Stack Overflow
Stack Overflow

Questions tagged [e1071]

27 questions
3
votes
1 answer

SVM performance not consistent with AUC score

I have a dataset that contains information about patients. It includes several variables and their clinical status (0 if they are healthy, 1 if they are sick). I have tried to implement an SVM model to predict patient status based on these…
A Jorg
  • 141
  • 1
  • 5
2
votes
0 answers

Installing package e1071

I am trying to use 'rfe' function from 'caret': lmProfile <- rfe(x=trainData[, 0:(ncol(trainData)-1)], y=trainData$target, sizes = subsets, rfeControl = ctrl) but I get the following error: Error: package e1071 is…
Vivi
  • 21
  • 1
  • 4
1
vote
1 answer

Why do the "DescTools" & "e1071" packages cause an error when trying to view lists containing dist objects?

I have the following dataframe, 'A'. I calculate a distance matrix 'B' from it. Then I add that distance matrix 'B' to a list 'C' and view it. A <- data.frame(x = c(1:10), y = c(21:30)) B <- dist(A) C <- list(B) View(C) So far so…
bkl
  • 13
  • 4
1
vote
0 answers

How to estimate gamma and cost parameters for SVM quickly

I want to train SVMs in R and I know there are functions such as e1071::tune.svm() that can be used to find the optimal parameters for the SVM. However, it seems there are some formulas out there (e.g. used in this report) that can give you a…
Manuel Popp
  • 1,003
  • 1
  • 10
  • 33
1
vote
1 answer

Does the kurtosis calculation in the e1071 package in R need more than 3 values?

When calculating kurtosis using the e1071 package like the following: x_test <- c(100,98, 4) kurtosis(x_test) I always get -2.33 no matter what 3 numbers I pick. With 2 numbers, it's always -2.75. However when using other methods (such as pandas in…
user16182116
  • 13
  • 4
1
vote
0 answers

Error in SVM Regression looping over Kernels in R

I want to loop over each Kernal for SVM regression Getting error 'kernel_name' not found also want output for each kernel in tabular form with Rsquare, AdjRsq and RMSE library(e1071) test_data = #upload test data here. training_data=…
Ajit
  • 39
  • 6
1
vote
2 answers

R: e1071 svm function - is it necessary to convert categorical to dummies?

I know svm model needs preprocessing that converts categorical variables into dummy variables. However, when I am using e1071's svm function to fit a model with unconverted data (see train and test), no error pops up. I am assuming the function…
Rachel Zhang
  • 562
  • 6
  • 20
1
vote
1 answer

Use F1 Score instead of Accuracy to Optimize SVM Parameters

I am using the e1071 'tune' function to optimize an SVM model. I would like to use F1 instead of Accuracy as the value to optimize for. I have found on this post: Optimize F-score in e1071 package that I need to define a new error.fun. The…
Jamie
  • 555
  • 3
  • 14
1
vote
1 answer

Which algorithm does R use for computing one-class SVM ? (package e1071)

Which algorithm does R use for computing one-class SVM ? This is the function e1071::svm(..., type=one-classification, ...) I have found this very nice blog, where author writes about two algorithms for one-class SVM. Which one does the function…
pikachu
  • 690
  • 1
  • 6
  • 17
1
vote
1 answer

What is the maximal number of iterations in the e1071 svm() function?

I know that there is a hard coded number of maximal iterations in the e1071 svm() function, but can someone tell me how high this number is?
Mirko
  • 89
  • 5
1
vote
2 answers

How can I plot two ROC Curves on the same plot using PRECREC package

I am using the precrec package in order to evaluate multiple models and plotting ROC and PR-ROC. I want to do a model comparison at the end, but it seems I can't plot both models on the same plot. Here is my attempt:…
Kermit
  • 3,112
  • 2
  • 10
  • 34
0
votes
0 answers

How does the kernel SVM in e1071 predict?

I am trying to understand the way the e1071 package obtains its SVM predictions in a two-class classification framework. Consider the following toy example. library(mvtnorm) library(e1071) n <- 50 ### Gaussians eps <- 0.05 data1 <-…
Claudio Moneo
  • 489
  • 1
  • 4
  • 10
0
votes
0 answers

SVM Plot e1071 plots single color

I am trying to plot my SVM classification with usinf e1071 library.However, the classification plot shows only single value for my parameters.Even though I change the selected parameters to create 2d classification plot it is…
Mert Pınarbaşı
  • 63
  • 5
0
votes
1 answer

"Model is empty! error using tune for svm method in package e1071

I'm trying to tune hyperparameters epsilon and cost using the tune function in e1071, but I keep getting this error whenever I try to expand the ranges of values that I want to test: "Error in predict.svm(ret, xhold, decision.values = TRUE) : Model…
Antonio Robelo
  • 1
0
votes
0 answers

No models other than naiveBayes work with text categorization

I have a text classification problem with a text feature 'DESCRIPTION' and output variable 'TYPE', which has three different values. I perform the preprocessing steps and then run the model but I get the following error when I run the confusion…
Neha
  • 3
  • 3
1
2