Hi Bill,
Great info.
The problem is what was originally given to me looks like DPUT1 below (random
sample of 25).
This is the only format they can give me this in and the data already looks
molten. So I applied reshape2::dcast which resulted in a dataframe made of
character vectors; except for the first column which is an integer vector.
So after dropping columns full of "" (blanks) and reordering columns I figured
I needed factors to accomplish my goal (refer below) and converted everything
to factors with:
> x2[,-1]<-as.data.frame(lapply(x[,-1],as.factor))
and ended up with DPUT2 below (random sample of 25)
Now after reading your last email I figured I've done will since no attributes
got dropped and no levels got dropped (just need to add some in because
couldn't be derived from original dataframe) and column names seem fine.
Now I have a new problem which is how to reorder levels in a dataframe and
possible add some unused. After seeing contents using Hmisc::contents I figured
the next logical step is to handle like vectors a chunk at a time.
For example subsetting to grepl("Q1_",names(scs.c2)) gives these vectors which
all have identical levels except for one:
$Q1_1 thru $Q1_7 except $Q1_3
[1] "" "important" "not important" "somewhat
important" "very important"
$Q1_3
[1] "important" "not important" "somewhat important" "very
important"
#So I tried I tried this which had no effect
keepcols<- grepl("Q1_",names(scs.c2))
levels(scs.c2[,keepcols])<-list(NoResp="",NotImportant="not
important",SomewhatImpt="somewhat
important",Important="important",VeryImpt="very important")
#then this which also failed. It coerced a bunch of NA's and turned the vectors
back to character vectors
scs.c2[,keepcols]<-sapply(scs.c2[,keepcols],function(x)
factor(x,levels(x)[c(NoResp="",NotImportant="not
important",SomewhatImpt="somewhat
important",Important="important",VeryImpt="very important")])
Mind you I can easily do this in MS Excel and is probably what I am going to
break down and do fairly soon. But I wanted to give this a good solid shot in R
because I want to learn to handle these situations in R. I've been using R for
almost a year.
__________________________
ADDITIONAL BACKGROUND
MY GOAL
I ultimately want to get started with some basic correlation analysis for some
of the columns : taking your example (slightly modified) I hope to be able to
do this
xx <- data.frame(stringsAsFactors=FALSE, check.names=FALSE,"No/Yes" =
factor(c("Yes","No","No","No"), levels=c("No","Yes")),
"Size" = ordered(c("Small","Large","Medium","Medium"),
levels=c("Small","Medium","Large")),"Name" = c("Adam","Bill","Chuck","Larry"))
> cor(sapply(xx[,1:2],as.numeric))
No/Yes Size
No/Yes 1.0000000 -0.8164966
Size -0.8164966 1.0000000
DPUT1
structure(list(svaID = c(771L, 771L, 775L, 775L, 774L, 776L,
774L, 771L, 771L, 771L, 771L, 774L, 774L, 775L, 765L, 775L, 765L,
775L, 771L, 777L, 775L, 771L, 774L, 776L, 776L), question = structure(c(19L,
12L, 23L, 3L, 10L, 36L, 25L, 1L, 30L, 7L, 21L, 13L, 16L, 32L,
6L, 5L, 18L, 19L, 14L, 2L, 2L, 9L, 37L, 28L, 24L), .Label = c("Q1",
"Q1_1", "Q1_2", "Q1_3", "Q1_4", "Q1_5", "Q1_6", "Q1_7", "Q10",
"Q11", "Q12", "Q13", "Q14", "Q15", "Q16", "Q17", "Q17_1", "Q17_2",
"Q17_3", "Q17_4", "Q17_5", "Q18", "Q19", "Q2", "Q20", "Q3", "Q4",
"Q5", "Q6", "Q6_A_1", "Q6_A_2", "Q6_A_3", "Q6_A_4", "Q6_A_5",
"Q7", "Q8", "Q9"), class = "factor"), answer = structure(c(11L,
29L, 29L, 26L, 29L, 29L, 1L, 1L, 1L, 13L, 11L, 1L, 1L, 1L, 26L,
26L, 11L, 11L, 29L, 13L, 13L, 29L, 29L, 29L, 27L), .Label = c("",
"1", "2", "3", "4", "5", "Change of College/University", "Change of Field of
Study",
"Confirmed Field of Study", "did not meet expectations", "exceeded
expectations",
"Family/Friend", "important", "Live Locally", "LLNL Contact",
"LLNL Housing page", "Local Newspaper", "met expectations", "no",
"None", "Not at All", "not important", "Pursue an Advanced Degree",
"Somewhat", "somewhat important", "very important", "Very Much",
"Web", "yes"), class = "factor")), .Names = c("svaID", "question",
"answer"), row.names = c(68L, 62L, 147L, 113L, 97L, 168L, 111L,
45L, 51L, 43L, 70L, 100L, 108L, 127L, 5L, 115L, 30L, 142L, 64L,
186L, 112L, 59L, 95L, 160L, 157L), class = "data.frame")
DPUT2
structure(list(svaID = c(765L, 771L, 774L, 775L, 776L, 777L,
778L, 779L, 782L, 783L, 786L, 788L, 789L, 790L, 791L, 793L, 794L,
795L, 797L, 801L, 803L, 804L, 805L, 807L, 808L), Q1_1 = structure(c(5L,
5L, 5L, 2L, 5L, 2L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 2L, 5L,
5L, 5L, 5L, 5L, 5L, 2L, 2L, 2L), .Label = c("", "important",
"not important", "somewhat important", "very important"), class = "factor"),
Q1_2 = structure(c(2L, 5L, 2L, 5L, 2L, 4L, 3L, 5L, 4L, 2L,
2L, 5L, 2L, 3L, 5L, 2L, 2L, 5L, 5L, 5L, 5L, 2L, 1L, 2L, 3L
), .Label = c("", "important", "not important", "somewhat important",
"very important"), class = "factor"), Q1_3 = structure(c(4L,
4L, 4L, 4L, 4L, 1L, 1L, 4L, 1L, 4L, 4L, 4L, 4L, 4L, 4L, 1L,
4L, 4L, 1L, 4L, 4L, 4L, 4L, 1L, 4L), .Label = c("important",
"not important", "somewhat important", "very important"), class =
"factor"),
Q1_4 = structure(c(5L, 5L, 5L, 5L, 5L, 2L, 2L, 5L, 2L, 2L,
5L, 5L, 5L, 5L, 5L, 2L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L, 5L
), .Label = c("", "important", "not important", "somewhat important",
"very important"), class = "factor"), Q1_5 = structure(c(5L,
3L, 5L, 5L, 3L, 2L, 2L, 3L, 2L, 3L, 5L, 5L, 5L, 4L, 4L, 5L,
5L, 5L, 3L, 3L, 3L, 5L, 2L, 2L, 4L), .Label = c("", "important",
"not important", "somewhat important", "very important"), class =
"factor"),
Q1_6 = structure(c(5L, 2L, 2L, 2L, 5L, 2L, 4L, 5L, 4L, 5L,
5L, 5L, 5L, 5L, 5L, 2L, 5L, 2L, 4L, 2L, 4L, 5L, 2L, 4L, 4L
), .Label = c("", "important", "not important", "somewhat important",
"very important"), class = "factor"), Q1_7 = structure(c(3L,
2L, 5L, 2L, 2L, 5L, 2L, 5L, 5L, 5L, 2L, 5L, 5L, 2L, 4L, 2L,
5L, 2L, 3L, 5L, 4L, 5L, 2L, 2L, 4L), .Label = c("", "important",
"not important", "somewhat important", "very important"), class =
"factor"),
Q2 = structure(c(4L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 4L,
4L, 4L, 4L, 4L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 3L, 4L
), .Label = c("", "Not at All", "Somewhat", "Very Much"), class =
"factor"),
Q3 = structure(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L
), .Label = c("", "yes"), class = "factor"), Q4 = structure(c(4L,
5L, 6L, 4L, 5L, 5L, 5L, 4L, 5L, 4L, 4L, 4L, 4L, 6L, 3L, 5L,
4L, 4L, 5L, 5L, 4L, 4L, 5L, 5L, 4L), .Label = c("", "Change of
College/University",
"Change of Field of Study", "Confirmed Field of Study", "None",
"Pursue an Advanced Degree"), class = "factor"), Q5 = structure(c(3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("", "no",
"yes"), class = "factor"), Q6 = structure(c(3L, 5L, 2L, 2L,
7L, 5L, 7L, 5L, 4L, 5L, 3L, 4L, 4L, 5L, 7L, 5L, 5L, 3L, 4L,
5L, 2L, 3L, 5L, 5L, 4L), .Label = c("", "Family/Friend",
"Live Locally", "LLNL Contact", "LLNL Housing page", "Local Newspaper",
"Web"), class = "factor"), Q6_A_1 = structure(c(1L, 1L, 1L,
6L, 1L, 1L, 3L, 1L, 1L, 1L, 1L, 1L, 3L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("", "1", "2", "3",
"4", "5"), class = "factor"), Q6_A_2 = structure(c(1L, 1L,
1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("", "4", "5"), class =
"factor"),
Q6_A_3 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L), .Label = c("", "5"), class = "factor"), Q6_A_4 = structure(c(1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L), .Label = c("", "5"), class =
"factor"),
Q6_A_5 = structure(c(1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L, 1L,
3L), .Label = c("", "2", "3", "4", "5"), class = "factor"),
Q8 = structure(c(3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 2L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L
), .Label = c("", "no", "yes"), class = "factor"), Q9 = structure(c(3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("", "no",
"yes"), class = "factor"), Q10 = structure(c(3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("", "no", "yes"), class =
"factor"),
Q11 = structure(c(3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L
), .Label = c("", "no", "yes"), class = "factor"), Q12 = structure(c(3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 2L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("", "no",
"yes"), class = "factor"), Q13 = structure(c(3L, 3L, 3L,
3L, 3L, 3L, 1L, 3L, 3L, 1L, 1L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
1L, 3L, 1L, 1L, 3L, 1L, 3L), .Label = c("", "no", "yes"), class =
"factor"),
Q14 = structure(c(3L, 1L, 1L, 3L, 2L, 3L, 1L, 3L, 3L, 1L,
1L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 1L, 1L, 1L, 3L, 3L, 1L, 2L
), .Label = c("", "no", "yes"), class = "factor"), Q15 = structure(c(2L,
2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L,
2L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 2L), .Label = c("", "yes"
), class = "factor"), Q16 = structure(c(4L, 4L, 4L, 3L, 3L,
3L, 4L, 4L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L, 4L, 3L, 4L, 3L,
3L, 3L, 4L, 3L, 4L), .Label = c("", "did not meet expectations",
"exceeded expectations", "met expectations"), class = "factor"),
Q17_1 = structure(c(3L, 4L, 4L, 3L, 3L, 3L, 4L, 4L, 4L, 3L,
3L, 3L, 3L, 4L, 2L, 4L, 4L, 3L, 3L, 3L, 3L, 3L, 4L, 4L, 4L
), .Label = c("", "did not meet expectations", "exceeded expectations",
"met expectations"), class = "factor"), Q17_2 = structure(c(3L,
4L, 4L, 3L, 3L, 3L, 4L, 4L, 4L, 3L, 4L, 3L, 3L, 3L, 4L, 4L,
4L, 3L, 3L, 3L, 3L, 4L, 3L, 3L, 4L), .Label = c("", "did not meet
expectations",
"exceeded expectations", "met expectations"), class = "factor"),
Q17_3 = structure(c(3L, 3L, 4L, 3L, 3L, 4L, 4L, 3L, 4L, 4L,
4L, 4L, 3L, 4L, 4L, 4L, 4L, 3L, 4L, 3L, 3L, 3L, 3L, 3L, 4L
), .Label = c("", "did not meet expectations", "exceeded expectations",
"met expectations"), class = "factor"), Q17_4 = structure(c(4L,
4L, 4L, 3L, 2L, 3L, 4L, 3L, 3L, 3L, 4L, 4L, 3L, 4L, 3L, 4L,
4L, 3L, 2L, 4L, 3L, 3L, 3L, 3L, 4L), .Label = c("", "did not meet
expectations",
"exceeded expectations", "met expectations"), class = "factor"),
Q17_5 = structure(c(3L, 3L, 4L, 3L, 4L, 4L, 4L, 3L, 4L, 4L,
4L, 3L, 4L, 4L, 4L, 4L, 4L, 4L, 3L, 4L, 4L, 3L, 4L, 4L, 3L
), .Label = c("", "did not meet expectations", "exceeded expectations",
"met expectations"), class = "factor"), Q18 = structure(c(3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 1L, 3L, 3L, 3L, 3L), .Label = c("", "no",
"yes"), class = "factor"), Q19 = structure(c(3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L, 3L,
3L, 3L, 3L, 3L, 3L, 3L, 3L), .Label = c("", "no", "yes"), class =
"factor")), .Names = c("svaID",
"Q1_1", "Q1_2", "Q1_3", "Q1_4", "Q1_5", "Q1_6", "Q1_7", "Q2",
"Q3", "Q4", "Q5", "Q6", "Q6_A_1", "Q6_A_2", "Q6_A_3", "Q6_A_4",
"Q6_A_5", "Q8", "Q9", "Q10", "Q11", "Q12", "Q13", "Q14", "Q15",
"Q16", "Q17_1", "Q17_2", "Q17_3", "Q17_4", "Q17_5", "Q18", "Q19"
), row.names = c(NA, 25L), class = "data.frame")
Thanks.
Dan
-----Original Message-----
From: William Dunlap [mailto:wdun...@tibco.com]
Sent: Thursday, February 21, 2013 8:33 AM
To: Mark Lamias; Lopez, Dan; R help (r-help@r-project.org)
Subject: RE: [R] Having trouble converting a dataframe of character vectors to
factors
> scs2<-data.frame(lapply(scs2, factor))
Calling data.frame() on the output of lapply() can result in changing column
names and will drop attributes that the input data.frame may have had. I
prefer to modify the original data.frame instead of making a new one from
scratch to avoid these problems.
Also, calling factor() on a factor will drop any unused levels, which you may
not want to do. Calling as.factor will not.
Compare the following three methods
f1 <- function (dataFrame) {
dataFrame[] <- lapply(dataFrame, factor)
dataFrame
}
f2 <- function (dataFrame) {
dataFrame[] <- lapply(dataFrame, as.factor)
dataFrame
}
f3 <- function (dataFrame) {
data.frame(lapply(dataFrame, factor))
}
on the following data.frame
x <- data.frame(stringsAsFactors=FALSE, check.names=FALSE,
"No/Yes" = factor(c("Yes","Yes","Yes"), levels=c("No","Yes")),
"Size" = ordered(c("Small","Large","Medium"),
levels=c("Small","Medium","Large")),
"Name" = c("Adam","Bill","Chuck"))
attr(x, "Date") <- as.POSIXlt("2013-02-21")
> str(x)
'data.frame': 3 obs. of 3 variables:
$ No/Yes: Factor w/ 2 levels "No","Yes": 2 2 2
$ Size : Ord.factor w/ 3 levels "Small"<"Medium"<..: 1 3 2
$ Name : chr "Adam" "Bill" "Chuck"
- attr(*, "Date")= POSIXlt, format: "2013-02-21"
> str(f1(x)) # drops unused levels
'data.frame': 3 obs. of 3 variables:
$ No/Yes: Factor w/ 1 level "Yes": 1 1 1
$ Size : Ord.factor w/ 3 levels "Small"<"Medium"<..: 1 3 2
$ Name : Factor w/ 3 levels "Adam","Bill",..: 1 2 3
- attr(*, "Date")= POSIXlt, format: "2013-02-21"
> str(f2(x))
'data.frame': 3 obs. of 3 variables:
$ No/Yes: Factor w/ 2 levels "No","Yes": 2 2 2
$ Size : Ord.factor w/ 3 levels "Small"<"Medium"<..: 1 3 2
$ Name : Factor w/ 3 levels "Adam","Bill",..: 1 2 3
- attr(*, "Date")= POSIXlt, format: "2013-02-21"
> str(f3(x)) # mangles column names, drops unused levels, drops Date attribute
'data.frame': 3 obs. of 3 variables:
$ No.Yes: Factor w/ 1 level "Yes": 1 1 1
$ Size : Ord.factor w/ 3 levels "Small"<"Medium"<..: 1 3 2
$ Name : Factor w/ 3 levels "Adam","Bill",..: 1 2 3
Bill Dunlap
Spotfire, TIBCO Software
wdunlap tibco.com
> -----Original Message-----
> From: r-help-boun...@r-project.org
> [mailto:r-help-boun...@r-project.org] On Behalf Of Mark Lamias
> Sent: Wednesday, February 20, 2013 6:51 PM
> To: Daniel Lopez; R help (r-help@r-project.org)
> Subject: Re: [R] Having trouble converting a dataframe of character
> vectors to factors
>
> How about this?
>
> scs2<-data.frame(lapply(scs2, factor))
>
>
>
>
> ________________________________
> From: "Lopez, Dan" <lopez...@llnl.gov>
> To: "R help (r-help@r-project.org)" <r-help@r-project.org>
> Sent: Wednesday, February 20, 2013 7:09 PM
> Subject: [R] Having trouble converting a dataframe of character
> vectors to factors
>
> R Experts,
>
> I have a dataframe made up of character vectors--these are results
> from survey questions. I need to convert them to factors.
>
> I tried the following which did not work:
> scs2<-sapply(scs2,as.factor)
> also this didn't work:
> scs2<-sapply(scs2,function(x) as.factor(x))
>
> After doing either of above I end up with
> >str(scs2)
>
> chr [1:10, 1:10] "very important" "very important" "very important" "very
> important" ...
>
> - attr(*, "dimnames")=List of 2
>
> ..$ : NULL
>
> ..$ : chr [1:10] "Q1_1" "Q1_2" "Q1_3" "Q1_4" ...
>
> >class(scs2)
> "matrix"
>
> But when I do it one at a time it works:
> scs2$Q1_1<-as.factor(scs2$Q1_1)
> scs2$Q1_2<- as.factor(scs2$Q1_2)
>
> What am I doing wrong? How do I accomplish this with sapply or similar
> function?
>
> Data for reproducibility:
>
>
> scs2<-structure(list(Q1_1 = c("very important", "very important",
> "very important",
>
> "very important", "very important", "very important", "very
> important",
>
> "somewhat important", "important", "very important"), Q1_2 =
> c("important",
>
> "somewhat important", "very important", "important", "important",
>
> "very important", "somewhat important", "somewhat important",
>
> "very important", "very important"), Q1_3 = c("very important",
>
> "important", "very important", "very important", "important",
>
> "very important", "very important", "somewhat important", "not
> important",
>
> "important"), Q1_4 = c("very important", "important", "very
> important",
>
> "very important", "important", "important", "important", "very
> important",
>
> "somewhat important", "important"), Q1_5 = c("very important",
>
> "not important", "important", "very important", "not important",
>
> "important", "somewhat important", "important", "somewhat important",
>
> "not important"), Q1_6 = c("very important", "not important",
>
> "important", "very important", "somewhat important", "very important",
>
> "very important", "very important", "important", "important"),
>
> Q1_7 = c("very important", "somewhat important", "important",
>
> "somewhat important", "important", "important", "very important",
>
> "very important", "somewhat important", "not important"),
>
> Q2 = c("Somewhat", "Very Much", "Somewhat", "Very Much",
>
> "Very Much", "Very Much", "Very Much", "Very Much", "Very Much",
>
> "Very Much"), Q3 = c("yes", "yes", "yes", "yes", "yes", "yes",
>
> "yes", "yes", "yes", "yes"), Q4 = c("None", "None", "None",
>
> "None", "Confirmed Field of Study", "Confirmed Field of Study",
>
> "Confirmed Field of Study", "None", "None", "None")), .Names =
> c("Q1_1",
>
> "Q1_2", "Q1_3", "Q1_4", "Q1_5", "Q1_6", "Q1_7", "Q2", "Q3", "Q4"
>
> ), row.names = c(78L, 46L, 80L, 196L, 188L, 197L, 39L, 195L,
>
> 172L, 110L), class = "data.frame")
>
>
> [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@r-project.org 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.
> [[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org 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.
