Bootstrap-class: Class "Bootstrap"

In performanceEstimation: An Infra-Structure for Performance Estimation of Predictive Models

Description

This class of objects contains the information describing a bootstrap experiment, i.e. its settings.

Objects from the Class

Objects can be created by calls of the form Bootstrap(...) providing the values for the class slots. The objects contain information on the type of boostrap, the number of repetitions, the random number generator seed and optionally the concrete data splits to use on each iteration of the boostrap experiment. Note that most of the times you will not supply these data splits as the boostrap routines in this infra-structure will take care of building them. Still, this allows you to replicate some experiment carried out with specific train/test splits.

Slots

type:

Object of class character indicating the type of boostrap estimates to use: "e0" (default) or ".632".

nReps:

Object of class numeric indicating the number of repetitions of the bootstrap experiment (defaulting to 200).

seed:

Object of class numeric with the random number generator seed (defaulting to 1234).

dataSplits:

Object of class list containing the data splits to use on each bootstrap repetition. Each element should be a list with two components: test and train, on this order. Each of these is a vector with the row ids to use as test and train sets of each repetition of the bootstrap experiment.

Extends

Class EstCommon, directly. Class EstimationMethod, directly.

Methods

show

signature(object = "Bootstrap"): method used to show the contents of a Bootstrap object.

Author(s)

Luis Torgo [e-mail]

References

Torgo, L. (2014) An Infra-Structure for Performance Estimation and Experimental Comparison of Predictive Models in R. arXiv:1412.0436 [cs.MS] http://arxiv.org/abs/1412.0436

See Also

MonteCarlo, LOOCV, CV, Holdout, EstimationMethod, EstimationTask

Examples

showClass("Bootstrap")

s <- Bootstrap(type=".632",nReps=400)
s

## Small example illustrating the format of user supplied data splits
s2 <- Bootstrap(dataSplits=list(list(test=sample(1:150,50),train=sample(1:150,50)),
                                list(test=sample(1:150,50),train=sample(1:150,50)),
                                list(test=sample(1:150,50),train=sample(1:150,50))
                               ))
s2
s2@dataSplits

Example output

Class "Bootstrap" [package "performanceEstimation"]

Slots:
                                                  
Name:        type      nReps       seed dataSplits
Class:  character    numeric    numeric    OptList

Extends: "EstCommon", "EstimationMethod"
400  repetitions of  .632  Bootstrap experiment
	 Run with seed =  1234 
3  repetitions of  e0  Bootstrap experiment
	 User-supplied data splits
[[1]]
[[1]]$test
 [1] 110 116  35  41  16  46  72 120  11  21  59  34 146  90  40  71   4 113 107
[20]  38  51 135   3 119 101 144  49 140  42  19  85  52 147  78  70  33  81  28
[39] 126  69   6  74 102  63 133  93  45  57  65  95

[[1]]$train
 [1]  11  22 141  68 148  36  92  50  12 112 127  67  27  73  91 138  49 140  59
[20]  37   4  70 111  65  33 133 101  24 130  30  18 106 117 131 113  20  93  85
[39] 121 149  64  35  94  28  40 109  82  39  76  47


[[2]]
[[2]]$test
 [1]   9  91  48  60   7  50 119 109   1  70  89 108  31  96  98 135  32  57  23
[20]  74  87  30  64  29 114  18 110 125 146 142  49  58 122  26  16  71  45  34
[39] 139 107  10  53  73   4 102  42  28  85  17  19

[[2]]$train
 [1]  38 147   9 142  69 149 130  70  35   7  33 143 135  73  67 125  10  31 104
[20] 103  51   4  79  45   3 144  34  15 105  93  71  65  21  47 117  28   8  42
[39]  24  23  40  36  27   5   2  13  30  59 114 120


[[3]]
[[3]]$test
 [1]  93 144  71  96  29  21  74  17  95 124  46  42 149 142  52 109 131  68  25
[20]  30  32  59   3 139  27 130  77  50  67 103 115   5  82  98  15  87 102   7
[39] 129  53  12 114 120 150  10  28 107  37 125 104

[[3]]$train
 [1]  17 136  27 140  18  80  54  16  31  19  73  25  66 135  29  61 105 143 120
[20]  10  60  14  90  77  37  13 134  34  53   7  36  44  97  41  23 115 146  15
[39]  35  43  74 125  98 138  39  83   8  33  99  12

performanceEstimation documentation built on May 2, 2019, 6:01 a.m.