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.

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

all possible regression fails when model formula contains inline functions or interaction variables #4

Closed
aravindhebbali opened this issue Jun 2, 2017 · 1 comment

Comments

Projects
None yet
1 participant
@aravindhebbali
Copy link
Member

commented Jun 2, 2017

ols_all_subset() returns an error when the formula in the model contains inline functions or interaction variables.

library(caret)
data("Sacramento")
> lm_fit2 <- lm(price  ~ beds + baths + log(sqft), data = Sacramento)
> ols_all_subset(lm_fit2)
Error in eval(predvars, data, env) : object 'sqft' not found
Called from: eval(predvars, data, env)

# interaction variables
> lm_fit3 <- lm(mpg ~ disp + hp + wt + am * disp, data = mtcars)
> ols_all_subset(lm_fit3)
Error in ols_mallows_cp(out$model, model) : 
  model must be a subset of full model
Called from: ols_mallows_cp(out$model, model)

Session Info

> sessionInfo()
R version 3.4.0 (2017-04-21)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows >= 8 x64 (build 9200)

Matrix products: default

locale:
[1] LC_COLLATE=English_India.1252  LC_CTYPE=English_India.1252   
[3] LC_MONETARY=English_India.1252 LC_NUMERIC=C                  
[5] LC_TIME=English_India.1252    

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] purrr_0.2.2     dplyr_0.5.0     caret_6.0-76    ggplot2_2.2.1  
[5] lattice_0.20-35

loaded via a namespace (and not attached):
 [1] Rcpp_0.12.7        magrittr_1.5       splines_3.4.0     
 [4] MASS_7.3-47        munsell_0.4.3      colorspace_1.2-7  
 [7] R6_2.2.1           foreach_1.4.3      minqa_1.2.4       
[10] stringr_1.1.0      car_2.1-2          plyr_1.8.4        
[13] tools_3.4.0        parallel_3.4.0     nnet_7.3-12       
[16] pbkrtest_0.4-6     grid_3.4.0         gtable_0.2.0      
[19] nlme_3.1-125       mgcv_1.8-17        quantreg_5.19     
[22] DBI_0.5-1          MatrixModels_0.4-1 iterators_1.0.8   
[25] lme4_1.1-11        lazyeval_0.2.0     assertthat_0.2.0  
[28] tibble_1.2         Matrix_1.2-9       nloptr_1.0.4      
[31] reshape2_1.4.2     ModelMetrics_1.1.0 codetools_0.2-15  
[34] stringi_1.1.2      compiler_3.4.0     scales_0.4.1      
[37] stats4_3.4.0       SparseM_1.7       

@aravindhebbali aravindhebbali added the bug label Jun 2, 2017

@aravindhebbali aravindhebbali self-assigned this Jun 2, 2017

@aravindhebbali aravindhebbali added this to the v0.2.0 milestone Jun 5, 2017

aravindhebbali added a commit that referenced this issue Jun 5, 2017

@aravindhebbali

This comment has been minimized.

Copy link
Member Author

commented Jun 5, 2017

ols_all_subset() now works when model formula contains inline functions or interaction variables.

> library(olsrr)
> library(caret)
> data("Sacramento")

> lm_fit2 <- lm(price  ~ beds + baths + log(sqft), data = Sacramento)
> ols_all_subset(lm_fit2)
  Index N           Predictors R-Square Adj. R-Square Mallow's Cp
1     1 1            log(sqft)    0.568         0.567     52.6943
2     2 1                baths    0.331         0.331    589.5143
3     3 1                 beds    0.215         0.214    854.1735
4     4 2       beds log(sqft)    0.591          0.59      2.9559
5     5 2      baths log(sqft)    0.568         0.567     54.5318
6     6 2           beds baths    0.344         0.343    562.4425
7     7 3 beds baths log(sqft)    0.591          0.59           4

# interaction variables
> lm_fit3 <- lm(mpg ~ disp + hp + wt + am * disp, data = mtcars)
> ols_all_subset(lm_fit3)
   Index N            Predictors R-Square Adj. R-Square Mallow's Cp
1      1 1                    wt    0.753         0.745     15.7814
2      2 1                  disp    0.718         0.709     21.8906
3      3 1                    hp    0.602         0.589     42.4214
4      4 1                    am     0.36         0.338     85.4006
5      5 1               disp:am    0.025        -0.008    144.7555
6      6 2                 hp wt    0.827         0.815       4.682
7      7 2                 hp am    0.782         0.767     12.6088
8      8 2               disp wt    0.781         0.766     12.8044
9      9 2            wt disp:am    0.779         0.764     13.1616
10    10 2                 wt am    0.753         0.736     17.7811
11    11 2               disp hp    0.748         0.731     18.5949
12    12 2               disp am    0.733         0.715     21.2358
13    13 2            hp disp:am    0.723         0.703     23.1505
14    14 2          disp disp:am    0.719         0.699     23.8295
15    15 2            am disp:am    0.642         0.618     37.3666
16    16 3              hp wt am     0.84         0.823      4.3607
17    17 3         wt am disp:am     0.83         0.812      6.0674
18    18 3            disp hp wt    0.827         0.808       6.673
19    19 3         hp wt disp:am    0.827         0.809       6.573
20    20 3            disp hp am    0.799         0.778     11.5672
21    21 3       disp wt disp:am    0.796         0.774     12.1161
22    22 3       disp am disp:am     0.79         0.767     13.2175
23    23 3         hp am disp:am    0.789         0.767     13.2901
24    24 3            disp wt am    0.781         0.758     14.7845
25    25 3       disp hp disp:am    0.764         0.739     17.7208
26    26 4      hp wt am disp:am    0.853         0.831      4.0081
27    27 4         disp hp wt am     0.84         0.817      6.3004
28    28 4    disp wt am disp:am    0.836         0.812      6.9704
29    29 4    disp hp wt disp:am    0.827         0.802      8.5727
30    30 4    disp hp am disp:am    0.811         0.783     11.5263
31    31 5 disp hp wt am disp:am    0.853         0.825           6
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
You can’t perform that action at this time.