Question

Been using SAS for 6 years and migrating across to R. I used to use proc contents to get a healthy description of a table, a characteristic and a data type.

Using str(tableName) I can see the type but not the vector position in a data frame.

Using name(tableName) I can see the names and positions of the vectors but not the type.

Using summary(tableName) I can see the quantiles/category but not the type easily or vector position.

Is there a way I can just get a list of
Name vectorPosition type min max avg med [..]

Answer 1

You can use lapply to call a function
on each column of the data.frame,
and compute all the quantities you want in that function.

summary_text <- function(d) {
  do.call(rbind, lapply( d, function(u)
    data.frame(
      Type    = class(u)[1],
      Min     = if(is.numeric(u)) min(   u, na.rm=TRUE) else NA,
      Mean    = if(is.numeric(u)) mean(  u, na.rm=TRUE) else NA,
      Median  = if(is.numeric(u)) median(u, na.rm=TRUE) else NA,
      Max     = if(is.numeric(u)) max(   u, na.rm=TRUE) else NA,
      Missing = sum(is.na(u))
    )    
  ) )
}
summary_text(iris)

But I personnally prefer to look at the data graphically:
the following function will draw a histogram and a quantile-quantile plot
for each numeric variable, and a barplot for each factor,
on a single page. If you have 20 to 30 variables, it should remain usable.

summary_plot <- function(d, aspect=1) {
  # Split the screen: find the optimal number of columns 
  # and rows to be as close as possible from the desired aspect ratio.
  n <- ncol(d)
  dx <- par()$din[1]
  dy <- par()$din[2]
  f <- function(u,v) {
    if( u*v >= n && (u-1)*v < n && u*(v-1) < n ) {
      abs(log((dx/u)/(dy/v)) - log(aspect))
    } else { 
      NA 
    }
  }
  f <- Vectorize(f)
  r <- outer( 1:n, 1:n, f )
  r <- which( r == min(r,na.rm=TRUE), arr.ind=TRUE )
  r <- r[1,2:1]

  op <- par(mfrow=c(1,1),mar=c(2,2,2,2))
  plot.new()
  if( is.null( names(d) ) ) { names(d) <- 1:ncol(d) }
  ij <- matrix(seq_len(prod(r)), nr=r[1], nc=r[2], byrow=TRUE)
  for(k in seq_len(ncol(d))) {
    i <- which(ij==k, arr.ind=TRUE)[1]
    j <- which(ij==k, arr.ind=TRUE)[2]
    i <- r[1] - i + 1
    f <- c(j-1,j,i-1,i) / c(r[2], r[2], r[1], r[1] )
    par(fig=f, new=TRUE)
    if(is.numeric(d[,k])) { 
      hist(d[,k], las=1, col="grey", main=names(d)[k], xlab="", ylab="")
      o <- par(fig=c(
          f[1]*.4  + f[2]*.6,
          f[1]*.15 + f[2]*.85,
          f[3]*.4  + f[4]*.6,
          f[3]*.15 + f[4]*.85
        ), 
        new=TRUE,
        mar=c(0,0,0,0)
      )
      qqnorm(d[,k],axes=FALSE,xlab="",ylab="",main="")
      qqline(d[,k])
      box()
      par(o)
    } else {
      o <- par(mar=c(2,5,2,2))
      barplot(table(d[,k]), horiz=TRUE, las=1, main=names(d)[k])
      par(o)
    }
  }
  par(op)
}
summary_plot(iris)