yardstick (version 0.0.7)

roc_aunp: Area under the ROC curve of each class against the rest, using the a priori class distribution

Description

roc_aunp() is a multiclass metric that computes the area under the ROC curve of each class against the rest, using the a priori class distribution. This is equivalent to roc_auc(estimator = "macro_weighted").

Usage

roc_aunp(data, ...)

# S3 method for data.frame roc_aunp(data, truth, ..., options = list(), na_rm = TRUE)

roc_aunp_vec(truth, estimate, options = list(), na_rm = TRUE, ...)

Arguments

data

A data.frame containing the truth and estimate columns.

...

A set of unquoted column names or one or more dplyr selector functions to choose which variables contain the class probabilities. There should be as many columns as factor levels of truth.

truth

The column identifier for the true class results (that is a factor). This should be an unquoted column name although this argument is passed by expression and supports quasiquotation (you can unquote column names). For _vec() functions, a factor vector.

options

A list of named options to pass to pROC::roc() such as smooth. These options should not include response, predictor, levels, quiet, or direction.

na_rm

A logical value indicating whether NA values should be stripped before the computation proceeds.

estimate

A matrix with as many columns as factor levels of truth. It is assumed that these are in the same order as the levels of truth.

Value

A tibble with columns .metric, .estimator, and .estimate and 1 row of values.

For grouped data frames, the number of rows returned will be the same as the number of groups.

For roc_aunp_vec(), a single numeric value (or NA).

Relevant Level

There is no common convention on which factor level should automatically be considered the "event" or "positive" result when computing binary classification metrics. In yardstick, the default is to use the first level. To alter this, change the argument event_level to "second" to consider the last level of the factor the level of interest. For multiclass extensions involving one-vs-all comparisons (such as macro averaging), this option is ignored and the "one" level is always the relevant result.

Multiclass

This multiclass method for computing the area under the ROC curve uses the a priori class distribution and is equivalent to roc_auc(estimator = "macro_weighted").

References

Ferri, C., Hern<U+00E1>ndez-Orallo, J., & Modroiu, R. (2009). "An experimental comparison of performance measures for classification". Pattern Recognition Letters. 30 (1), pp 27-38.

See Also

roc_aunu() for computing the area under the ROC curve of each class against the rest, using the uniform class distribution.

Other class probability metrics: average_precision(), gain_capture(), mn_log_loss(), pr_auc(), roc_auc(), roc_aunu()

Examples

Run this code
# NOT RUN {
# Multiclass example

# `obs` is a 4 level factor. The first level is `"VF"`, which is the
# "event of interest" by default in yardstick. See the Relevant Level
# section above.
data(hpc_cv)

# You can use the col1:colN tidyselect syntax
library(dplyr)
hpc_cv %>%
  filter(Resample == "Fold01") %>%
  roc_aunp(obs, VF:L)

# Change the first level of `obs` from `"VF"` to `"M"` to alter the
# event of interest. The class probability columns should be supplied
# in the same order as the levels.
hpc_cv %>%
  filter(Resample == "Fold01") %>%
  mutate(obs = relevel(obs, "M")) %>%
  roc_aunp(obs, M, VF:L)

# Groups are respected
hpc_cv %>%
  group_by(Resample) %>%
  roc_aunp(obs, VF:L)

# Vector version
# Supply a matrix of class probabilities
fold1 <- hpc_cv %>%
  filter(Resample == "Fold01")

roc_aunp_vec(
  truth = fold1$obs,
  matrix(
    c(fold1$VF, fold1$F, fold1$M, fold1$L),
    ncol = 4
  )
)

# ---------------------------------------------------------------------------
# Options for `pROC::roc()`

# Pass options via a named list and not through `...`!
roc_aunp(
  hpc_cv,
  obs,
  VF:L,
  options = list(smooth = TRUE)
)

# }

Run the code above in your browser using DataCamp Workspace