mlr3measures (version 0.5.0)

logloss: Log Loss

Description

Measure to compare true observed labels with predicted probabilities in multiclass classification tasks.

Usage

logloss(truth, prob, sample_weights = NULL, eps = 1e-15, ...)

Value

Performance value as numeric(1).

Arguments

truth

(factor())
True (observed) labels. Must have the same levels and length as response.

prob

(matrix())
Matrix of predicted probabilities, each column is a vector of probabilities for a specific class label. Columns must be named with levels of truth.

sample_weights

(numeric())
Vector of non-negative and finite sample weights. Must have the same length as truth. The vector gets automatically normalized to sum to one. Defaults to equal sample weights.

eps

(numeric(1))
Probabilities are clipped to max(eps, min(1 - eps, p)). Otherwise the measure would be undefined for probabilities p = 0 and p = 1.

...

(any)
Additional arguments. Currently ignored.

Meta Information

• Type: "classif"

• Range: \([0, \infty)\)

• Minimize: TRUE

• Required prediction: prob

Details

The Log Loss is defined as $$ -\frac{1}{n} \sum_{i=1}^n w_i \log \left( p_i \right ) $$ where \(p_i\) is the probability for the true class of observation \(i\).

See Also

Other Classification Measures: acc(), bacc(), ce(), mauc_aunu(), mbrier(), zero_one()

Examples

set.seed(1)
lvls = c("a", "b", "c")
truth = factor(sample(lvls, 10, replace = TRUE), levels = lvls)
prob = matrix(runif(3 * 10), ncol = 3, dimnames = list(NULL, lvls))
prob = t(apply(prob, 1, function(x) x / sum(x)))
logloss(truth, prob)