HI, of course.
The a mini-version of my data-set is below, stored in d2. Then the code I'm
working follows.
library(reshape2)
#Create d2
structure(list(row = 1:50, rank1 = structure(c(3L, 3L, 3L, 4L,
3L, 3L, NA, NA, 3L, NA, 3L, 3L, 1L, NA, 2L, NA, 3L, NA, 2L, 1L,
1L, 3L, NA, 6L, NA, 1L, NA, 3L, 1L, NA, 1L, NA, NA, 6L, 3L, NA,
1L, 3L, 3L, 4L, 1L, NA, 3L, 3L, 3L, NA, 3L, 3L, NA, 1L), .Label =
c("accessible",
"alternatives", "information", "responsive", "social", "technical",
"trade"), class = "factor"), rank2 = structure(c(6L, 1L, 1L,
2L, 4L, 6L, NA, NA, 6L, NA, 6L, 4L, 2L, NA, 4L, NA, 6L, NA, 1L,
6L, 3L, 2L, NA, 3L, NA, 6L, NA, 6L, 6L, NA, 3L, NA, NA, 3L, 6L,
NA, 6L, 6L, 6L, 7L, 3L, NA, 1L, 6L, 6L, NA, 2L, 6L, NA, 2L), .Label =
c("accessible",
"alternatives", "information", "responsive", "social", "technical",
"trade"), class = "factor"), rank3 = structure(c(1L, 6L, 4L,
3L, 2L, 4L, NA, NA, 4L, NA, 1L, 1L, 6L, NA, 1L, NA, 1L, NA, 7L,
3L, 6L, 1L, NA, 2L, NA, 4L, NA, 1L, 3L, NA, 6L, NA, NA, 4L, 2L,
NA, 7L, 1L, 1L, 6L, 7L, NA, 6L, 1L, 1L, NA, 4L, 1L, NA, 3L), .Label =
c("accessible",
"alternatives", "information", "responsive", "social", "technical",
"trade"), class = "factor"), rank4 = structure(c(7L, 4L, 2L,
1L, 1L, 7L, NA, NA, 1L, NA, 7L, 2L, 7L, NA, 3L, NA, 2L, NA, 3L,
4L, 5L, 6L, NA, 4L, NA, 3L, NA, 4L, 4L, NA, 4L, NA, NA, 2L, 7L,
NA, 2L, 2L, 2L, 3L, 6L, NA, 2L, 5L, 4L, NA, 1L, 2L, NA, 4L), .Label =
c("accessible",
"alternatives", "information", "responsive", "social", "technical",
"trade"), class = "factor"), rank5 = structure(c(2L, 7L, 6L,
7L, 7L, 2L, NA, NA, 2L, NA, 2L, 7L, 3L, NA, 6L, NA, 7L, NA, 6L,
7L, 4L, 7L, NA, 7L, NA, 7L, NA, 2L, 2L, NA, 2L, NA, NA, 7L, 1L,
NA, 3L, 7L, 4L, 2L, 2L, NA, 4L, 2L, 2L, NA, 6L, 4L, NA, 5L), .Label =
c("accessible",
"alternatives", "information", "responsive", "social", "technical",
"trade"), class = "factor"), rank6 = structure(c(4L, 2L, 7L,
6L, 6L, 1L, NA, NA, 7L, NA, 4L, 5L, 4L, NA, 7L, NA, 4L, NA, 4L,
2L, 2L, 4L, NA, 1L, NA, 2L, NA, 7L, 7L, NA, 7L, NA, NA, 1L, 4L,
NA, 4L, 4L, 7L, 1L, 4L, NA, 7L, 7L, 7L, NA, 7L, 7L, NA, 7L), .Label =
c("accessible",
"alternatives", "information", "responsive", "social", "technical",
"trade"), class = "factor"), rank7 = structure(c(5L, 5L, 5L,
5L, 5L, 5L, NA, NA, 5L, NA, 5L, 6L, 5L, NA, 5L, NA, 5L, NA, 5L,
5L, 7L, 5L, NA, 5L, NA, 5L, NA, 5L, 5L, NA, 5L, NA, NA, 5L, 5L,
NA, 5L, NA, 5L, 5L, 5L, NA, 5L, 4L, 5L, NA, 5L, 5L, NA, 6L), .Label =
c("accessible",
"alternatives", "information", "responsive", "social", "technical",
"trade"), class = "factor")), .Names = c("row", "rank1", "rank2",
"rank3", "rank4", "rank5", "rank6", "rank7"), row.names = c(NA,
50L), class = "data.frame")
#This code is a replication of David Carlson's code (below) which works
splendidly, but does not work on my data-set
#Melt d2: Note, I've used value.name='color' to maximize comparability with
David's suggestion
d3 <- melt(d2, id.vars=1, measure.vars=2:8,
variable.name="rank",value.name="color")
#Make Rank Variable Numeric
d3$rank<-as.numeric(d3$rank)
#Recast d3 into d4
d4<- dcast(d3, row~color,value.var="rank", fill=0)
#Note that d4 appears to provide a binary variable for one if a respondent
checked the option, but does not provide information as to which rank they
assigned each option, but also seems to summarize the number of missing values
#David Carlson's Code
mydf <- data.frame(t(replicate(100, sample(c("red", "blue", "green", "yellow",
NA), 4))))
mydf <- data.frame(rows=1:100, mydf)
colnames(mydf) <- c("row", "rank1", "rank2", "rank3", "rank4")
mymelt <- melt(mydf, id.vars=1, measure.vars=2:5, variable.name="rank",
value.name="color")
mymelt$rank <- as.numeric(mymelt$rank)
mycast <- dcast(mymelt, row~color, value.var="rank", fill=0)
#Compare
str(mydf)
str(d2)
head(mycast)
head(d4)
Again, I'm grateful for assistance. I can't understand what how my data-set
differs from David's sample data-set.
Simon Kiss
On Sep 4, 2014, at 2:35 PM, David L Carlson <[email protected]> wrote:
> I think we would need enough of the data you are using to figure out how to
> modify the process. Can you use dput() to send a small data set that fails to
> work?
>
> David C
>
> -----Original Message-----
> From: Simon Kiss [mailto:[email protected]]
> Sent: Thursday, September 4, 2014 1:28 PM
> To: David L Carlson
> Cc: [email protected]
> Subject: Re: [R] Turn Rank Ordering Into Numerical Scores By Transposing A
> Data Frame
>
> Hi David and list:
> This is working, except at this command
> mycast <- dcast(mymelt, row~color, value.var="rank", fill=0)
>
> dcast is using "length" as the default aggregating function. This results in
> not accurate results. It tells me, for example how many choices were missing
> values and it tells me if a person selected any given option (value is
> reported as 1).
> When I try to run your reproducible research, it works great, but something
> with the aggregating function is not working properly with mine.
> Any other thoughts?
> Simon
> On Aug 18, 2014, at 10:44 AM, David L Carlson <[email protected]> wrote:
>
>> Another approach using reshape2:
>>
>>> library(reshape2)
>>> # Construct data/ add column of row numbers
>>> set.seed(42)
>>> mydf <- data.frame(t(replicate(100, sample(c("red", "blue",
>> + "green", "yellow", NA), 4))))
>>> mydf <- data.frame(rows=1:100, mydf)
>>> colnames(mydf) <- c("row", "rank1", "rank2", "rank3", "rank4")
>>> head(mydf)
>> row rank1 rank2 rank3 rank4
>> 1 1 <NA> yellow red blue
>> 2 2 yellow green <NA> red
>> 3 3 yellow green blue <NA>
>> 4 4 <NA> blue yellow green
>> 5 5 <NA> red blue green
>> 6 6 <NA> red green blue
>>> # Reshape
>>> mymelt <- melt(mydf, id.vars=1, measure.vars=2:5,
>> + variable.name="rank", value.name="color")
>>> # Convert rank to numeric
>>> mymelt$rank <- as.numeric(mymelt$rank)
>>> mycast <- dcast(mymelt, row~color, value.var="rank", fill=0)
>>> head(mycast)
>> row blue green red yellow NA
>> 1 1 4 0 3 2 1
>> 2 2 0 2 4 1 3
>> 3 3 3 2 0 1 4
>> 4 4 2 4 0 3 1
>> 5 5 3 4 2 0 1
>> 6 6 4 3 2 0 1
>>
>> David C
>>
>> -----Original Message-----
>> From: [email protected] [mailto:[email protected]] On
>> Behalf Of David L Carlson
>> Sent: Sunday, August 17, 2014 6:32 PM
>> To: Simon Kiss; [email protected]
>> Subject: Re: [R] Turn Rank Ordering Into Numerical Scores By Transposing A
>> Data Frame
>>
>> There is probably an easier way to do this, but
>>
>>> set.seed(42)
>>> mydf <- data.frame(t(replicate(100, sample(c("red", "blue",
>> + "green", "yellow", NA), 4))))
>>> colnames(mydf) <- c("rank1", "rank2", "rank3", "rank4")
>>> head(mydf)
>> rank1 rank2 rank3 rank4
>> 1 <NA> yellow red blue
>> 2 yellow green <NA> red
>> 3 yellow green blue <NA>
>> 4 <NA> blue yellow green
>> 5 <NA> red blue green
>> 6 <NA> red green blue
>>> lvls <- levels(mydf$rank1)
>>> # convert color factors to numeric
>>> for (i in seq_along(mydf)) mydf[,i] <- as.numeric(mydf[,i])
>>> # stack the columns
>>> mydf2 <- stack(mydf)
>>> # convert rank factor to numeric
>>> mydf2$ind <- as.numeric(mydf2$ind)
>>> # add row numbers
>>> mydf2 <- data.frame(rows=1:100, mydf2)
>>> # Create table
>>> mytbl <- xtabs(ind~rows+values, mydf2)
>>> # convert to data frame
>>> mydf3 <- data.frame(unclass(mytbl))
>>> colnames(mydf3) <- lvls
>>> head(mydf3)
>> blue green red yellow
>> 1 4 0 3 2
>> 2 0 2 4 1
>> 3 3 2 0 1
>> 4 2 4 0 3
>> 5 3 4 2 0
>> 6 4 3 2 0
>>
>> David C
>>
>> -----Original Message-----
>> From: [email protected] [mailto:[email protected]] On
>> Behalf Of Simon Kiss
>> Sent: Friday, August 15, 2014 3:58 PM
>> To: [email protected]
>> Subject: Re: [R] Turn Rank Ordering Into Numerical Scores By Transposing A
>> Data Frame
>>
>>
>> Both the suggestions I got work very well, but what I didn't realize is that
>> NA values would cause serious problems. Where there is a missing value,
>> using the argument na.last=NA to order just returns the the order of the
>> factor levels, but excludes the missing values, but I have no idea where
>> those occur in the or rather which of those variables were actually missing.
>>
>> Have I explained this problem sufficiently?
>> I didn't think it would cause such a problem so I didn't include it in the
>> original problem definition.
>> Yours, Simon
>> On Jul 25, 2014, at 4:58 PM, David L Carlson <[email protected]> wrote:
>>
>>> I think this gets what you want. But your data are not reproducible since
>>> they are randomly drawn without setting a seed and the two data sets have
>>> no relationship to one another.
>>>
>>>> set.seed(42)
>>>> mydf <- data.frame(t(replicate(100, sample(c("red", "blue",
>>> + "green", "yellow")))))
>>>> colnames(mydf) <- c("rank1", "rank2", "rank3", "rank4")
>>>> mydf2 <- data.frame(t(apply(mydf, 1, order)))
>>>> colnames(mydf2) <- levels(mydf$rank1)
>>>> head(mydf)
>>> rank1 rank2 rank3 rank4
>>> 1 yellow green red blue
>>> 2 green blue yellow red
>>> 3 green yellow red blue
>>> 4 yellow red green blue
>>> 5 yellow red green blue
>>> 6 yellow red blue green
>>>> head(mydf2)
>>> blue green red yellow
>>> 1 4 2 3 1
>>> 2 2 1 4 3
>>> 3 4 1 3 2
>>> 4 4 3 2 1
>>> 5 4 3 2 1
>>> 6 3 4 2 1
>>>
>>> -------------------------------------
>>> David L Carlson
>>> Department of Anthropology
>>> Texas A&M University
>>> College Station, TX 77840-4352
>>>
>>> -----Original Message-----
>>> From: [email protected] [mailto:[email protected]] On
>>> Behalf Of Simon Kiss
>>> Sent: Friday, July 25, 2014 2:34 PM
>>> To: [email protected]
>>> Subject: [R] Turn Rank Ordering Into Numerical Scores By Transposing A Data
>>> Frame
>>>
>>> Hello:
>>> I have data that looks like mydf, below. It is the results of a survey
>>> where participants were to put a number of statements (in this case
>>> colours) in their order of preference. In this case, the rank number is the
>>> variable, and the factor level for each respondent is which colour they
>>> assigned to that rank. I would like to find a way to effectively transpose
>>> the data frame so that it looks like mydf2, also below, where the colours
>>> the participants were able to choose are the variables and the variable
>>> score is what that person ranked that variable.
>>>
>>> Ultimately what I would like to do is a factor analysis on these items, so
>>> I'd like to be able to see if people ranked red and yellow higher together
>>> but ranked green and blue together lower, that sort of thing.
>>> I have played around with different variations of t(), melt(), ifelse() and
>>> if() but can't find a solution.
>>> Thank you
>>> Simon
>>> #Reproducible code
>>> mydf<-data.frame(rank1=sample(c('red', 'blue', 'green', 'yellow'),
>>> replace=TRUE, size=100), rank2=sample(c('red', 'blue', 'green', 'yellow'),
>>> replace=TRUE, size=100), rank3=sample(c('red', 'blue', 'green', 'yellow'),
>>> replace=TRUE, size=100), rank4=sample(c('red', 'blue', 'green', 'yellow'),
>>> replace=TRUE, size=100))
>>>
>>> mydf2<-data.frame(red=sample(c(1,2,3,4),
>>> replace=TRUE,size=100),blue=sample(c(1,2,3,4),
>>> replace=TRUE,size=100),green=sample(c(1,2,3,4), replace=TRUE,size=100)
>>> ,yellow=sample(c(1,2,3,4), replace=TRUE,size=100))
>>> *********************************
>>> Simon J. Kiss, PhD
>>> Assistant Professor, Wilfrid Laurier University
>>> 73 George Street
>>> Brantford, Ontario, Canada
>>> N3T 2C9
>>>
>>> ______________________________________________
>>> [email protected] 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.
>>
>> *********************************
>> Simon J. Kiss, PhD
>> Assistant Professor, Wilfrid Laurier University
>> 73 George Street
>> Brantford, Ontario, Canada
>> N3T 2C9
>> Cell: +1 905 746 7606
>>
>> ______________________________________________
>> [email protected] 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.
>>
>> ______________________________________________
>> [email protected] 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.
>
> *********************************
> Simon J. Kiss, PhD
> Assistant Professor, Wilfrid Laurier University
> 73 George Street
> Brantford, Ontario, Canada
> N3T 2C9
> Cell: +1 905 746 7606
>
>
>
*********************************
Simon J. Kiss, PhD
Assistant Professor, Wilfrid Laurier University
73 George Street
Brantford, Ontario, Canada
N3T 2C9
Cell: +1 905 746 7606
______________________________________________
[email protected] 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.
