yardstick (version 0.0.4)

gain_capture: Gain capture

Description

gain_capture() is a measure of performance similar to an AUC calculation, but applied to a gain curve.

Usage

gain_capture(data, ...)

# S3 method for data.frame gain_capture(data, truth, ..., estimator = NULL, na_rm = TRUE)

gain_capture_vec(truth, estimate, estimator = NULL, 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. If truth is binary, only 1 column should be selected. Otherwise, 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.

estimator

One of "binary", "macro", or "macro_weighted" to specify the type of averaging to be done. "binary" is only relevant for the two class case. The other two are general methods for calculating multiclass metrics. The default will automatically choose "binary" or "macro" based on truth.

na_rm

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

estimate

If truth is binary, a numeric vector of class probabilities corresponding to the "relevant" class. Otherwise, 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 gain_capture_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. In yardstick, the default is to use the first level. To change this, a global option called yardstick.event_first is set to TRUE when the package is loaded. This can be changed to FALSE if the last level of the factor is considered the level of interest by running: options(yardstick.event_first = FALSE). 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

Macro and macro-weighted averaging is available for this metric. The default is to select macro averaging if a truth factor with more than 2 levels is provided. Otherwise, a standard binary calculation is done. See vignette("multiclass", "yardstick") for more information.

Details

gain_capture() calculates the area under the gain curve, but above the baseline, and then divides that by the area under a perfect gain curve, but above the baseline. It is meant to represent the amount of potential gain "captured" by the model.

The gain_capture() metric is identical to the accuracy ratio (AR), which is also sometimes called the gini coefficient. These two are generally calculated on a cumulative accuracy profile curve, but this is the same as a gain curve. See the Engelmann reference for more information.

References

Engelmann, Bernd & Hayden, Evelyn & Tasche, Dirk (2003). "Measuring the Discriminative Power of Rating Systems," Discussion Paper Series 2: Banking and Financial Studies 2003,01, Deutsche Bundesbank.

See Also

gain_curve() to compute the full gain curve.

Other class probability metrics: average_precision, mn_log_loss, pr_auc, roc_auc

Examples

Run this code
# NOT RUN {
# ---------------------------------------------------------------------------
# Two class example

# `truth` is a 2 level factor. The first level is `"Class1"`, which is the
# "event of interest" by default in yardstick. See the Relevant Level
# section above.
data(two_class_example)

# Binary metrics using class probabilities take a factor `truth` column,
# and a single class probability column containing the probabilities of
# the event of interest. Here, since `"Class1"` is the first level of
# `"truth"`, it is the event of interest and we pass in probabilities for it.
gain_capture(two_class_example, truth, Class1)

# ---------------------------------------------------------------------------
# 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") %>%
  gain_capture(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")) %>%
  gain_capture(obs, M, VF:L)

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

# Weighted macro averaging
hpc_cv %>%
  group_by(Resample) %>%
  gain_capture(obs, VF:L, estimator = "macro_weighted")

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

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

# ---------------------------------------------------------------------------
# Visualize gain_capture()

# Visually, this represents the area under the black curve, but above the
# 45 degree line, divided by the area of the shaded triangle.
library(ggplot2)
autoplot(gain_curve(two_class_example, truth, Class1))

# }

Run the code above in your browser using DataCamp Workspace