Reformat dataset in R into rows as levels and columns as range

Question

I have a dataset that looks like:

partyid            coninc
Ind,Near Dem       25926
Not Str Democrat   33333
Not Str Democrat   41667
Strong Democrat    69444
Ind,Near Dem       60185
Ind,Near Dem       50926
Ind,Near Dem       18519
Strong Democrat    3704
Strong Democrat    25926
Strong Democrat    18519
Not Str Republican 18519
Strong Democrat    18519
Not Str Democrat   18519

What I want to do is format the dataset into something like this:

partyid             0-50,000   50,000-100,000   100,000-150,000   >150,000
Strong Democrat     2344       3423             4342              54
Not Str Democrat    2643       934              ..
Ind, Near Dem       7656       343              ..
Ind, Near Rep       7655       833              .. 
Not Str Republican  2443       343
Strong Republican   3444       773

i.e Sort the rows by the levels of partyid variable and the columns by the count of range of coninc variable.

A dput of my data:

structure(list(partyid = structure(c(3L, 2L, 2L, 1L, 3L, 3L, 3L, 1L, 1L, 1L, 5L, 1L, 2L, 1L, 1L, 4L, 4L, 3L, 4L, 3L), .Label = c("Strong Democrat", "Not Str Democrat", "Ind,Near Dem", "Ind,Near Rep", "Not Str Republican", "Strong Republican"), class = "factor"), coninc = c(25926L, 33333L, 41667L, 69444L, 60185L, 50926L, 18519L, 3704L, 25926L, 18519L, 18519L, 18519L, 18519L, 25926L, 18519L, 33333L, 25926L, 60185L, 69444L, 50926L)), .Names = c("partyid", "coninc"), row.names = c(1L, 2L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L), class = "data.frame")

Answer 1

You can do that quite easily with the plyr package (as your sample data are a bit hard to read, I deleted the commas and spaces in partyid):

# creating sample data
dat <- structure(list(partyid = structure(c(3L, 2L, 2L, 1L, 3L, 3L, 3L, 1L, 1L, 1L, 5L, 1L, 2L, 1L, 1L, 4L, 4L, 3L, 4L, 3L), .Label = c("Strong Democrat", "Not Str Democrat", "Ind,Near Dem", "Ind,Near Rep", "Not Str Republican", "Strong Republican"), class = "factor"), coninc = c(25926L, 33333L, 41667L, 69444L, 60185L, 50926L, 18519L, 3704L, 25926L, 18519L, 18519L, 18519L, 18519L, 25926L, 18519L, 33333L, 25926L, 60185L, 69444L, 50926L)), .Names = c("partyid", "coninc"), row.names = c(1L, 2L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, 16L, 17L, 18L, 19L, 20L, 21L), class = "data.frame")

# summarising the data with plyr
require(plyr)
dat2 <- ddply(dat, .(partyid), summarise,
              zero = sum(coninc < 50001),
              fifty = sum(coninc > 50000 & coninc < 100001),
              hundred = sum(coninc > 100000 & coninc < 150001),
              hfifty = sum(coninc > 150000))

This results in the following output:

dat2 <- structure(list(partyid = structure(1:5, .Label = c("Strong Democrat", "Not Str Democrat", "Ind,Near Dem", "Ind,Near Rep", "Not Str Republican", "Strong Republican"), class = "factor"), zero = c(6L, 3L, 2L, 2L, 1L), fifty = c(1L, 0L, 4L, 1L, 0L), hundred = c(0L, 0L, 0L, 0L, 0L), hfifty = c(0L, 0L, 0L, 0L, 0L)), .Names = c("partyid", "zero", "fifty", "hundred", "hfifty"), row.names = c(NA, -5L), class = "data.frame")

Answer 2

You could just use cut and table in base R:

dat$cat <- cut(dat$coninc, breaks = c(0, 50000, 100000, 150000, Inf),
               labels = c("< 50K", "50K - 100K", "100K - 150K", "> 150K"))
table(dat$partyid, dat$cat)
#                     
#                      < 50K 50K - 100K 100K - 150K > 150K
#   Strong Democrat        6          1           0      0
#   Not Str Democrat       3          0           0      0
#   Ind,Near Dem           2          4           0      0
#   Ind,Near Rep           2          1           0      0
#   Not Str Republican     1          0           0      0
#   Strong Republican      0          0           0      0