Christopher Bail
2006-Jun-14 13:59 UTC
[R] fclustIndex(package e1071) error: LaPack Routine dgesv
Dear colleagues: Despite my best efforts, I have not been able to understand/overcome an error message I received while running the fclustIndex command in package e1071, which produces validity measures for the fuzzy c-means clustering algorithm. I am relatively new to R-- and still depend heavily on Rcmdr-- and so I apologize in advance if there is an obvious answer to my question: My code is as follows: library(e1071) Dataset <- read.dta("/Users/chris/Desktop/Fuzzy Cluster.dta", convert.dates=TRUE, convert.factors=TRUE, missing.type=TRUE, convert.underscore=TRUE, warn.missing.labels=TRUE) row.names(Dataset) <- as.character(Dataset$cntry) Dataset$cntry <- NULL cl <- cmeans(Dataset, 4, 20, verbose=TRUE, method="cmeans") resultindexes <- fclustIndex(cl, Dataset, index= "all") resultindexes I am receiving the following error message: ERROR: Lapack routine dgesv I have tried running the example for fclustIndex and it works fine. The code above is based on the example from the manual (below). I also checked that I have the latest version installed. I have also had no trouble running similar commands from other packages which leads me to believe that everything is installed/compiled properly-- where have I gone wrong? The description of fclustIndex in the e1071 .pdf is available via the following link: http://rweb.stat.umn.edu/R/library/e1071/html/fclustIndex.html I thank you in advance for your time and help. Sincerely, Christopher Bail
Possibly Parallel Threads
- fclustindex, e1071 package
- new version of e1071 on CRAN
- Error in solve.default(res$hessian * n.used) :Lapack routine dgesv: system is exactly singular
- Lapack routine dgesv: system is exactly singular
- sem : Error in solve.default(C[ind, ind]) : Lapack routine dgesv: system is exactly singular