One-vs-Rest multiclass reduction (Geron Ch 3, morie.fn grovr)

K classifiers, each class against the rest, argmax of the scores.

Usage

morie_geron_one_vs_rest(X, y, base_fit = NULL, eta = 0.5, n_iter = 400)

Arguments

X

(m, n) design.

y

Integer class labels.

base_fit

Optional function(X, y_binary) returning a scorer.

eta, n_iter

Passed to morie_geron_train_logreg().

Value

List with predictions, scores, classes, n_classifiers, accuracy, coefficients.

Examples

X <- matrix(c(1, 2, 1, 3, 1, 5, 1, 7), 4, byrow = TRUE)
y <- c(2, 3, 6, 9)
th <- c(0.5, 1.1)
morie_geron_elastic_net_cost(X, y, th, 0.4, 0.6)
#> $cost
#> [1] 0.8033
#> 
#> $mse
#> [1] 0.4425
#> 
#> $l1_penalty
#> [1] 0.264
#> 
#> $l2_penalty
#> [1] 0.0968
#> 
#> $l1_norm
#> [1] 1.1
#> 
#> $l2_norm_sq
#> [1] 1.21
#> 
#> $alpha
#> [1] 0.4
#> 
#> $r
#> [1] 0.6
#> 
#> $estimate
#> [1] 0.8033
#> 
#> $n
#> [1] 4
#> 
morie_geron_one_vs_rest(X = X, y = y)
#> $predictions
#> [1] 2 3 6 9
#> 
#> $scores
#>            [,1]       [,2]         [,3]      [,4]
#> [1,]   1.621273 -0.1024271 -1.367815803 -7.463978
#> [2,]  -1.979327 -0.6752868 -0.914809972 -5.554783
#> [3,]  -9.180526 -1.8210063 -0.008798311 -1.736393
#> [4,] -16.381725 -2.9667257  0.897213350  2.081997
#> 
#> $classes
#> [1] 2 3 6 9
#> 
#> $n_classifiers
#> [1] 4
#> 
#> $accuracy
#> [1] 1
#> 
#> $coefficients
#> $coefficients[[1]]
#> [1]  4.411236  4.411236 -3.600599
#> 
#> $coefficients[[2]]
#> [1]  0.5216462  0.5216462 -0.5728597
#> 
#> $coefficients[[3]]
#> [1] -1.1369137 -1.1369137  0.4530058
#> 
#> $coefficients[[4]]
#> [1] -5.641184 -5.641184  1.909195
#> 
#> 
#> $estimate
#> [1] 2 3 6 9
#> 
#> $n
#> [1] 4
#>