Create a panel data frame

Question

I would like to create a panel from a dataset that has one observation for every given time period such that every unit has a new observation for every time period. Using th

Answer 1

Using data.table:

require(data.table)
DT <- data.table(frame, key=c("id", "year"))
comb <- CJ(1:4, 2005:2008) # like 'expand.grid', but faster + sets key
ans <- DT[comb][is.na(y), y:=0L] # perform a join (DT[comb]), then set NAs to 0
#     id year y
#  1:  1 2005 1
#  2:  1 2006 0
#  3:  1 2007 0
#  4:  1 2008 0
#  5:  2 2005 0
#  6:  2 2006 0
#  7:  2 2007 0
#  8:  2 2008 0
#  9:  3 2005 0
# 10:  3 2006 0
# 11:  3 2007 0
# 12:  3 2008 0
# 13:  4 2005 0
# 14:  4 2006 0
# 15:  4 2007 1
# 16:  4 2008 0

Answer 2

1) reshape2 Create a grid g of all years and id values crossed and rbind it with frame.

Then using the reshape2 package cast frame from long to wide form and then melt it back to long form. Finally rearrange the rows and columns as desired.

The lines ending in one # are only to ensure that every year is present so if we knew that were the case those lines could be omitted. The line ending in ## is only to rearrange the rows and columns so if that did not matter that line could be omitted too.

library(reshape2)

g <- with(frame, expand.grid(year = seq(min(year), max(year)), id = unique(id), y = 0)) #
frame <- rbind(frame, g) #

wide <- dcast(frame, year ~ id, fill = 0, fun = sum, value.var = "y")
long <- melt(wide, id = "year", variable.name = "id", value.name = "y")

long <- long[order(long$id, long$year), c("id", "year", "y")] ##

giving:

> long
   id year y
1   1 2005 1
2   1 2006 0
3   1 2007 0
4   1 2008 0
5   2 2005 0
6   2 2006 0
7   2 2007 0
8   2 2008 0
9   3 2005 0
10  3 2006 0
11  3 2007 0
12  3 2008 0
13  4 2005 0
14  4 2006 0
15  4 2007 1
16  4 2008 0

2) aggregate A shorter solution would be to run just the two lines that end with # above and then follow those with an aggregate as shown. This solution uses no addon packages.

g <- with(frame, expand.grid(year = seq(min(year), max(year)), id = unique(id), y = 0)) #
frame <- rbind(frame, g) # 

aggregate(y ~ year + id, frame, sum)[c("id", "year", "y")]

This gives the same answer as solution (1) except as noted by a commenter solution (1) above makes id a factor whereas it is not in this solution.

Answer 3

maybe not an elegant solution, but anyway:

df <- expand.grid(id=id, year=unique(year))
frame <- frame[frame$y != 0,]
df$y <- 0
df2 <- rbind(frame, df)
df2 <- df2[!duplicated(df2[,c("id", "year")]),]
df2 <- df2[order(df2$id, df2$year),]
rownames(df2) <- NULL
df2
# id year y
# 1   1 2005 1
# 2   1 2006 0
# 3   1 2007 0
# 4   1 2008 0
# 5   2 2005 0
# 6   2 2006 0
# 7   2 2007 0
# 8   2 2008 0
# 9   3 2005 0
# 10  3 2006 0
# 11  3 2007 0
# 12  3 2008 0
# 13  4 2005 0
# 14  4 2006 0
# 15  4 2007 1
# 16  4 2008 0