$variable<- as.character(dat$variable) #not that

H all, I have relative abundance data from >100 sites. This is from acoustic monitoring and usually the data is for 2-3 nights but in some cases my be longer like months or years for each location.. The data output from my management data base is proved by species by night for each location so data frame would look like this below. What I need to do is sum the Survey_time by Spec_Code for

HI Fares, You could try this: dat1<- read.table(text=" date????? donation 3jan2003?? 20235 4jan2003?? 25655 5jan2003?? 225860 6jan2003?? 289658 7jan2003?? 243889 8jan2003?? 244338 9jan2003?? 243889 ",sep="",header=TRUE,stringsAsFactors=FALSE) The post is not very specific as to what you need.? I hope this works for you. library(xts)

Hi, May be this helps: dat1<- read.csv("dat7.csv",header=TRUE,stringsAsFactors=FALSE,sep="\t") dat.bru<- dat1[!is.na(dat1$evnmt_brutal),] fun2<- function(dat){?? ????? lst1<- split(dat,dat$patient_id) ??? lst2<- lapply(lst1,function(x) x[cumsum(x$evnmt_brutal==0)>0,]) ??? lst3<- lapply(lst2,function(x) x[!(all(x$evnmt_brutal==1)|all(x$evnmt_brutal==0)),])