zero_one: Zero-One Classification Loss (per observation)

In mlr3measures: Performance Measures for 'mlr3'

Zero-One Classification Loss (per observation)

Description

Calculates the per-observation 0/1 (zero-one) loss as

\mathbf{1} (t_i \neq r_1).

The 1/0 (one-zero) loss is equal to 1 - zero-one and calculated as

\mathbf{1} (t_i = r_i).

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

Note that this is an unaggregated measure, returning the losses per observation.

Usage

zero_one(truth, response, ...)

one_zero(truth, response, ...)

Arguments

truth	(factor()) True (observed) labels. Must have the same levels and length as response.
response	(factor()) Predicted response labels. Must have the same levels and length as truth.
...	(any) Additional arguments. Currently ignored.

Value

Performance value as numeric(length(truth)).

Meta Information

• Type: "classif"

• Range (per observation): [0, 1]

• Minimize (per observation): TRUE

• Required prediction: response

See Also

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

mlr3measures documentation built on Sept. 12, 2024, 7:20 a.m.