[R] Finding unique terms

[Dénes Tóth]

On 10/12/2018 12:12 AM, roslinazairimah zakaria wrote:
> Dear r-users,
> 
> I have this data:
> 
> structure(list(STUDENT_ID = structure(c(1L, 1L, 1L, 1L, 1L, 1L,
> 2L, 2L, 2L, 2L, 2L), .Label = c("AA15285", "AA15286"), class = "factor"),
>      COURSE_CODE = structure(c(1L, 2L, 5L, 6L, 7L, 8L, 2L, 3L,
>      4L, 5L, 6L), .Label = c("BAA1113", "BAA1322", "BAA2113",
>      "BAA2513", "BAA2713", "BAA2921", "BAA4273", "BAA4513"), class =
> "factor"),
>      PO1M = c(155.7, 48.9, 83.2, NA, NA, NA, 48.05, 68.4, 41.65,
>      82.35, NA), PO1T = c(180, 70, 100, NA, NA, NA, 70, 100, 60,
>      100, NA), PO2M = c(NA, NA, NA, 37, NA, NA, NA, NA, NA, NA,
>      41), PO2T = c(NA, NA, NA, 50, NA, NA, NA, NA, NA, NA, 50),
>      X = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA), X.1 = c(NA,
>      NA, NA, NA, NA, NA, NA, NA, NA, NA, NA)), .Names = c("STUDENT_ID",
> "COURSE_CODE", "PO1M", "PO1T", "PO2M", "PO2T", "X", "X.1"), class =
> "data.frame", row.names = c(NA,
> -11L))
> 
> I want to combine the same Student ID and add up all the values for PO1M,
> PO1T,...,PO2T obtained by the same ID.

dat <- structure(list(STUDENT_ID = structure(c(1L, 1L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 2L), .Label = c("AA15285", "AA15286"), class = "factor"),
     COURSE_CODE = structure(c(1L, 2L, 5L, 6L, 7L, 8L, 2L, 3L,
     4L, 5L, 6L), .Label = c("BAA1113", "BAA1322", "BAA2113",
     "BAA2513", "BAA2713", "BAA2921", "BAA4273", "BAA4513"), class =
"factor"),
     PO1M = c(155.7, 48.9, 83.2, NA, NA, NA, 48.05, 68.4, 41.65,
     82.35, NA), PO1T = c(180, 70, 100, NA, NA, NA, 70, 100, 60,
     100, NA), PO2M = c(NA, NA, NA, 37, NA, NA, NA, NA, NA, NA,
     41), PO2T = c(NA, NA, NA, 50, NA, NA, NA, NA, NA, NA, 50),
     X = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA), X.1 = c(NA,
     NA, NA, NA, NA, NA, NA, NA, NA, NA, NA)), .Names = c("STUDENT_ID",
"COURSE_CODE", "PO1M", "PO1T", "PO2M", "PO2T", "X", "X.1"), class =
"data.frame", row.names = c(NA,
-11L))

# I assume you would like to add up the values with na.rm = TRUE
meanFn <- function(x) mean(x, na.rm = TRUE)

# see ?aggregate
aggregate(dat[, c("PO1M", "PO1T", "PO2M")],
           by = dat["STUDENT_ID"],
           FUN = meanFn)

# if you have largish or large data
library(data.table)
dat2 <- as.data.table(dat)
dat2[, lapply(.SD, meanFn),
      by = STUDENT_ID,
      .SDcols = c("PO1M", "PO1T", "PO2M")]


Regards,
Denes


> 
> How do I do that?
> Thank you for any help given.
>