Example of allowed libSizes for tau or negative tp
heinonmatti opened this issue · 4 comments
Hi,
Stupid question: I've been stuck for days trying to figure out how to use rEDM::CCM() with tau > 0 and tp < -1.
Would it be possible to give an example of how to specify libSizes here?
I keep getting an error such as:
Error in RtoCpp_CCM(pathIn, dataFile, dataFrame, pathOut, predictFile, :
DataFrame::DataFrameFromColumnIndex(): A column index (60) exceeds the data frame domain.
I cannot use the example in https://ha0ye.github.io/rEDM/articles/rEDM.html, because the same happens there (additionally, target_column and lib_column need to be specified as.character() for the code to work)
output <- do.call(rbind, lapply(seq_len(NROW(params)), function(i) {
ccm(paramecium_didinium, E = params$E[i], lib_sizes = NROW(paramecium_didinium),
random_libs = FALSE, lib_column = params$lib_column[i], target_column = params$target_column[i],
tp = params$tp[i], silent = TRUE)
}))
It looks like there is a problem in the code validation checks with CCM and tau > 0. We need to look into this.
I don't think the problem has to do with libSizes, which is documented here.
It looks like the case of positive tau and negative Tp works in Simplex, which is the underlying method of CCM. This can offer a rather laborious workaround. Another option is to use the legacy package from which the example you cite is formed.
Please note that the example you cite is from a legacy version of rEDM. The current version suggests to use the current API (CCM rather than the legacy version ccm), as noted in the rEDM NEWS. The new API are direct calls into the underlying C++ library. The legacy API has an intermediate wrapper layer that is not complete.
Please also note your rEDM version and environment with sessionInfo().
Thanks for the quick reaction!
Another option is to use the legacy package from which the example you cite is formed.
Which version should I download to have a go? (given CCM in the current version gives an equivalent error to ccm)
My current rEDM is v. 1.9.1
sessionInfo:
R version 4.1.0 (2021-05-18)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 10 x64 (build 18363)
Matrix products: default
locale:
[1] LC_COLLATE=Finnish_Finland.1252
[2] LC_CTYPE=Finnish_Finland.1252
[3] LC_MONETARY=Finnish_Finland.1252
[4] LC_NUMERIC=C
[5] LC_TIME=Finnish_Finland.1252
attached base packages:
[1] stats graphics grDevices utils
[5] datasets methods base
other attached packages:
[1] ggridges_0.5.3 rEDM_1.9.1
[3] forcats_0.5.1 stringr_1.4.0
[5] dplyr_1.0.7 purrr_0.3.4
[7] readr_2.0.1 tidyr_1.1.3
[9] tibble_3.1.4 ggplot2_3.3.5
[11] tidyverse_1.3.1
loaded via a namespace (and not attached):
[1] readxl_1.3.1 backports_1.2.1
[3] plyr_1.8.6 igraph_1.2.6
[5] sp_1.4-5 usethis_2.0.1
[7] digest_0.6.27 httpcache_1.2.0
[9] yardstick_0.0.8 foreach_1.5.1
[11] casnet_0.2.0 htmltools_0.5.2
[13] viridis_0.6.1 lars_1.2
[15] fansi_0.5.0 checkmate_2.0.0
[17] magrittr_2.0.1 memoise_2.0.0
[19] cluster_2.1.2 doParallel_1.0.16
[21] tzdb_0.1.2 openxlsx_4.2.4
[23] remotes_2.4.0 modelr_0.1.8
[25] vroom_1.5.4 stabledist_0.7-1
[27] prettyunits_1.1.1 colorspace_2.0-2
[29] ecp_3.1.3 rvest_1.0.1
[31] ggrepel_0.9.1 haven_2.4.3
[33] xfun_0.25 callr_3.7.0
[35] crayon_1.4.1 jsonlite_1.7.2
[37] zoo_1.8-9 iterators_1.0.13
[39] glue_1.4.2 gtable_0.3.0
[41] car_3.0-11 pkgbuild_1.2.0
[43] DEoptimR_1.0-9 abind_1.4-5
[45] VIM_6.1.1 scales_1.1.1
[47] DBI_1.1.1 Rcpp_1.0.7
[49] laeken_0.5.1 viridisLite_0.4.0
[51] units_0.7-2 clue_0.3-59
[53] TSMCP_1.0 bit_4.0.4
[55] foreign_0.8-81 proxy_0.4-26
[57] DT_0.18 vcd_1.4-8
[59] htmlwidgets_1.5.3 timeSeries_3062.100
[61] httr_1.4.2 ellipsis_0.3.2
[63] spatial_7.3-14 pkgconfig_2.0.3
[65] farver_2.1.0 nnet_7.3-16
[67] invctr_0.1.0 dbplyr_2.1.1
[69] utf8_1.2.2 tidyselect_1.1.1
[71] labeling_0.4.2 rlang_0.4.11
[73] munsell_0.5.0 cellranger_1.1.0
[75] tools_4.1.0 cachem_1.0.6
[77] cli_3.0.1 generics_0.1.0
[79] ranger_0.13.1 devtools_2.4.2
[81] broom_0.7.9 mpmi_0.43.1
[83] evaluate_0.14 fastmap_1.1.0
[85] yaml_2.2.1 bit64_4.0.5
[87] processx_3.5.2 knitr_1.33
[89] fs_1.5.0 plus_1.0
[91] zip_2.2.0 pander_0.6.4
[93] robustbase_0.93-8 visdat_0.5.3
[95] xml2_1.3.2 compiler_4.1.0
[97] rstudioapi_0.13 curl_4.3.2
[99] e1071_1.7-8 testthat_3.0.4
[101] reprex_2.0.1 rjstat_0.4.1
[103] stringi_1.7.4 statip_0.2.3
[105] ps_1.6.0 desc_1.3.0
[107] modeest_2.4.0 lattice_0.20-44
[109] fBasics_3042.89.1 Matrix_1.3-3
[111] classInt_0.4-3 vctrs_0.3.8
[113] pillar_1.6.2 lifecycle_1.0.0
[115] lmtest_0.9-38 data.table_1.14.0
[117] cowplot_1.1.1 R6_2.5.1
[119] stable_1.1.4 KernSmooth_2.23-20
[121] gridExtra_2.3 rio_0.5.27
[123] sessioninfo_1.1.1 codetools_0.2-18
[125] COVID19_2.3.2 boot_1.3-28
[127] MASS_7.3-54 assertthat_0.2.1
[129] pkgload_1.2.1 rprojroot_2.0.2
[131] fmi2_0.2.0 withr_2.4.2
[133] naniar_0.6.1 parallel_4.1.0
[135] hms_1.1.0 grid_4.1.0
[137] rpart_4.1-15 timeDate_3043.102
[139] class_7.3-19 rmarkdown_2.10
[141] carData_3.0-4 rmutil_1.1.5
[143] sf_1.0-2 pROC_1.17.0.1
[145] lubridate_1.7.10
Thank you for the sessionInfo, and, for reporting the bug.
To use the legacy version hosted on CRAN, here are three options, the first two within R, the third as a command line from a system console:
require(devtools)
install_version("rEDM", version = "0.7.3", repos = "http://cran.us.r-project.org")
url = "https://cran.r-project.org/src/contrib/Archive/rEDM/rEDM_0.7.3.tar.gz"
install.packages( url, repos = NULL, type = "source" )
wget http://cran.r-project.org/src/contrib/Archive/rEDM/rEDM_0.7.3.tar.gz
R CMD INSTALL rEDM_0.7.3.tar.gz
I believe that Hao Ye also publishes the legacy packages on his github.
This has been fixed in version 1.9.2, now available on CRAN.