Matthews correlation coefficient

Matthews correlation coefficient

Usage

mcc(data, ...)

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

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

Arguments

data

Either a data.frame containing the columns specified by the truth and estimate arguments, or a table/matrix where the true class results should be in the columns of the table.

...

Not currently used.

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.

estimate

The column identifier for the predicted class results (that is also factor). As with truth this can be specified different ways but the primary method is to use an unquoted variable name. For _vec() functions, a factor vector.

na_rm

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

case_weights

The optional column identifier for case weights. This should be an unquoted column name that evaluates to a numeric column in data. For _vec() functions, a numeric vector, hardhat::importance_weights(), or hardhat::frequency_weights().

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 mcc_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 when computing binary classification metrics. In yardstick, the default is to use the first level. To alter this, change the argument event_level to "second" to consider the last level of the factor the level of interest. 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

mcc() has a known multiclass generalization and that is computed automatically if a factor with more than 2 levels is provided. Because of this, no averaging methods are provided.

References

Giuseppe, J. (2012). "A Comparison of MCC and CEN Error Measures in Multi-Class Prediction". PLOS ONE. Vol 7, Iss 8, e41882.

See also

Other class metrics: accuracy(), bal_accuracy(), detection_prevalence(), f_meas(), j_index(), kap(), npv(), ppv(), precision(), recall(), sens(), spec()

Author

Max Kuhn

Examples

library(dplyr)
data("two_class_example")
data("hpc_cv")

# Two class
mcc(two_class_example, truth, predicted)
#> # A tibble: 1 × 3
#>   .metric .estimator .estimate
#>   <chr>   <chr>          <dbl>
#> 1 mcc     binary         0.677

# Multiclass
# mcc() has a natural multiclass extension
hpc_cv %>%
  filter(Resample == "Fold01") %>%
  mcc(obs, pred)
#> # A tibble: 1 × 3
#>   .metric .estimator .estimate
#>   <chr>   <chr>          <dbl>
#> 1 mcc     multiclass     0.542

# Groups are respected
hpc_cv %>%
  group_by(Resample) %>%
  mcc(obs, pred)
#> # A tibble: 10 × 4
#>    Resample .metric .estimator .estimate
#>    <chr>    <chr>   <chr>          <dbl>
#>  1 Fold01   mcc     multiclass     0.542
#>  2 Fold02   mcc     multiclass     0.521
#>  3 Fold03   mcc     multiclass     0.602
#>  4 Fold04   mcc     multiclass     0.519
#>  5 Fold05   mcc     multiclass     0.520
#>  6 Fold06   mcc     multiclass     0.494
#>  7 Fold07   mcc     multiclass     0.461
#>  8 Fold08   mcc     multiclass     0.538
#>  9 Fold09   mcc     multiclass     0.459
#> 10 Fold10   mcc     multiclass     0.498