R yardstick pr_auc 查準率曲線下麵積

pr_auc(data, ...)

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

pr_auc_vec(
  truth,
  estimate,
  estimator = NULL,
  na_rm = TRUE,
  event_level = yardstick_event_level(),
  case_weights = NULL,
  ...
)

pr_curve() 用於計算全精度召回曲線。

其他類概率指標：average_precision() , brier_class() , classification_cost() , gain_capture() , mn_log_loss() , roc_auc() , roc_aunp() , roc_aunu()

# ---------------------------------------------------------------------------
# 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_auc(two_class_example, truth, Class1)
#> # A tibble: 1 × 3
#>   .metric .estimator .estimate
#>   <chr>   <chr>          <dbl>
#> 1 pr_auc  binary         0.946

# ---------------------------------------------------------------------------
# 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") %>%
  pr_auc(obs, VF:L)
#> # A tibble: 1 × 3
#>   .metric .estimator .estimate
#>   <chr>   <chr>          <dbl>
#> 1 pr_auc  macro          0.611

# 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")) %>%
  pr_auc(obs, M, VF:L)
#> # A tibble: 1 × 3
#>   .metric .estimator .estimate
#>   <chr>   <chr>          <dbl>
#> 1 pr_auc  macro          0.611

# Groups are respected
hpc_cv %>%
  group_by(Resample) %>%
  pr_auc(obs, VF:L)
#> # A tibble: 10 × 4
#>    Resample .metric .estimator .estimate
#>    <chr>    <chr>   <chr>          <dbl>
#>  1 Fold01   pr_auc  macro          0.611
#>  2 Fold02   pr_auc  macro          0.620
#>  3 Fold03   pr_auc  macro          0.689
#>  4 Fold04   pr_auc  macro          0.680
#>  5 Fold05   pr_auc  macro          0.620
#>  6 Fold06   pr_auc  macro          0.650
#>  7 Fold07   pr_auc  macro          0.607
#>  8 Fold08   pr_auc  macro          0.650
#>  9 Fold09   pr_auc  macro          0.628
#> 10 Fold10   pr_auc  macro          0.603

# Weighted macro averaging
hpc_cv %>%
  group_by(Resample) %>%
  pr_auc(obs, VF:L, estimator = "macro_weighted")
#> # A tibble: 10 × 4
#>    Resample .metric .estimator     .estimate
#>    <chr>    <chr>   <chr>              <dbl>
#>  1 Fold01   pr_auc  macro_weighted     0.746
#>  2 Fold02   pr_auc  macro_weighted     0.743
#>  3 Fold03   pr_auc  macro_weighted     0.789
#>  4 Fold04   pr_auc  macro_weighted     0.754
#>  5 Fold05   pr_auc  macro_weighted     0.737
#>  6 Fold06   pr_auc  macro_weighted     0.743
#>  7 Fold07   pr_auc  macro_weighted     0.748
#>  8 Fold08   pr_auc  macro_weighted     0.756
#>  9 Fold09   pr_auc  macro_weighted     0.711
#> 10 Fold10   pr_auc  macro_weighted     0.737

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

pr_auc_vec(
   truth = fold1$obs,
   matrix(
     c(fold1$VF, fold1$F, fold1$M, fold1$L),
     ncol = 4
   )
)
#> [1] 0.6109931