Open msmith01 opened 4 years ago
I discuss the error in a reply to one of the issues here:
https://github.com/ymattu/MlBayesOpt/issues/55
I still get a warning which is something to do with the following line:
cv_folds <- KFold(datalabel, nfolds = n_folds, stratified = TRUE, seed = seed)
Running the new xgb_cv_opt function with the following data should work:
xgb_cv_opt
library(MlBayesOpt) library(dplyr) library(Matrix) library(xgboost) library(rBayesianOptimization) df <- iris label_Species <- iris$Species xgb_cv_opt(data = df, label = label_Species, objectfun = "reg:linear", evalmetric = "rmse", n_folds = 2, eta_range = c(0.1, 1L), max_depth_range = c(4L, 6L), nrounds_range = c(70, 160L), subsample_range = c(0.1, 1L), bytree_range = c(0.4, 1L), init_points = 4, n_iter = 10, acq = "ucb", kappa = 2.576, eps = 0, optkernel = list(type = "exponential", power = 2), classes = NULL, seed = 0)
Output:
> library(MlBayesOpt) > library(dplyr) > library(Matrix) > library(xgboost) > library(rBayesianOptimization) > df <- iris > label_Species <- iris$Species > xgb_cv_opt(data = df, + label = label_Species, + objectfun = "reg:linear", evalmetric = "rmse", n_folds = 2, eta_range = c(0.1, 1L), + max_depth_range = c(4L, 6L), nrounds_range = c(70, 160L), + subsample_range = c(0.1, 1L), bytree_range = c(0.4, 1L), + init_points = 4, n_iter = 10, acq = "ucb", kappa = 2.576, eps = 0, + optkernel = list(type = "exponential", power = 2), classes = NULL, + seed = 0) elapsed = 0.01 Round = 1 eta_opt = 0.2703 max_depth_opt = 5.0000 nrounds_opt = 153.4572 subsample_opt = 0.8565 bytree_opt = 0.5312 Value = -0.8253 elapsed = 0.01 Round = 2 eta_opt = 0.7823 max_depth_opt = 5.0000 nrounds_opt = 95.4909 subsample_opt = 0.3862 bytree_opt = 0.7101 Value = -0.1033 elapsed = 0.01 Round = 3 eta_opt = 0.7520 max_depth_opt = 5.0000 nrounds_opt = 123.1516 subsample_opt = 0.8046 bytree_opt = 0.5614 Value = -0.0852 elapsed = 0.01 Round = 4 eta_opt = 0.9494 max_depth_opt = 4.0000 nrounds_opt = 79.9325 subsample_opt = 0.3408 bytree_opt = 0.5087 Value = -0.2351 elapsed = 0.01 Round = 5 eta_opt = 0.5938 max_depth_opt = 5.0000 nrounds_opt = 104.2419 subsample_opt = 0.1563 bytree_opt = 0.9367 Value = -0.1526 elapsed = 0.01 Round = 6 eta_opt = 0.6991 max_depth_opt = 4.0000 nrounds_opt = 99.4728 subsample_opt = 0.7752 bytree_opt = 0.9837 Value = -0.0516 elapsed = 0.01 Round = 7 eta_opt = 0.7259 max_depth_opt = 4.0000 nrounds_opt = 157.5705 subsample_opt = 0.9099 bytree_opt = 0.4197 Value = -0.2175 elapsed = 0.01 Round = 8 eta_opt = 1.0000 max_depth_opt = 4.0000 nrounds_opt = 160.0000 subsample_opt = 1.0000 bytree_opt = 0.9479 Value = -0.0791 elapsed = 0.01 Round = 9 eta_opt = 0.8652 max_depth_opt = 4.0000 nrounds_opt = 128.5974 subsample_opt = 0.1000 bytree_opt = 1.0000 Value = -0.1177 elapsed = 0.01 Round = 10 eta_opt = 0.1000 max_depth_opt = 4.0000 nrounds_opt = 70.0000 subsample_opt = 1.0000 bytree_opt = 1.0000 Value = -2.7314 elapsed = 0.01 Round = 11 eta_opt = 1.0000 max_depth_opt = 4.0000 nrounds_opt = 124.4014 subsample_opt = 1.0000 bytree_opt = 0.9440 Value = -0.0508 elapsed = 0.01 Round = 12 eta_opt = 0.6357 max_depth_opt = 5.0000 nrounds_opt = 70.0000 subsample_opt = 1.0000 bytree_opt = 0.4000 Value = -0.1727 elapsed = 0.01 Round = 13 eta_opt = 1.0000 max_depth_opt = 6.0000 nrounds_opt = 138.0422 subsample_opt = 0.1000 bytree_opt = 0.9535 Value = -0.0985 elapsed = 0.01 Round = 14 eta_opt = 0.7131 max_depth_opt = 4.0000 nrounds_opt = 105.8117 subsample_opt = 1.0000 bytree_opt = 0.6526 Value = -0.1199 Best Parameters Found: Round = 11 eta_opt = 1.0000 max_depth_opt = 4.0000 nrounds_opt = 124.4014 subsample_opt = 1.0000 bytree_opt = 0.9440 Value = -0.0508 $Best_Par eta_opt max_depth_opt nrounds_opt subsample_opt bytree_opt 1.0000000 4.0000000 124.4014440 1.0000000 0.9440231 $Best_Value [1] -0.050821 $History Round eta_opt max_depth_opt nrounds_opt subsample_opt bytree_opt Value 1: 1 0.2702743 5 153.45719 0.8564563 0.5311872 -0.8253185 2: 2 0.7822927 5 95.49093 0.3861673 0.7100781 -0.1032525 3: 3 0.7520490 5 123.15158 0.8045662 0.5613704 -0.0851570 4: 4 0.9493523 4 79.93245 0.3407574 0.5087010 -0.2351015 5: 5 0.5938150 5 104.24190 0.1562759 0.9367329 -0.1526330 6: 6 0.6990630 4 99.47276 0.7751549 0.9836891 -0.0515565 7: 7 0.7259076 4 157.57050 0.9098945 0.4197278 -0.2175365 8: 8 1.0000000 4 160.00000 1.0000000 0.9479365 -0.0790800 9: 9 0.8652452 4 128.59735 0.1000000 1.0000000 -0.1176970 10: 10 0.1000000 4 70.00000 1.0000000 1.0000000 -2.7313515 11: 11 1.0000000 4 124.40144 1.0000000 0.9440231 -0.0508210 12: 12 0.6356773 5 70.00000 1.0000000 0.4000000 -0.1727275 13: 13 1.0000000 6 138.04222 0.1000000 0.9535310 -0.0985300 14: 14 0.7130662 4 105.81170 1.0000000 0.6526395 -0.1198510 $Pred V1 V2 V3 V4 V5 V6 V7 V8 V9 V10 V11 V12 1: 1.794260 3.997718 3.872365 4.787029 2.999421 3.817092 3.923461 5.298461 4.692506 0.9798461 5.298461 3.363726 2: 1.601689 3.997718 3.872365 4.787029 2.999421 3.817092 3.923461 4.594231 4.692506 0.9094231 4.594231 3.363726 3: 1.601689 3.997718 3.872365 4.787029 2.999421 3.265959 3.387272 4.594231 4.692506 0.9094231 4.594231 3.363726 4: 1.601689 3.997718 3.872365 4.787029 2.999421 3.265959 3.387272 4.594231 4.692506 0.9094231 4.594231 3.363726 5: 1.794260 3.997718 3.872365 4.787029 2.999421 3.817092 3.923461 5.298461 4.692506 0.9798461 5.298461 3.363726 --- 146: 2.090428 4.892015 4.817782 6.000310 3.703391 4.633369 4.723159 6.407742 4.692506 1.0907743 6.407742 4.142464 147: 2.032701 4.811997 4.760699 5.808878 3.754106 4.518176 4.613933 6.580435 4.735147 1.1080434 6.580435 3.558663 148: 2.090428 4.892015 4.817782 6.000310 3.703391 4.633369 4.723159 6.407742 4.692506 1.0907743 6.407742 4.142464 149: 2.090428 4.892015 4.817782 6.000310 3.703391 4.633369 4.723159 6.407742 4.692506 1.0907743 6.407742 4.142464 150: 2.090428 4.892015 4.817782 6.000310 3.703391 4.633369 4.723159 6.407742 4.692506 1.0907743 6.407742 4.142464 V13 V14 1: 5.446154 3.921621 2: 5.446154 3.419458 3: 5.446154 3.419458 4: 5.446154 3.419458 5: 5.446154 3.921621 --- 146: 5.446154 4.712611 147: 5.379070 4.835752 148: 5.446154 4.712611 149: 5.446154 4.712611 150: 5.446154 4.712611 Warning messages: 1: In matrix(c(sample(index), rep(NA, NA_how_many)), ncol = nfolds) : data length [15] is not a sub-multiple or multiple of the number of rows [8] 2: In matrix(c(sample(index), rep(NA, NA_how_many)), ncol = nfolds) : data length [43] is not a sub-multiple or multiple of the number of rows [22] 3: In matrix(c(sample(index), rep(NA, NA_how_many)), ncol = nfolds) : data length [109] is not a sub-multiple or multiple of the number of rows [55] 4: In matrix(c(sample(index), rep(NA, NA_how_many)), ncol = nfolds) : data length [107] is not a sub-multiple or multiple of the number of rows [54] 5: In matrix(c(sample(index), rep(NA, NA_how_many)), ncol = nfolds) : data length [133] is not a sub-multiple or multiple of the number of rows [67]
I discuss the error in a reply to one of the issues here:
https://github.com/ymattu/MlBayesOpt/issues/55
I still get a warning which is something to do with the following line:
Running the new
xgb_cv_optfunction with the following data should work:Output: