R relative frequency by date and operator

Previous Topic Next Topic
 
classic Classic list List threaded Threaded
2 messages Options
Reply | Threaded
Open this post in threaded view
|

R relative frequency by date and operator

moadeep
I have the data frame with the following structure

   Operator Score     Date Freq
1          A  Crap Apr 2013    0
2          D  Crap Apr 2013    0
3          J  Crap Apr 2013    0
4          L  Crap Apr 2013    0
5          M  Crap Apr 2013    0
6          A  Good Apr 2013    1
7          D  Good Apr 2013   14
8          J  Good Apr 2013   26
9          L  Good Apr 2013    3
10         M  Good Apr 2013    9

I would like to aggregate this data such that I can find the relative frequency of each score (Good, Ok, Poor and Crap) for each combination of month and operator. For example For operator A in the month Jan 2013 - I would like the following output

   Operator Score     Date Freq Rel.Freq
1          A  Crap Jan 2013    0       0
2          A  Poor Jan 2013    5      0.22
3          A  Good Jan 2013    15  0.65
4          A  Ok Jan 2013   3           0.13

i.e I would like to add a relative frequency column to my existing data.frame. I haven't got anywhere near an automated solution. The closest I have is

tmp <- subset(df, Operator == "A")
tmp$N.norm <- tmp$Freq/sum(ans2$Freq)

However this sums all data for operator A regardless of date. So I would need to subset again according to date. Is there a straightforward way to do this in R



<nabble_embed>structure(list(Operator = structure(c(1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L), .Label = c("A", "D", "J", "L", "M"), class = "factor"), Score = structure(c(1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L), .Label = c("Crap", "Good", "OK", "Poor"), class = "factor"), Date = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L ), .Label = c("Apr 2013", "Feb 2013", "Jan 2013", "Mar 2013", "May 2013"), class = "factor"), Freq = c(0L, 0L, 0L, 0L, 0L, 1L, 14L, 26L, 3L, 9L, 3L, 5L, 3L, 0L, 6L, 3L, 24L, 20L, 29L, 14L, 0L, 0L, 0L, 0L, 0L, 2L, 17L, 24L, 12L, 9L, 2L, 10L, 4L, 0L, 4L, 0L, 27L, 36L, 37L, 13L, 0L, 0L, 0L, 0L, 0L, 15L, 16L, 20L, 5L, 15L, 3L, 6L, 17L, 3L, 5L, 5L, 31L, 12L, 41L, 9L, 0L, 1L, 0L, 0L, 0L, 1L, 8L, 11L, 12L, 17L, 1L, 1L, 3L, 4L, 4L, 5L, 16L, 21L, 25L, 15L, 0L, 0L, 0L, 0L, 0L, 5L, 7L, 18L, 4L, 3L, 0L, 5L, 2L, 0L, 1L, 1L, 15L, 9L, 10L, 9L)), .Names = c("Operator", "Score", "Date", "Freq" ), row.names = c(NA, -100L), class = "data.frame")</nabble_embed>
Reply | Threaded
Open this post in threaded view
|

Re: R relative frequency by date and operator

arun kirshna
Hi,
Try either:
dat2<- structure(list(Operator = structure(c(1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L), .Label = c("A", "D", "J", "L", "M"), class = "factor"), Score = structure(c(1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L), .Label = c("Crap", "Good", "OK", "Poor"),
 class = "factor"), Date = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L ), .Label = c("Apr 2013", "Feb 2013", "Jan 2013", "Mar 2013", "May 2013"), class = "factor"), Freq = c(0L, 0L, 0L, 0L, 0L, 1L, 14L, 26L, 3L, 9L, 3L, 5L, 3L, 0L, 6L, 3L, 24L, 20L, 29L, 14L, 0L, 0L, 0L, 0L, 0L, 2L, 17L, 24L, 12L, 9L, 2L, 10L, 4L, 0L, 4L, 0L, 27L, 36L, 37L, 13L, 0L, 0L, 0L, 0L, 0L, 15L, 16L, 20L, 5L, 15L, 3L, 6L, 17L, 3L, 5L, 5L, 31L, 12L, 41L, 9L, 0L, 1L, 0L, 0L, 0L, 1L, 8L, 11L, 12L, 17L, 1L, 1L, 3L, 4L, 4L, 5L, 16L, 21L, 25L, 15L, 0L, 0L, 0L, 0L, 0L, 5L, 7L, 18L, 4L, 3L, 0L, 5L, 2L, 0L, 1L, 1L, 15L, 9L, 10L,
 9L)), .Names = c("Operator", "Score", "Date", "Freq" ), row.names = c(NA, -100L), class = "data.frame")

dat2[,1:3]<- lapply(dat2[,1:3],as.character)
res1<-unsplit(lapply(split(dat2,dat2$Operator),function(x) {x$Rel.Freq<-round(x$Freq/with(x,ave(Freq,Date,FUN=sum)),2);x}),dat2$Operator)
 subset(res1,Operator=="A" & Date=="Jan 2013")
#   Operator Score     Date Freq Rel.Freq
#41        A  Crap Jan 2013    0     0.00
#46        A  Good Jan 2013   15     0.65
#51        A    OK Jan 2013    3     0.13
#56        A  Poor Jan 2013    5     0.22
#or
dat3<- dat2
dat3$Rel.Freq<-round(dat3$Freq/with(dat3,ave(Freq,Operator,Date,FUN=sum)),2)
 subset(dat3,Operator=="A" & Date=="Jan 2013")
#   Operator Score     Date Freq Rel.Freq
#41        A  Crap Jan 2013    0     0.00
#46        A  Good Jan 2013   15     0.65
#51        A    OK Jan 2013    3     0.13
#56        A  Poor Jan 2013    5     0.22
 row.names(dat3)<- row.names(res1)
 identical(dat3,res1)
#[1] TRUE
A.K.


>I have the data frame with the following structure
>
 >  Operator Score     Date Freq

>1          A  Crap Apr 2013    0
>2          D  Crap Apr 2013    0
>3          J  Crap Apr 2013    0
>4          L  Crap Apr 2013    0
>5          M  Crap Apr 2013    0
>6          A  Good Apr 2013    1
>7          D  Good Apr 2013   14
>8          J  Good Apr 2013   26
>9          L  Good Apr 2013    3
>10         M  Good Apr 2013    9
>
>I would like to aggregate this data such that I can find the
relative frequency of each score (Good, Ok, Poor and Crap) for each
combination of >month and operator. For example For operator A in the
month Jan 2013 - I would like the following output
>
>   Operator Score     Date Freq Rel.Freq
>1          A  Crap Jan 2013    0       0
>2          A  Poor Jan 2013    5      0.22
>3          A  Good Jan 2013    15  0.65
>4          A  Ok Jan 2013   3           0.13
>
>i.e I would like to add a relative frequency column to my
existing data.frame. I haven't got anywhere near an automated solution.
The closest I >have is
>
>tmp <- subset(df, Operator == "A")
>tmp$N.norm <- tmp$Freq/sum(ans2$Freq)
>
>However this sums all data for operator A regardless of date. So
 I would need to subset again according to date. Is there a
straightforward way to >do this in R



<nabble_embed>structure(list(Operator = structure(c(1L, 2L, 3L, 4L, 5L, 1L,
2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L,
3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L,
4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L,
5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L,
1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L,
2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L), .Label = c("A",
"D", "J", "L", "M"), class = "factor"), Score = structure(c(1L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L,
4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L,
3L, 3L, 4L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L,
2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 1L, 1L, 1L, 1L, 1L,
2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 1L,
1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L, 3L, 3L, 3L, 3L, 3L, 4L, 4L,
4L, 4L, 4L), .Label = c("Crap", "Good", "OK", "Poor"), class = "factor"),
    Date = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
    1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 2L,
    2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L,
    3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
    3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L,
    4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 5L, 5L, 5L, 5L, 5L,
    5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L
    ), .Label = c("Apr 2013", "Feb 2013", "Jan 2013", "Mar 2013",
    "May 2013"), class = "factor"), Freq = c(0L, 0L, 0L, 0L,
    0L, 1L, 14L, 26L, 3L, 9L, 3L, 5L, 3L, 0L, 6L, 3L, 24L, 20L,
    29L, 14L, 0L, 0L, 0L, 0L, 0L, 2L, 17L, 24L, 12L, 9L, 2L,
    10L, 4L, 0L, 4L, 0L, 27L, 36L, 37L, 13L, 0L, 0L, 0L, 0L,
    0L, 15L, 16L, 20L, 5L, 15L, 3L, 6L, 17L, 3L, 5L, 5L, 31L,
    12L, 41L, 9L, 0L, 1L, 0L, 0L, 0L, 1L, 8L, 11L, 12L, 17L,
    1L, 1L, 3L, 4L, 4L, 5L, 16L, 21L, 25L, 15L, 0L, 0L, 0L, 0L,
    0L, 5L, 7L, 18L, 4L, 3L, 0L, 5L, 2L, 0L, 1L, 1L, 15L, 9L,
    10L, 9L)), .Names = c("Operator", "Score", "Date", "Freq"
), row.names = c(NA, -100L), class = "data.frame")</nabble_embed>

______________________________________________
[hidden email] mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.