minor readme edits

Author: ercbk

README.Rmd

@@ -218,7 +218,7 @@ b + e + plot_layout(guides = "auto") +
   * Runtimes for n = 100 and n = 800 are close, and there's a large jump in runtime going from n = 2000 to n = 5000.  
   * The number of repeats has little effect on the amount of percent error.
   * For n = 100, there is substantially more variation in percent error than in the other sample sizes.  
-  * While there is a large runtime cost that comes with increasing the sample size from 2000 to 5000 obsservations, it doesn't seem to provide any benefit in gaining a more accurate estimate of the out-of-sample error.  
+  * While there is a large runtime cost that comes with increasing the sample size from 2000 to 5000 observations, it doesn't seem to provide any benefit in gaining a more accurate estimate of the out-of-sample error.  
 
 
 ```{r perf_build_times_r, echo=FALSE, message=FALSE}
@@ -244,7 +244,7 @@ subtargets_raw_r <- map_dfr(subtarget_bts_r$target, function(x) {
 subtargets_r <- subtargets_raw_r %>% 
       mutate(repeats = factor(repeats),
              n = factor(n),
-             elapsed = round(as.numeric(elapsed)/3600, 2),
+             elapsed = round(as.numeric(elapsed)/60, 2),
              percent_error = round(delta_error/oos_error, 3))
 
 readr::write_csv(subtargets_r, "performance-experiment/output/perf-exp-output-r.csv")
@@ -261,7 +261,7 @@ b_r <- ggplot(subtargets_r, aes(y = elapsed, x = repeats,
    geom_bar_text(position = "dodge", min.size = 9,
                  place = "right", contrast = TRUE) +
    coord_flip() +
-   labs(y = "Runtime (hrs)", x = "Repeats",
+   labs(y = "Runtime (minutes)", x = "Repeats",
         fill = "Sample Size") +
    theme(title = element_text(family = "Roboto"),
          text = element_text(family = "Roboto"),

README.md

@@ -127,7 +127,7 @@ implementation and method used.
   - For n = 100, there is substantially more variation in percent error
     than in the other sample sizes.  
   - While there is a large runtime cost that comes with increasing the
-    sample size from 2000 to 5000 obsservations, it doesn’t seem to
+    sample size from 2000 to 5000 observations, it doesn’t seem to
     provide any benefit in gaining a more accurate estimate of the
     out-of-sample error.
 

README_files/figure-gfm/kj-patch-1.png

@@ -1,21 +1,21 @@
 subtarget,n,repeats,method,oos_error,ncv_error,delta_error,chosen_algorithm,mixture,penalty,mtry,trees,elapsed,percent_error
-ncv_results_r_100_2cf8f29f,100,4,raschka,2.19966,1.99714,0.20252000000000026,glmnet,0.9937975914264098,3.6844362948689596e-6,NA,NA,0.11,0.092
-ncv_results_r_100_73d34817,100,1,raschka,2.20712,1.92178,0.28534000000000015,glmnet,0.2830161499953829,0.4736074164981174,NA,NA,0.03,0.129
-ncv_results_r_100_80f90de9,100,3,raschka,2.24343,2.05019,0.19323999999999986,glmnet,0.8434229354886338,0.38592594070682457,NA,NA,0.08,0.086
-ncv_results_r_100_c6a30309,100,5,raschka,2.19318,1.99697,0.19621,glmnet,0.27113973276223985,0.27236778939605205,NA,NA,0.13,0.089
-ncv_results_r_100_ed9aeedc,100,2,raschka,2.19315,2.02878,0.16437000000000035,glmnet,0.3506598100136034,0.24982118433658881,NA,NA,0.05,0.075
-ncv_results_r_2000_97d0d6fc,2000,4,raschka,1.39104,1.40004,0.008999999999999897,rf,NA,NA,5,1167,0.14,0.006
-ncv_results_r_2000_a6a8efea,2000,1,raschka,1.38907,1.40676,0.017689999999999984,rf,NA,NA,6,227,0.05,0.013
-ncv_results_r_2000_b959e941,2000,2,raschka,1.38666,1.39311,0.006450000000000067,rf,NA,NA,5,1167,0.08,0.005
-ncv_results_r_2000_e7878a5b,2000,5,raschka,1.38627,1.39816,0.011890000000000178,rf,NA,NA,6,1309,0.18,0.009
-ncv_results_r_2000_f2c5e5eb,2000,3,raschka,1.39259,1.40355,0.01096000000000008,rf,NA,NA,7,576,0.11,0.008
-ncv_results_r_5000_0131c1ff,5000,5,raschka,1.24466,1.27121,0.02654999999999985,rf,NA,NA,5,1454,0.4,0.021
-ncv_results_r_5000_5b1d8a27,5000,3,raschka,1.24056,1.27153,0.030969999999999942,rf,NA,NA,6,1874,0.27,0.025
-ncv_results_r_5000_86c8ceed,5000,4,raschka,1.2404,1.28051,0.04011000000000009,rf,NA,NA,6,1281,0.34,0.032
-ncv_results_r_5000_8bc71439,5000,2,raschka,1.24009,1.27624,0.036150000000000126,rf,NA,NA,6,446,0.19,0.029
-ncv_results_r_5000_e931a398,5000,1,raschka,1.24406,1.28087,0.03681000000000001,rf,NA,NA,5,1462,0.13,0.03
-ncv_results_r_800_0f9280b4,800,4,raschka,1.6537,1.63063,0.023069999999999924,rf,NA,NA,7,92,0.12,0.014
-ncv_results_r_800_2ff75ff1,800,5,raschka,1.64388,1.61275,0.031130000000000102,rf,NA,NA,7,162,0.14,0.019
-ncv_results_r_800_67abc218,800,3,raschka,1.63369,1.61903,0.014660000000000117,rf,NA,NA,9,256,0.09,0.009
-ncv_results_r_800_a8ac41db,800,2,raschka,1.63013,1.62835,0.0017800000000001148,rf,NA,NA,9,1807,0.06,0.001
-ncv_results_r_800_e4b0a9bc,800,1,raschka,1.63248,1.59467,0.0378099999999999,rf,NA,NA,7,1289,0.04,0.023
+ncv_results_r_100_2cf8f29f,100,4,raschka,2.19966,1.99714,0.20252000000000026,glmnet,0.9937975914264098,3.6844362948689596e-6,NA,NA,6.48,0.092
+ncv_results_r_100_73d34817,100,1,raschka,2.20712,1.92178,0.28534000000000015,glmnet,0.2830161499953829,0.4736074164981174,NA,NA,1.65,0.129
+ncv_results_r_100_80f90de9,100,3,raschka,2.24343,2.05019,0.19323999999999986,glmnet,0.8434229354886338,0.38592594070682457,NA,NA,4.75,0.086
+ncv_results_r_100_c6a30309,100,5,raschka,2.19318,1.99697,0.19621,glmnet,0.27113973276223985,0.27236778939605205,NA,NA,7.9,0.089
+ncv_results_r_100_ed9aeedc,100,2,raschka,2.19315,2.02878,0.16437000000000035,glmnet,0.3506598100136034,0.24982118433658881,NA,NA,3.13,0.075
+ncv_results_r_2000_97d0d6fc,2000,4,raschka,1.39104,1.40004,0.008999999999999897,rf,NA,NA,5,1167,8.43,0.006
+ncv_results_r_2000_a6a8efea,2000,1,raschka,1.38907,1.40676,0.017689999999999984,rf,NA,NA,6,227,3.08,0.013
+ncv_results_r_2000_b959e941,2000,2,raschka,1.38666,1.39311,0.006450000000000067,rf,NA,NA,5,1167,4.85,0.005
+ncv_results_r_2000_e7878a5b,2000,5,raschka,1.38627,1.39816,0.011890000000000178,rf,NA,NA,6,1309,10.68,0.009
+ncv_results_r_2000_f2c5e5eb,2000,3,raschka,1.39259,1.40355,0.01096000000000008,rf,NA,NA,7,576,6.52,0.008
+ncv_results_r_5000_0131c1ff,5000,5,raschka,1.24466,1.27121,0.02654999999999985,rf,NA,NA,5,1454,23.95,0.021
+ncv_results_r_5000_5b1d8a27,5000,3,raschka,1.24056,1.27153,0.030969999999999942,rf,NA,NA,6,1874,16.2,0.025
+ncv_results_r_5000_86c8ceed,5000,4,raschka,1.2404,1.28051,0.04011000000000009,rf,NA,NA,6,1281,20.13,0.032
+ncv_results_r_5000_8bc71439,5000,2,raschka,1.24009,1.27624,0.036150000000000126,rf,NA,NA,6,446,11.53,0.029
+ncv_results_r_5000_e931a398,5000,1,raschka,1.24406,1.28087,0.03681000000000001,rf,NA,NA,5,1462,7.7,0.03
+ncv_results_r_800_0f9280b4,800,4,raschka,1.6537,1.63063,0.023069999999999924,rf,NA,NA,7,92,7.27,0.014
+ncv_results_r_800_2ff75ff1,800,5,raschka,1.64388,1.61275,0.031130000000000102,rf,NA,NA,7,162,8.52,0.019
+ncv_results_r_800_67abc218,800,3,raschka,1.63369,1.61903,0.014660000000000117,rf,NA,NA,9,256,5.37,0.009
+ncv_results_r_800_a8ac41db,800,2,raschka,1.63013,1.62835,0.0017800000000001148,rf,NA,NA,9,1807,3.88,0.001
+ncv_results_r_800_e4b0a9bc,800,1,raschka,1.63248,1.59467,0.0378099999999999,rf,NA,NA,7,1289,2.22,0.023