similar to: SVM cross validation in e1071

Hi everyone I am trying to do cross validation (10 fold CV) by using e1071:svm method. I know that there is an option (?cross?) for cross validation but still I wanted to make a function to Generate cross-validation indices using pls: cvsegments method. ##################################################################### Code (at the end) Is working fine but sometime caret:confusionMatrix

I expected, that I will get the same prediction, if I multiply the weights for all classes with a constant factor, but I got different results. Please look for the following code. > library(e1071) > data(Glass, package = "mlbench") > index <- 1:nrow(Glass) > testindex <- sample(index, trunc(length(index)/5)) > testset <- Glass[testindex, ] > trainset <-

Dear Sir, I got a problem with my program. I would like to classify my data using bagging support vector machine ensemble. I split my data into training data and test data. For a given data sets TR(X), K replicated training data sets are first randomly generated by bootstrapping technique with replacement. Next, Support Vector Mechine (SVM) is applied for each bootstrap data sets. Finally, the

Hi, I'm encountering trouble compiling caTools_1.17.1.tar.gz and e1071_1.6-4.tar.gz on a Linux system using the Intel compiler suite. 14 other packages I generally use installed without any trouble. I notice both of these trouble packages have a C++ component, so I wonder if that might be the issue. Below, there's information on my platform, compiler, and some diagnostic output showing

Dear all, I'm training an SVM with default settings on a matrix csr (SparseM package). I realized that if I train the SVM with the (hopefully) equivalent matrix (Matrix package) representation, the returned models and predictions sometimes differ. I expected both representations of the same data to lead to the same results though. It could be that it is a scaling problem, because unscaled

hello, i am so glad to write you. i am dealing now with writing my M.Sc in Applied Statistics thesis, titled " Data Mining Classifiers and Predictive Models Validation and Evaluation". I am planning to compare several DM classifiers like "NN, kNN, SVM, Dtree, and Naïve Bayes" according to their Predicting accuracy, interpretability, scalability, and time consuming etc. I have

Hi Martyn, Thanks for your insight, that seems pretty direct. Unfortunately, I did not compile this version of R (it's on a large supercomputer system and this version of R was installed by the admins). Using "R CMD config", I see the following relevant settings: DYLIB_LD = icc -std=gnu99 DYLIB_LDFLAGS = -shared -openmp LDFLAGS = -L/opt/compilers/intel/cce/9.1.039/lib

Hi, I'm working with support vector machine for the classification purpose, and I have a problem about the accuracy of prediction. I divided my data set in train (1/3 of enteire data set) and test (2/3 of data set) using the "sample" function. Each time I perform the svm model I obtain different result, according with the result of the "sample" function. I would like

Hi Did you try google? I got several answers using your question e.g. https://stackoverflow.com/questions/54687321/fill-area-between-lines-using-g gplot-in-r Cheers Petr > -----Original Message----- > From: R-help <r-help-bounces at r-project.org> On Behalf Of Luigi Marongiu > Sent: Friday, October 23, 2020 9:59 AM > To: r-help <r-help at r-project.org> > Subject:

Hi What about something like p+geom_ribbon(aes(ymin = slope_1*x + intercept_1 - 1/w[2], ymax = slope_1*x + intercept_1 + 1/w[2], fill = "grey70", alpha=0.1)) Cheers Petr > -----Original Message----- > From: Luigi Marongiu <marongiu.luigi at gmail.com> > Sent: Friday, October 23, 2020 11:11 AM > To: PIKAL Petr <petr.pikal at precheza.cz> > Cc: r-help

On Tue, Oct 27, 2020 at 6:04 PM Luigi Marongiu <marongiu.luigi at gmail.com> wrote: > > Hello, > I am using e1071 to run support vector machine. I would like to plot > the data with lattice and specifically show the hyperplanes created by > the system. > I can store the hyperplane as a contour in an object, and I can plot > one object at a time. Since there will be

Hello, I am running SVM and showing the results with ggplot2. The results include the decision boundaries, which are two dashed lines parallel to a solid line. I would like to remove the dashed lines and use a shaded area instead. How can I do that? Here is the code I wrote.. ``` library(e1071) library(ggplot2) set.seed(100) x1 = rnorm(100, mean = 0.2, sd = 0.1) y1 = rnorm(100, mean = 0.7, sd =

also from this site: https://plotly.com/ggplot2/geom_ribbon/ I get the answer is geom_ribbon but I am still missing something ``` #! plot p = ggplot(data = trainset, aes(x=x, y=y, color=z)) + geom_point() + scale_color_manual(values = c("red", "blue")) # show support vectors df_sv = trainset[svm_model$index, ] p = p + geom_point(data = df_sv, aes(x=x, y=y),

Dear All: I found a problem with the SVM internal cross-validation (CV) accuracy estimation in the e1071 package. File: Rsvm.c Line: 120 Today, it is: int j = rand()%(prob->l-i); Should be: int j = i + rand()%(prob->l-i); The erroneous code doesn't shuffle objects. Instead, it "randomly" moves objects from beginning to the end. In hope for a prompt response from the

Full_Name: Julien Gagneur Version: 2.2.1 OS: Linux (Suse 9.3) Submission from: (NULL) (194.94.44.4) Using the SparseM library (SparseM_0.66) and the e1071 library (e1071_1.5-12) I fail using svm method with a sparse matrix. Here is a sample example. I experienced the same problem under Windows. > library(SparseM) [1] "SparseM library loaded" > library("e1071")

Hello, I am using e1071 to run support vector machine. I would like to plot the data with lattice and specifically show the hyperplanes created by the system. I can store the hyperplane as a contour in an object, and I can plot one object at a time. Since there will be thousands of elements to plot, I can't manually add them one by one to the plot, so I tried to loop into them, but only the

Hi Put fill outside aes p+geom_ribbon(aes(ymin = slope_1*x + intercept_1 - 1/w[2], ymax = slope_1*x + intercept_1 + 1/w[2]), fill = "blue", alpha=0.1) The "hole" is because you have two levels of data (red and blue). To get rid of this you should put new data in ribbon call. Something like newdat <- trainset newdat$z <- factor(0) p+geom_ribbon(data=newdat, aes(ymin =

Hello, When calling several times the svm() function, I get different results. Do I miss something, or is there some random generation in the C library? In this second hypothesis, is it possible to fix an eventual seed? Thank you Pierre ### Example library('e1071') x = rnorm(100) # train set y = rnorm(100) c = runif(100)>0.5 x2 = rnorm(100)# test set y2 = rnorm(100) # learning a

I am starting to use svm from e1071 and I wonder how exactly crossvalidation is implemented. Whenever I run > svm.model <- svm(y ~ ., data = trainset, cross = 3) on my data I get dirrerent values for svm.model$MSE e.g. [1] 0.9517001 1.7069627 0.6108726 [1] 0.3634670 0.9165497 1.4606322 This suggests to me that data are scrambled each time - the last time I looked at libsvm python

Hello, Connoisseurs! Please explain to novices, why svm model gives different results in the loop with the same data? As a result, I can not find the best gamma and cost parameters. Also tune.svm yields results that can not be repeated. How can I avoid this? My sessionInfo: R version 2.11.1 (2010-05-31) x86_64-pc-linux-gnu locale: [1] LC_CTYPE=en_US.UTF-8 LC_NUMERIC=C