R yardstick roc_curve 接收者算子曲線

roc_curve(data, ...)

# S3 method for data.frame
roc_curve(
  data,
  truth,
  ...,
  na_rm = TRUE,
  event_level = yardstick_event_level(),
  case_weights = NULL,
  options = list()
)

使用 roc_auc() 計算 ROC 曲線下的麵積。

其他曲線指標：gain_curve()、lift_curve()、pr_curve()

# ---------------------------------------------------------------------------
# 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.
roc_curve(two_class_example, truth, Class1)
#> # A tibble: 502 × 3
#>    .threshold specificity sensitivity
#>         <dbl>       <dbl>       <dbl>
#>  1 -Inf           0                 1
#>  2    1.79e-7     0                 1
#>  3    4.50e-6     0.00413           1
#>  4    5.81e-6     0.00826           1
#>  5    5.92e-6     0.0124            1
#>  6    1.22e-5     0.0165            1
#>  7    1.40e-5     0.0207            1
#>  8    1.43e-5     0.0248            1
#>  9    2.38e-5     0.0289            1
#> 10    3.30e-5     0.0331            1
#> # ℹ 492 more rows

# ---------------------------------------------------------------------------
# `autoplot()`

# Visualize the curve using ggplot2 manually
library(ggplot2)
library(dplyr)
roc_curve(two_class_example, truth, Class1) %>%
  ggplot(aes(x = 1 - specificity, y = sensitivity)) +
  geom_path() +
  geom_abline(lty = 3) +
  coord_equal() +
  theme_bw()


# Or use autoplot
autoplot(roc_curve(two_class_example, truth, Class1))


if (FALSE) {

# Multiclass one-vs-all approach
# One curve per level
hpc_cv %>%
  filter(Resample == "Fold01") %>%
  roc_curve(obs, VF:L) %>%
  autoplot()

# Same as above, but will all of the resamples
hpc_cv %>%
  group_by(Resample) %>%
  roc_curve(obs, VF:L) %>%
  autoplot()
}