10
folds and 1
repetitions.The performance is measured in three different ways.
algo | model | succ | par10 | mcp |
---|---|---|---|---|
baseline | vbs | 0.927 | 1357.946 | 0.000 |
baseline | singleBest | 0.880 | 2231.047 | 118.358 |
baseline | singleBestByPar | 0.880 | 2231.047 | 118.358 |
baseline | singleBestBySuccesses | 0.880 | 2231.047 | 118.358 |
classif | rpart | 0.890 | 2022.319 | 71.361 |
classif | randomForest | 0.900 | 1845.000 | 55.772 |
classif | ksvm | 0.903 | 1783.047 | 47.730 |
cluster | XMeans | 0.902 | 1839.296 | 77.024 |
regr | lm | 0.902 | 1830.388 | 68.116 |
regr | rpart | 0.889 | 2063.111 | 85.198 |
regr | randomForest | 0.912 | 1646.440 | 45.898 |
The following default feature steps were used for model building:
ALL
Number of presolved instances: 0
The cost for using the feature steps (adapted for presolving) is: 0
or on average: NA
The feature steps correspond to the following 37
/ 37
instance features:
f_1, f_2, f_3, f_4, f_5,
f_6, f_7, f_8, f_9, f_10,
f_11, f_12, f_13, f_14, f_15,
f_16, f_17, f_18, f_19, f_20,
f_21, f_22, f_23, f_24, f_25,
f_26, f_27, f_28, f_29, f_30,
f_31, f_32, f_33, f_34, f_35,
f_36, f_37
29
to 7
, resulting in a PAR10 score of 1561.791
for the reduced model. Analogously, the model that was generated based on 5
of the originally 29
features resulted in a PAR10 score of 1524.254
.
Below, you can find the list of the selected features and solvers:
Selected Features:
f_3, f_9, f_11, f_15, f_36
Selected Solvers:
CCEHC2akms, ILP.2015, LMHS.I, MaxHS, Open.WBO.R,
WPM3.2015.co, maxino.k16