Implement forward feature selection and return data with selected features Uses root mean squared error for regression and accuracy for classification

Implement forward feature selection and return data with selected features Uses root mean squared error for regression and accuracy for classification

ForwardSelection(
  my_mod,
  feature,
  label,
  min_f = 1,
  max_f = NA,
  type = "classification",
  cv = 3
)

Arguments

my_mod	model name in string (must be in caret::modelLookup())
feature	training dataset with features
label	training dataset with labels.
min_f	minimum amount of features to select
max_f	maximum amount of features to select
type	problem type. (Must be 'regression' or 'classification')
cv	number of folds for cross validation

Value

The dataset with selected features.

Examples

y <- iris$Species
x <- iris[c(1,2,3,4)]
ffs <- ForwardSelection(feature=x, label=y, my_mod="rf")
#> Loading required package: lattice
#> Loading required package: ggplot2
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> Warning: invalid mtry: reset to within valid range
#> note: only 1 unique complexity parameters in default grid. Truncating the grid to 1 .
#> 
#> note: only 1 unique complexity parameters in default grid. Truncating the grid to 1 .
#> 
#> note: only 1 unique complexity parameters in default grid. Truncating the grid to 1 .
#> 
print(x[ffs])
#>     Sepal.Width
#> 1           3.5
#> 2           3.0
#> 3           3.2
#> 4           3.1
#> 5           3.6
#> 6           3.9
#> 7           3.4
#> 8           3.4
#> 9           2.9
#> 10          3.1
#> 11          3.7
#> 12          3.4
#> 13          3.0
#> 14          3.0
#> 15          4.0
#> 16          4.4
#> 17          3.9
#> 18          3.5
#> 19          3.8
#> 20          3.8
#> 21          3.4
#> 22          3.7
#> 23          3.6
#> 24          3.3
#> 25          3.4
#> 26          3.0
#> 27          3.4
#> 28          3.5
#> 29          3.4
#> 30          3.2
#> 31          3.1
#> 32          3.4
#> 33          4.1
#> 34          4.2
#> 35          3.1
#> 36          3.2
#> 37          3.5
#> 38          3.6
#> 39          3.0
#> 40          3.4
#> 41          3.5
#> 42          2.3
#> 43          3.2
#> 44          3.5
#> 45          3.8
#> 46          3.0
#> 47          3.8
#> 48          3.2
#> 49          3.7
#> 50          3.3
#> 51          3.2
#> 52          3.2
#> 53          3.1
#> 54          2.3
#> 55          2.8
#> 56          2.8
#> 57          3.3
#> 58          2.4
#> 59          2.9
#> 60          2.7
#> 61          2.0
#> 62          3.0
#> 63          2.2
#> 64          2.9
#> 65          2.9
#> 66          3.1
#> 67          3.0
#> 68          2.7
#> 69          2.2
#> 70          2.5
#> 71          3.2
#> 72          2.8
#> 73          2.5
#> 74          2.8
#> 75          2.9
#> 76          3.0
#> 77          2.8
#> 78          3.0
#> 79          2.9
#> 80          2.6
#> 81          2.4
#> 82          2.4
#> 83          2.7
#> 84          2.7
#> 85          3.0
#> 86          3.4
#> 87          3.1
#> 88          2.3
#> 89          3.0
#> 90          2.5
#> 91          2.6
#> 92          3.0
#> 93          2.6
#> 94          2.3
#> 95          2.7
#> 96          3.0
#> 97          2.9
#> 98          2.9
#> 99          2.5
#> 100         2.8
#> 101         3.3
#> 102         2.7
#> 103         3.0
#> 104         2.9
#> 105         3.0
#> 106         3.0
#> 107         2.5
#> 108         2.9
#> 109         2.5
#> 110         3.6
#> 111         3.2
#> 112         2.7
#> 113         3.0
#> 114         2.5
#> 115         2.8
#> 116         3.2
#> 117         3.0
#> 118         3.8
#> 119         2.6
#> 120         2.2
#> 121         3.2
#> 122         2.8
#> 123         2.8
#> 124         2.7
#> 125         3.3
#> 126         3.2
#> 127         2.8
#> 128         3.0
#> 129         2.8
#> 130         3.0
#> 131         2.8
#> 132         3.8
#> 133         2.8
#> 134         2.8
#> 135         2.6
#> 136         3.0
#> 137         3.4
#> 138         3.1
#> 139         3.0
#> 140         3.1
#> 141         3.1
#> 142         3.1
#> 143         2.7
#> 144         3.2
#> 145         3.3
#> 146         3.0
#> 147         2.5
#> 148         3.0
#> 149         3.4
#> 150         3.0