R yardstick rsq R 平方

rsq(data, ...)

# S3 method for data.frame
rsq(data, truth, estimate, na_rm = TRUE, case_weights = NULL, ...)

rsq_vec(truth, estimate, na_rm = TRUE, case_weights = NULL, ...)

其他数字指标：ccc() , huber_loss_pseudo() , huber_loss() , iic() , mae() , mape() , mase() , mpe() , msd() , poisson_log_loss() , rmse() , rpd() , rpiq() , rsq_trad() , smape()

其他一致性指标：ccc()、rpd()、rpiq()、rsq_trad()

# Supply truth and predictions as bare column names
rsq(solubility_test, solubility, prediction)
#> # A tibble: 1 × 3
#>   .metric .estimator .estimate
#>   <chr>   <chr>          <dbl>
#> 1 rsq     standard       0.879

library(dplyr)

set.seed(1234)
size <- 100
times <- 10

# create 10 resamples
solubility_resampled <- bind_rows(
  replicate(
    n = times,
    expr = sample_n(solubility_test, size, replace = TRUE),
    simplify = FALSE
  ),
  .id = "resample"
)

# Compute the metric by group
metric_results <- solubility_resampled %>%
  group_by(resample) %>%
  rsq(solubility, prediction)

metric_results
#> # A tibble: 10 × 4
#>    resample .metric .estimator .estimate
#>    <chr>    <chr>   <chr>          <dbl>
#>  1 1        rsq     standard       0.874
#>  2 10       rsq     standard       0.879
#>  3 2        rsq     standard       0.891
#>  4 3        rsq     standard       0.916
#>  5 4        rsq     standard       0.892
#>  6 5        rsq     standard       0.858
#>  7 6        rsq     standard       0.873
#>  8 7        rsq     standard       0.852
#>  9 8        rsq     standard       0.915
#> 10 9        rsq     standard       0.884

# Resampled mean estimate
metric_results %>%
  summarise(avg_estimate = mean(.estimate))
#> # A tibble: 1 × 1
#>   avg_estimate
#>          <dbl>
#> 1        0.883
# With uninformitive data, the traditional version of R^2 can return
# negative values.
set.seed(2291)
solubility_test$randomized <- sample(solubility_test$prediction)
rsq(solubility_test, solubility, randomized)
#> # A tibble: 1 × 3
#>   .metric .estimator .estimate
#>   <chr>   <chr>          <dbl>
#> 1 rsq     standard     0.00199
rsq_trad(solubility_test, solubility, randomized)
#> # A tibble: 1 × 3
#>   .metric  .estimator .estimate
#>   <chr>    <chr>          <dbl>
#> 1 rsq_trad standard       -1.01

# A constant `truth` or `estimate` vector results in a warning from
# a divide by zero error in the correlation calculation.
# `NA` will be returned in these cases.
truth <- c(1, 2)
estimate <- c(1, 1)
rsq_vec(truth, estimate)
#> Warning: A correlation computation is required, but `estimate` is constant and has 0 standard deviation, resulting in a divide by 0 error. `NA` will be returned.
#> [1] NA