R yardstick pr_curve 精確率召回曲線

pr_curve(data, ...)

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

使用 pr_auc() 計算精確召回曲線下的麵積。

其他曲線指標：gain_curve()、lift_curve()、roc_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.
pr_curve(two_class_example, truth, Class1)
#> # A tibble: 501 × 3
#>    .threshold  recall precision
#>         <dbl>   <dbl>     <dbl>
#>  1     Inf    0               1
#>  2       1.00 0.00388         1
#>  3       1.00 0.00775         1
#>  4       1.00 0.0116          1
#>  5       1.00 0.0155          1
#>  6       1.00 0.0194          1
#>  7       1.00 0.0233          1
#>  8       1.00 0.0271          1
#>  9       1.00 0.0310          1
#> 10       1.00 0.0349          1
#> # ℹ 491 more rows

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

# Visualize the curve using ggplot2 manually
library(ggplot2)
library(dplyr)
pr_curve(two_class_example, truth, Class1) %>%
  ggplot(aes(x = recall, y = precision)) +
  geom_path() +
  coord_equal() +
  theme_bw()


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


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


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