How to create a lag variable within each group?

Question

I have a data.table:

set.seed(1)
data <- data.table(time = c(1:3, 1:4),
                   groups = c(rep(c(\"b\", \"a\"), c(3, 4))),
                   v         


        

Answer 1

If you wanted to make sure that you avoided any issue with ordering the data, you can do this, using dplyr, manually with something like:

df <- data.frame(Names = c(rep('Dan',50),rep('Dave',100)),
            Dates = c(seq(1,100,by=2),seq(1,100,by=1)),
            Values = rnorm(150,0,1))

df <- df %>% group_by(Names) %>% mutate(Rank=rank(Dates),
                                    RankDown=Rank-1)

df <- df %>% left_join(select(df,Rank,ValueDown=Values,Names),by=c('RankDown'='Rank','Names')
) %>% select(-Rank,-RankDown)

head(df)

Or alternatively I like the idea of putting it in a function with a chosen grouping variable(s), ranking column (like Date or otherwise), and chosen number of lags. This also requires lazyeval as well as dplyr.

groupLag <- function(mydf,grouping,ranking,lag){
  df <- mydf
  groupL <- lapply(grouping,as.symbol)

  names <- c('Rank','RankDown')
  foos <- list(interp(~rank(var),var=as.name(ranking)),~Rank-lag)

  df <- df %>% group_by_(.dots=groupL) %>% mutate_(.dots=setNames(foos,names))

  selectedNames <- c('Rank','Values',grouping)
  df2 <- df %>% select_(.dots=selectedNames)
  colnames(df2) <- c('Rank','ValueDown',grouping)

  df <- df %>% left_join(df2,by=c('RankDown'='Rank',grouping)) %>% select(-Rank,-RankDown)

  return(df)
}

groupLag(df,c('Names'),c('Dates'),1)