I have a dataframe with 67 items that looks like this:
df <- data.frame("item"= c("item1", "item2", "item3", "item4", "item5"), "variable1"=c(10.51, 16.54, 12.35, 9.44, 20.11), "variable2"=c(15.65, 25.68, 14.48, 19.87, 30.21), "variable3"=c(19.35, 45.86, 39.25, 39.43, 34.08))
Now I want an even subsample of items, where, if it was only one variable, I would want every 7th item, but since I have three variables I want a subsample which comes closes to all three variables being evenly spread out over the value frame for each variable.
I was thinking of creating 'bins' of data where I cluster items with similiar values for each variable, but I would still not know how to execute this in R Somebody?
