Hi
r-help-boun...@r-project.org napsal dne 17.03.2010 13:04:05: > Jim & Petr, > Thank you for your hint - I am really grateful, because they helped me to > get one step further, > and although now the problem lies somewhere else, you encouraged that we can > find the > solution soon! > > 1. To Petr's comments > > Petr, your hint to define y: > y <- LVvar[,1, drop=FALSE] > did solve the problem, so I got a data.frame with the indexes. Going through help page y <- as.matrix(LVvar[,1, drop=FALSE]) x <- as.matrix(LVvar[,-1] svp <- ksvm(x, y, type="nu-svc") shall work. However as I never used this package and function I am not sure if it is used correctly. Regards Petr > > Yet, then I turned to the call > svp <- ksvm(x, y, type="nu-svc") > Error in .local(x, ...) : y must be a vector or a factor. > > So then I followed your second advice, looking up the additional information > from help file: > == > x is defined as: > a symbolic description of the model to be fit. When not using a formula x > can be a matrix or vector containing the training data or a kernel matrix of > class kernelMatrix of the training data or a list of character vectors (for > use with the string kernel). Note, that the intercept is always excluded, > whether given in the formula or not. > > y is defined as > a response vector with one label for each row/component of x. Can be either > a factor (for classification tasks) or a numeric vector (for regression). > == > > So I tried to convert LVvar into a matrix via as.matrix() but didn't make a > difference. > ============================================================ > > 2. To Jim's comments > > On Wed, Mar 17, 2010 at 1:10 AM, jim holtman <jholt...@gmail.com> wrote: > > > Please provide what LVvar is. > > > > LVvar is a dataframe > > > > At least provide str(LVvar), or preferably a 'dput' of the object. > > > > str(LVvar) returns: > > 'data.frame': 55 obs. of 7 variables: > $ rPerform : num 0.0682 -0.0682 -0.7443 0.7443 0.2619 ... > $ rCoordCap: num 4.98 6.08 5.73 5.92 4.96 ... > $ rKnowGrow: num 4.5 5.92 5.23 6.08 4.38 ... > $ rGoalcom : num 5.81 6.58 6 5.75 5.29 ... > $ rSupport : num 6.15 6.92 6.6 4.92 6 ... > $ rOpcomm : num 5.98 6.25 6.33 6.5 5.29 ... > $ rT2Cadap : num 5.03 6.12 4.9 6.25 5.12 ... > - attr(*, "na.action")=Class 'omit' Named int 40 > .. ..- attr(*, "names")= chr "40" > > == > > dput(LVvar) returns (abbreviated with ...): > > structure(list(rPerform = c(0.0681818181818183, -0.0681818181818183, > -0.744318181818182, 0.744318181818182, 0.261931818181818, > -0.900568181818182, > ... > rCoordCap = c(4.97916666666667, > 6.08333333333333, 5.73333333333333, 5.91666666666667, 4.95833333333333, > ... > .Names = c("rPerform", "rCoordCap", "rKnowGrow", > "rGoalcom", "rSupport", "rOpcomm", "rT2Cadap"), row.names = c(1L, > 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 15L, > 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 25L, 26L, 27L, 28L, > 29L, 30L, 31L, 32L, 33L, 34L, 35L, 36L, 37L, 38L, 39L, 41L, 42L, > 43L, 44L, 45L, 46L, 47L, 48L, 49L, 50L, 51L, 52L, 53L, 54L, 55L, > 56L), na.action = structure(40L, .Names = "40", class = "omit"), class = > "data.frame") > > > > > > > PLEASE do read the posting guide > > http://www.R-project.org/posting-guide.html<http://www.r-project.org/ > posting-guide.html> > > and provide commented, minimal, self-contained, reproducible code. > > > > > > Here's my try (please have mercy for a complete R beginner): > > library("kernlab") > library("methods") > > # Data Definitions > LV <- c("rPerform","rCoordCap", "rKnowGrow", "rGoalcom", "rSupport", > "rOpcomm", "rT2Cadap" ) > > # creates a dataframe > LVvar <- na.omit(loopLV_IndexScores(LV, u_proj)) > > x <- (LVvar[,-1]) > y <- (LVvar[,1]) > svp <- ksvm(x, y, type="nu-svc") > svp > > === > > Thanks so much for not giving up. > > Cheers, > Chaehan > > > > > > On Tue, Mar 16, 2010 at 6:03 PM, Chaehan So <chaehan...@gmail.com> wrote: > > > >> Dear r-helpers, > >> > >> I am getting a mismatch error between two variables: > >> > >> svp <- ksvm(x, y, type="nu-svc") > >> Error in .local(x, ...) : x and y don't match. > >> > >> and I suspect that it might be due to missing index in the y variable > >> which > >> I defined as: > >> > >> y <- (LVvar[,1]) > >> > >> I tried various methods to make the y assignment in the same format as x, > >> which is a dataframe > >> x <- (LVvar[,-1]) > >> > >> and looks like > >> x > >> rCoordCap rKnowGrow rGoalcom rSupport rOpcomm rT2Cadap > >> 1 4.979167 4.500000 5.812500 6.145833 5.979167 5.031250 > >> ... > >> > >> but I still get y without the indexes as a vector: > >> y > >> [1] -1.00000000 -6.91193182 -1.00000000 0.74431818 -6.91193182 > >> > >> > >> Why are the results different for x and y, even though the assignment is > >> the > >> same > >> except I exclude the columns for y? > >> > >> Cheers, > >> Chaehan > >> > >> [[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<http://www.r-project.org/ > posting-guide.html> > >> and provide commented, minimal, self-contained, reproducible code. > >> > > > > > > > > -- > > Jim Holtman > > Cincinnati, OH > > +1 513 646 9390 > > > > What is the problem that you are trying to solve? > > > > > > -- > Humboldt University Berlin, Germany > Institute of Psychology > Rudower Chaussee 18, Room 1221 > 12489 Berlin > Germany > Office: +49 30 2093 - 9337 > Mobile: +49 171- 626 9373 > > [[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. ______________________________________________ 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.