i just called trait3 to my variable. Is this what i'm suppose to wright? class(trait3), or class (my_trait3_variable? both give error 2016-03-03 23:42 GMT+00:00 Jim Lemon <drjimlemon at gmail.com>:> Hi Fabio, > It is possible that your remaining "numeric" variable is a factor. What > does: > > class(my_numeric_variable) > > say? (where you substitute the name of your "numeric" variable) > > Jim > > > On Fri, Mar 4, 2016 at 2:25 AM, Fabio Monteiro > <fabio.monteiro1992 at gmail.com> wrote: > > Hello, my name is F?bio and I'm a Marine Ecology student in Portugal. > > > > I'm currently using the FD package for my work and yesterday one message > > appeared that I wasn't expecting and I really need your help to try to > > figure out what's happening. > > I'm using the dbFD function and the following message appeared: > > > > FRic: Only categorical and/or ordinal trait(s) present in 'x'. FRic was > > measured as the number of unique trait combinations, NOT as the convex > > hull volume. > > FDiv: Cannot be computed when only categorical and/or ordinal trait(s) > > present in 'x'. > > > > My data: > > x is a matrix with species vs functional traits > > a is a matrix with species vs sampling (in abundances) > > > > Previously I used the dbFD function and was working just fine. Yesterday > I > > removed 2 traits and this message appeared. > > > > My traits now are 3 categorical traits and 1 numeric. The 2 trais that I > > removed were numeric traits as well. I really need to remove those trait, > > but I still need the FDiv to be calculated. Can you explain to me why is > > this error occurring? I need to know how the dbFD is measuring the > indexes > > so I can understanding the error and if I can or can't continue to use > this > > package (if it applies or not to my goals) > > > > Kind regards > > > > F?bio Monteiro > > > > [[alternative HTML version deleted]] > > > > ______________________________________________ > > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > > 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]]
Hi Fabio, You should write: class(...) where ... is the same as what you would type to have the variable displayed on the console. Looking at your earlier message, it might be: x$trait3 so try: class(x$trait3) Jim On Fri, Mar 4, 2016 at 11:30 AM, Fabio Monteiro <fabio.monteiro1992 at gmail.com> wrote:> i just called trait3 to my variable. > > Is this what i'm suppose to wright? class(trait3), or class > (my_trait3_variable? > > both give error > > 2016-03-03 23:42 GMT+00:00 Jim Lemon <drjimlemon at gmail.com>: >> >> Hi Fabio, >> It is possible that your remaining "numeric" variable is a factor. What >> does: >> >> class(my_numeric_variable) >> >> say? (where you substitute the name of your "numeric" variable) >> >> Jim >> >> >> On Fri, Mar 4, 2016 at 2:25 AM, Fabio Monteiro >> <fabio.monteiro1992 at gmail.com> wrote: >> > Hello, my name is F?bio and I'm a Marine Ecology student in Portugal. >> > >> > I'm currently using the FD package for my work and yesterday one message >> > appeared that I wasn't expecting and I really need your help to try to >> > figure out what's happening. >> > I'm using the dbFD function and the following message appeared: >> > >> > FRic: Only categorical and/or ordinal trait(s) present in 'x'. FRic was >> > measured as the number of unique trait combinations, NOT as the convex >> > hull volume. >> > FDiv: Cannot be computed when only categorical and/or ordinal trait(s) >> > present in 'x'. >> > >> > My data: >> > x is a matrix with species vs functional traits >> > a is a matrix with species vs sampling (in abundances) >> > >> > Previously I used the dbFD function and was working just fine. Yesterday >> > I >> > removed 2 traits and this message appeared. >> > >> > My traits now are 3 categorical traits and 1 numeric. The 2 trais that I >> > removed were numeric traits as well. I really need to remove those >> > trait, >> > but I still need the FDiv to be calculated. Can you explain to me why is >> > this error occurring? I need to know how the dbFD is measuring the >> > indexes >> > so I can understanding the error and if I can or can't continue to use >> > this >> > package (if it applies or not to my goals) >> > >> > Kind regards >> > >> > F?bio Monteiro >> > >> > [[alternative HTML version deleted]] >> > >> > ______________________________________________ >> > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see >> > 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. > >
Hi Fabio, What has probably happened is that ft$trait3 looks like numbers but when it was read in at least one value could not be read as a number. The default behavior in R is to transform the variable into a factor: testcase<-read.table(text="1 2 3 4 1 2 3 4 1 2 B 4")> testcaseV1 V2 V3 V4 1 1 2 3 4 2 1 2 3 4 3 1 2 B 4> sapply(testcase,class)V1 V2 V3 V4 "integer" "integer" "factor" "integer" So testcase$V3 was read in as a factor. There are a couple of things you can do. First, try to convert the factor to numeric and live with the NA values that will be generated: as.numeric(as.character(testcase$V3)) [1] 3 3 NA Warning message: NAs introduced by coercion If the number of non0numeric values in the original data is small and you can find them: testcase$V3[3]<-3 as.numeric(as.character(testcase$V3)) [1] 3 3 3 correct the original data and read it in again. I don't really know enough to answer your second question. JIm On Sat, Mar 5, 2016 at 2:58 AM, Fabio Monteiro <fabio.monteiro1992 at gmail.com> wrote:> I still have another question. apart from that one > > in the dbFD function in FD package there is one option which is if FRic > should be standardized or not. What does that mean? Why should our shouldn't > I have the FRic Standardized? > > Thank you Jim > > 2016-03-04 14:52 GMT+00:00 Fabio Monteiro <fabio.monteiro1992 at gmail.com>: >> >> class(ft$trait3) >> [1] "factor >> >> >> Yes is a factor. And now? >> >> Thank you >> >> Kind Regards >> F?bio >> >> 2016-03-04 7:15 GMT+00:00 Jim Lemon <drjimlemon at gmail.com>: >>> >>> Hi Fabio, >>> You should write: >>> >>> class(...) >>> >>> where ... is the same as what you would type to have the variable >>> displayed on the console. Looking at your earlier message, it might >>> be: >>> >>> x$trait3 >>> >>> so try: >>> >>> class(x$trait3) >>> >>> Jim >>> >>> >>> On Fri, Mar 4, 2016 at 11:30 AM, Fabio Monteiro >>> <fabio.monteiro1992 at gmail.com> wrote: >>> > i just called trait3 to my variable. >>> > >>> > Is this what i'm suppose to wright? class(trait3), or class >>> > (my_trait3_variable? >>> > >>> > both give error >>> > >>> > 2016-03-03 23:42 GMT+00:00 Jim Lemon <drjimlemon at gmail.com>: >>> >> >>> >> Hi Fabio, >>> >> It is possible that your remaining "numeric" variable is a factor. >>> >> What >>> >> does: >>> >> >>> >> class(my_numeric_variable) >>> >> >>> >> say? (where you substitute the name of your "numeric" variable) >>> >> >>> >> Jim >>> >> >>> >> >>> >> On Fri, Mar 4, 2016 at 2:25 AM, Fabio Monteiro >>> >> <fabio.monteiro1992 at gmail.com> wrote: >>> >> > Hello, my name is F?bio and I'm a Marine Ecology student in >>> >> > Portugal. >>> >> > >>> >> > I'm currently using the FD package for my work and yesterday one >>> >> > message >>> >> > appeared that I wasn't expecting and I really need your help to try >>> >> > to >>> >> > figure out what's happening. >>> >> > I'm using the dbFD function and the following message appeared: >>> >> > >>> >> > FRic: Only categorical and/or ordinal trait(s) present in 'x'. FRic >>> >> > was >>> >> > measured as the number of unique trait combinations, NOT as the >>> >> > convex >>> >> > hull volume. >>> >> > FDiv: Cannot be computed when only categorical and/or ordinal >>> >> > trait(s) >>> >> > present in 'x'. >>> >> > >>> >> > My data: >>> >> > x is a matrix with species vs functional traits >>> >> > a is a matrix with species vs sampling (in abundances) >>> >> > >>> >> > Previously I used the dbFD function and was working just fine. >>> >> > Yesterday >>> >> > I >>> >> > removed 2 traits and this message appeared. >>> >> > >>> >> > My traits now are 3 categorical traits and 1 numeric. The 2 trais >>> >> > that I >>> >> > removed were numeric traits as well. I really need to remove those >>> >> > trait, >>> >> > but I still need the FDiv to be calculated. Can you explain to me >>> >> > why is >>> >> > this error occurring? I need to know how the dbFD is measuring the >>> >> > indexes >>> >> > so I can understanding the error and if I can or can't continue to >>> >> > use >>> >> > this >>> >> > package (if it applies or not to my goals) >>> >> > >>> >> > Kind regards >>> >> > >>> >> > F?bio Monteiro >>> >> > >>> >> > [[alternative HTML version deleted]] >>> >> > >>> >> > ______________________________________________ >>> >> > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see >>> >> > 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. >>> > >>> > >> >> >
Hey Jim they are all numeric as you can see as.numeric(as.character(a$x)) [1] 20.0 50.0 7.9 25.0 20.0 20.0 15.0 30.0 48.0 75.0 75.0 25.0 300.0 [14] 103.0 20.0 45.0 15.0 20.0 50.0 6.0 18.0 59.0 70.0 80.0 100.0 40.0 [27] 15.0 30.0 40.0 60.0 9.0 11.0 27.5 75.0 60.0 70.0 70.0 60.0 20.0 [40] 21.0 50.0 35.0 46.0 F?bio 2016-03-05 9:38 GMT+00:00 Jim Lemon <drjimlemon at gmail.com>:> Hi Fabio, > What has probably happened is that ft$trait3 looks like numbers but > when it was read in at least one value could not be read as a number. > The default behavior in R is to transform the variable into a factor: > > testcase<-read.table(text="1 2 3 4 > 1 2 3 4 > 1 2 B 4") > > testcase > V1 V2 V3 V4 > 1 1 2 3 4 > 2 1 2 3 4 > 3 1 2 B 4 > > sapply(testcase,class) > V1 V2 V3 V4 > "integer" "integer" "factor" "integer" > > So testcase$V3 was read in as a factor. There are a couple of things > you can do. First, try to convert the factor to numeric and live with > the NA values that will be generated: > > as.numeric(as.character(testcase$V3)) > [1] 3 3 NA > Warning message: > NAs introduced by coercion > > If the number of non0numeric values in the original data is small and > you can find them: > > testcase$V3[3]<-3 > as.numeric(as.character(testcase$V3)) > [1] 3 3 3 > > correct the original data and read it in again. I don't really know > enough to answer your second question. > > JIm > > > On Sat, Mar 5, 2016 at 2:58 AM, Fabio Monteiro > <fabio.monteiro1992 at gmail.com> wrote: > > I still have another question. apart from that one > > > > in the dbFD function in FD package there is one option which is if FRic > > should be standardized or not. What does that mean? Why should our > shouldn't > > I have the FRic Standardized? > > > > Thank you Jim > > > > 2016-03-04 14:52 GMT+00:00 Fabio Monteiro <fabio.monteiro1992 at gmail.com > >: > >> > >> class(ft$trait3) > >> [1] "factor > >> > >> > >> Yes is a factor. And now? > >> > >> Thank you > >> > >> Kind Regards > >> F?bio > >> > >> 2016-03-04 7:15 GMT+00:00 Jim Lemon <drjimlemon at gmail.com>: > >>> > >>> Hi Fabio, > >>> You should write: > >>> > >>> class(...) > >>> > >>> where ... is the same as what you would type to have the variable > >>> displayed on the console. Looking at your earlier message, it might > >>> be: > >>> > >>> x$trait3 > >>> > >>> so try: > >>> > >>> class(x$trait3) > >>> > >>> Jim > >>> > >>> > >>> On Fri, Mar 4, 2016 at 11:30 AM, Fabio Monteiro > >>> <fabio.monteiro1992 at gmail.com> wrote: > >>> > i just called trait3 to my variable. > >>> > > >>> > Is this what i'm suppose to wright? class(trait3), or class > >>> > (my_trait3_variable? > >>> > > >>> > both give error > >>> > > >>> > 2016-03-03 23:42 GMT+00:00 Jim Lemon <drjimlemon at gmail.com>: > >>> >> > >>> >> Hi Fabio, > >>> >> It is possible that your remaining "numeric" variable is a factor. > >>> >> What > >>> >> does: > >>> >> > >>> >> class(my_numeric_variable) > >>> >> > >>> >> say? (where you substitute the name of your "numeric" variable) > >>> >> > >>> >> Jim > >>> >> > >>> >> > >>> >> On Fri, Mar 4, 2016 at 2:25 AM, Fabio Monteiro > >>> >> <fabio.monteiro1992 at gmail.com> wrote: > >>> >> > Hello, my name is F?bio and I'm a Marine Ecology student in > >>> >> > Portugal. > >>> >> > > >>> >> > I'm currently using the FD package for my work and yesterday one > >>> >> > message > >>> >> > appeared that I wasn't expecting and I really need your help to > try > >>> >> > to > >>> >> > figure out what's happening. > >>> >> > I'm using the dbFD function and the following message appeared: > >>> >> > > >>> >> > FRic: Only categorical and/or ordinal trait(s) present in 'x'. > FRic > >>> >> > was > >>> >> > measured as the number of unique trait combinations, NOT as the > >>> >> > convex > >>> >> > hull volume. > >>> >> > FDiv: Cannot be computed when only categorical and/or ordinal > >>> >> > trait(s) > >>> >> > present in 'x'. > >>> >> > > >>> >> > My data: > >>> >> > x is a matrix with species vs functional traits > >>> >> > a is a matrix with species vs sampling (in abundances) > >>> >> > > >>> >> > Previously I used the dbFD function and was working just fine. > >>> >> > Yesterday > >>> >> > I > >>> >> > removed 2 traits and this message appeared. > >>> >> > > >>> >> > My traits now are 3 categorical traits and 1 numeric. The 2 trais > >>> >> > that I > >>> >> > removed were numeric traits as well. I really need to remove those > >>> >> > trait, > >>> >> > but I still need the FDiv to be calculated. Can you explain to me > >>> >> > why is > >>> >> > this error occurring? I need to know how the dbFD is measuring the > >>> >> > indexes > >>> >> > so I can understanding the error and if I can or can't continue to > >>> >> > use > >>> >> > this > >>> >> > package (if it applies or not to my goals) > >>> >> > > >>> >> > Kind regards > >>> >> > > >>> >> > F?bio Monteiro > >>> >> > > >>> >> > [[alternative HTML version deleted]] > >>> >> > > >>> >> > ______________________________________________ > >>> >> > R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see > >>> >> > 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]]