remove factors with criteria
studenttable <- table(data$Anon.Student.Id)

l5eh0S53tB Qwq8d0du28 tyU2s0MBzm dvG32rxRzQ i8f2gg51r5 XL0eQIoG72
  9890       7989       7665       7242       6928       6651

biginstances <- studenttable>1000

bigdata <- subset(data, (biginstances[Anon.Student.Id]))

# Create some fake data
dat <- data.frame(id = rep(letters[1:5], 1:5), y = rnorm(15))
# tabulate the id variable
tab <- table(dat$id)
# Get the names of the ids that we care about.
# In this case the ids that occur >= 3 times
idx <- names(tab)[tab >=3]
# Only look at the data that we care about
dat[dat$id %in% idx,]

biginstances <- studenttable>1000

bigdata <- subset(data, (biginstances[Anon.Student.Id]))

> fac <- factor(rep(letters[1:3],each = 3))
> fac
[1] a a a b b b c c c
Levels: a b c
> fac[-(1:3)]
[1] b b b c c c
Levels: a b c
> droplevels(fac[-(1:3)])
[1] b b b c c c
Levels: b c

require(plyr)

set.seed(123)
Data <- data.frame(var1 = sample(LETTERS[1:5], size = 100, replace = TRUE),
                   var2 = 1:100)


R> table(Data$var1)

 A  B  C  D  E
19 20 21 22 18


## rows with category less than 20

mytable <- count(Data, vars = "var1")

## mytable <- as.data.frame(table(Data$var1))

R> str(mytable)
'data.frame':   5 obs. of  2 variables:
 $ var1: Factor w/ 5 levels "A","B","C","D",..: 1 2 3 4 5
 $ freq: int  19 20 21 22 18

Data <- join(Data, mytable)

## Data <- merge(Data, mytable)

R> str(Data)
'data.frame':   100 obs. of  3 variables:
 $ var1: Factor w/ 5 levels "A","B","C","D",..: 3 2 3 5 3 5 5 4 3 1 ...
 $ var2: int  1 2 3 4 5 6 7 8 9 10 ...
 $ freq: int  21 20 21 18 21 18 18 22 21 19 ...



mysubset <- droplevels(subset(Data, freq > 20))

R> table(mysubset$var1)

 C  D
21 22

studenttable <- sort(studenttable, decreasing=TRUE)

sum(studenttable>1000)
230
sum(studenttable<1000)
344
344+230=574

idx <- names(studenttable[1:230])
bigdata <- data[data$Anon.Student.Id %in% idx,]

bigstudenttable <- table(bigdata$Anon.Student.Id)