Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

error in cubist translation #57

Closed
topepo opened this issue Jul 16, 2019 · 2 comments · Fixed by #100
Closed

error in cubist translation #57

topepo opened this issue Jul 16, 2019 · 2 comments · Fixed by #100
Labels
bug an unexpected problem or unintended behavior

Comments

@topepo
Copy link
Member

topepo commented Jul 16, 2019

Model object generated using Cubist_0.2.2

library(tidypredict)
library(sessioninfo)
options(width = 100)

mod <-
  structure(
    list(
      data = "15\\.5,8,318.0,150,2.76,3.520,16.87,0,0,3,2\n15\\.5,8,318.0,150,2.76,3.520,16.87,0,0,3,2\n27\\.3,4,79.0,66,4.08,1.935,18.90,1,1,4,1\n21\\.4,6,258.0,110,3.08,3.215,19.44,1,0,3,1\n21,6,160.0,110,3.90,2.875,17.02,0,1,4,4\n21,6,160.0,110,3.90,2.620,16.46,0,1,4,4\n15\\.8,8,351.0,264,4.22,3.170,14.50,0,1,5,4\n14\\.7,8,440.0,230,3.23,5.345,17.42,0,0,3,4\n10\\.4,8,460.0,215,3.00,5.424,17.82,0,0,3,4\n15\\.2,8,275.8,180,3.07,3.780,18.00,0,0,3,3\n14\\.7,8,440.0,230,3.23,5.345,17.42,0,0,3,4\n18\\.1,6,225.0,105,2.76,3.460,20.22,1,0,3,1\n22\\.8,4,140.8,95,3.92,3.150,22.90,1,0,4,2\n21,6,160.0,110,3.90,2.620,16.46,0,1,4,4\n15,8,301.0,335,3.54,3.570,14.60,0,1,5,8\n21\\.4,4,121.0,109,4.11,2.780,18.60,1,1,4,2\n18\\.1,6,225.0,105,2.76,3.460,20.22,1,0,3,1\n10\\.4,8,460.0,215,3.00,5.424,17.82,0,0,3,4\n13\\.3,8,350.0,245,3.73,3.840,15.41,0,0,3,4\n14\\.7,8,440.0,230,3.23,5.345,17.42,0,0,3,4\n15\\.8,8,351.0,264,4.22,3.170,14.50,0,1,5,4\n26,4,120.3,91,4.43,2.140,16.70,0,1,5,2\n16\\.4,8,275.8,180,3.07,4.070,17.40,0,0,3,3\n22\\.8,4,108.0,93,3.85,2.320,18.61,1,1,4,1\n21\\.4,4,121.0,109,4.11,2.780,18.60,1,1,4,2\n19\\.7,6,145.0,175,3.62,2.770,15.50,0,1,5,6\n15\\.8,8,351.0,264,4.22,3.170,14.50,0,1,5,4\n15\\.2,8,304.0,150,3.15,3.435,17.30,0,0,3,2\n26,4,120.3,91,4.43,2.140,16.70,0,1,5,2\n17\\.3,8,275.8,180,3.07,3.730,17.60,0,0,3,3\n21\\.4,4,121.0,109,4.11,2.780,18.60,1,1,4,2\n22\\.8,4,108.0,93,3.85,2.320,18.61,1,1,4,1",
      names = "| Generated using R version 3.6.0 (2019-04-26)\n| on Mon Jul 15 20:36:50 2019\noutcome.\n\noutcome: continuous.\ncyl: continuous.\ndisp: continuous.\nhp: continuous.\ndrat: continuous.\nwt: continuous.\nqsec: continuous.\nvs: continuous.\nam: continuous.\ngear: continuous.\ncarb: continuous.\n",
      caseWeights = FALSE,
      model = "id=\"Cubist 2.07 GPL Edition 2019-07-15\"\nprec=\"1\" globalmean=\"18.37188\" extrap=\"1\" insts=\"0\" ceiling=\"44.2\" floor=\"0\"\natt=\"outcome\" mean=\"18.37\" sd=\"4.326829\" min=\"10.4\" max=\"27.3\"\natt=\"cyl\" mean=\"6.4\" sd=\"1.740181\" min=\"4\" max=\"8\"\natt=\"disp\" mean=\"252.61\" sd=\"121.1964\" min=\"79\" max=\"460\"\natt=\"hp\" mean=\"161.3\" sd=\"69.12569\" min=\"66\" max=\"335\"\natt=\"drat\" mean=\"3.572\" sd=\"0.5478398\" min=\"2.76\" max=\"4.43\"\natt=\"wt\" mean=\"3.4132\" sd=\"1.007245\" min=\"1.935\" max=\"5.424\"\natt=\"qsec\" mean=\"17.468\" sd=\"1.836215\" min=\"14.5\" max=\"22.9\"\natt=\"vs\" mean=\"0.3\" sd=\"0.4709301\" min=\"0\" max=\"1\"\natt=\"am\" mean=\"0.5\" sd=\"0.5080015\" min=\"0\" max=\"1\"\natt=\"gear\" mean=\"3.7\" sd=\"0.8032203\" min=\"3\" max=\"5\"\natt=\"carb\" mean=\"2.9\" sd=\"1.596052\" min=\"1\" max=\"8\"\nentries=\"1\"\nrules=\"1\"\nconds=\"0\" cover=\"32\" mean=\"18.37\" loval=\"10.4\" hival=\"27.3\" esterr=\"1.46\"\ncoeff=\"20.52\" att=\"disp\" coeff=\"-0.0294\" att=\"drat\" coeff=\"1.33\"\n",
      output = "\nCubist [Release 2.07 GPL Edition]  Mon Jul 15 20:36:50 2019\n---------------------------------\n\n    Target attribute `outcome'\n\nRead 32 cases (11 attributes) from undefined.data\n\nModel:\n\n  Rule 1: [32 cases, mean 18.37, range 10.4 to 27.3, est err 1.46]\n\n\toutcome = 20.52 - 0.0294 disp + 1.33 drat\n\n\nEvaluation on training data (32 cases):\n\n    Average  |error|               0.71\n    Relative |error|               0.19\n    Correlation coefficient        0.94\n\n\n\tAttribute usage:\n\t  Conds  Model\n\n\t         100%    disp\n\t         100%    drat\n\n\nTime: 0.0 secs\n",
      control = list(
        unbiased = FALSE,
        rules = 100,
        extrapolation = 1,
        sample = 0,
        label = "outcome",
        seed = 27L
      ),
      committees = 1,
      maxd = 2.3,
      dims = c(32L, 10L),
      splits = NULL,
      usage = structure(
        list(
          Conditions = c(0, 0, 0, 0, 0, 0, 0, 0, 0, 0),
          Model = c(100,
                    100, 0, 0, 0, 0, 0, 0, 0, 0),
          Variable = c(
            "disp",
            "drat",
            "cyl",
            "hp",
            "wt",
            "qsec",
            "vs",
            "am",
            "gear",
            "carb"
          )
        ),
        row.names = c(NA,-10L),
        class = "data.frame"
      ),
      call = as.call(quote(
        cubist.default(
          x = dat[, names(dat) != ".outcome", drop = FALSE],
          y = dat$.outcome,
          committees = 1,
          control = ctrl
        )
      )),
      coefficients = structure(
        list(
          `(Intercept)` = 20.52,
          cyl = NA_real_,
          disp = -0.0294,
          hp = NA_real_,
          drat = 1.33,
          wt = NA_real_,
          qsec = NA_real_,
          vs = NA_real_,
          am = NA_real_,
          gear = NA_real_,
          carb = NA_real_,
          committee = "1",
          rule = "1"
        ),
        row.names = "(Intercept)",
        reshapeWide = list(
          v.names = "value",
          timevar = "var",
          idvar = "tmp",
          times = structure(
            c(1L,
              4L, 5L, 8L, 6L, 11L, 9L, 10L, 2L, 7L, 3L),
            .Label = c(
              "(Intercept)",
              "am",
              "carb",
              "cyl",
              "disp",
              "drat",
              "gear",
              "hp",
              "qsec",
              "vs",
              "wt"
            ),
            class = "factor"
          ),
          varying = structure(
            c(
              "value.(Intercept)",
              "value.cyl",
              "value.disp",
              "value.hp",
              "value.drat",
              "value.wt",
              "value.qsec",
              "value.vs",
              "value.am",
              "value.gear",
              "value.carb"
            ),
            .Dim = c(1L, 11L)
          )
        ),
        class = "data.frame"
      ),
      vars = list(
        all = c(
          "cyl",
          "disp",
          "hp",
          "drat",
          "wt",
          "qsec",
          "vs",
          "am",
          "gear",
          "carb"
        ),
        used = c("drat", "committee",
                 "rule")
      )
    ),
    class = "cubist"
  )

tidypredict::tidypredict_fit(mod)
#> Error in splits[splits$rule == .x & splits$committee == comm, ]: incorrect number of dimensions

session_info()
#> ─ Session info ───────────────────────────────────────────────────────────────────────────────────
#>  setting  value                       
#>  version  R version 3.6.0 (2019-04-26)
#>  os       macOS High Sierra 10.13.6   
#>  system   x86_64, darwin15.6.0        
#>  ui       X11                         
#>  language (EN)                        
#>  collate  en_US.UTF-8                 
#>  ctype    en_US.UTF-8                 
#>  tz       America/New_York            
#>  date     2019-07-15                  
#> 
#> ─ Packages ───────────────────────────────────────────────────────────────────────────────────────
#>  package     * version    date       lib source                            
#>  assertthat    0.2.1      2019-03-21 [1] CRAN (R 3.6.0)                    
#>  cli           1.1.0      2019-03-19 [1] CRAN (R 3.6.0)                    
#>  crayon        1.3.4      2017-09-16 [1] CRAN (R 3.6.0)                    
#>  digest        0.6.20     2019-07-04 [1] CRAN (R 3.6.0)                    
#>  dplyr         0.8.3      2019-07-04 [1] CRAN (R 3.6.0)                    
#>  evaluate      0.14       2019-05-28 [1] CRAN (R 3.6.0)                    
#>  generics      0.0.2      2018-11-29 [1] CRAN (R 3.6.0)                    
#>  glue          1.3.1      2019-03-12 [1] CRAN (R 3.6.0)                    
#>  highr         0.8        2019-03-20 [1] CRAN (R 3.6.0)                    
#>  htmltools     0.3.6      2017-04-28 [1] CRAN (R 3.6.0)                    
#>  knitr         1.23       2019-05-18 [1] CRAN (R 3.6.0)                    
#>  magrittr      1.5        2014-11-22 [1] CRAN (R 3.6.0)                    
#>  pillar        1.4.2      2019-06-29 [1] CRAN (R 3.6.0)                    
#>  pkgconfig     2.0.2      2018-08-16 [1] CRAN (R 3.6.0)                    
#>  purrr         0.3.2      2019-03-15 [1] CRAN (R 3.6.0)                    
#>  R6            2.4.0      2019-02-14 [1] CRAN (R 3.6.0)                    
#>  Rcpp          1.0.1      2019-03-17 [1] CRAN (R 3.6.0)                    
#>  rlang         0.4.0.9000 2019-07-09 [1] Github (r-lib/rlang@a3d7e47)      
#>  rmarkdown     1.14       2019-07-12 [1] CRAN (R 3.6.0)                    
#>  sessioninfo * 1.1.1.9000 2019-03-26 [1] Github (r-lib/sessioninfo@dfb3ea8)
#>  stringi       1.4.3      2019-03-12 [1] CRAN (R 3.6.0)                    
#>  stringr       1.4.0      2019-02-10 [1] CRAN (R 3.6.0)                    
#>  tibble        2.1.3      2019-06-06 [1] CRAN (R 3.6.0)                    
#>  tidypredict * 0.4.2      2019-07-15 [1] local                             
#>  tidyselect    0.2.5      2018-10-11 [1] CRAN (R 3.6.0)                    
#>  withr         2.1.2      2018-03-15 [1] CRAN (R 3.6.0)                    
#>  xfun          0.8        2019-06-25 [1] CRAN (R 3.6.0)                    
#>  yaml          2.2.0      2018-07-25 [1] CRAN (R 3.6.0)                    
#> 
#> [1] /Library/Frameworks/R.framework/Versions/3.6/Resources/library

Created on 2019-07-15 by the reprex package (v0.2.1)
@topepo
Copy link
Member Author

topepo commented Jul 18, 2019

The underlying issue is that the model is:

Model:

  Rule 1: [32 cases, mean 18.37, range 10.4 to 27.3, est err 1.46]

	outcome = 20.52 - 0.0294 disp + 1.33 drat

so there is no information on the splitting vars (model$splits is NULL).

@topepo topepo mentioned this issue Jan 7, 2020
Closed
@topepo topepo added the bug an unexpected problem or unintended behavior label Apr 3, 2020
@topepo topepo mentioned this issue Apr 3, 2020
Open
@edgararuiz edgararuiz mentioned this issue Sep 27, 2021
Merged
@github-actions
Copy link

This issue has been automatically locked. If you believe you have found a related problem, please file a new issue (with a reprex: https://reprex.tidyverse.org) and link to this issue.

@github-actions github-actions bot locked and limited conversation to collaborators Oct 13, 2021
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Assignees
No one assigned
Labels
bug an unexpected problem or unintended behavior
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Adds ability to handle single committee and single rule Cubist models edgararuiz/tidypredict
1 participant
@topepo