These functions calculate the npv() (negative predictive value) of a
measurement system compared to a reference result (the "truth" or gold standard).
Highly related functions are spec(), sens(), and ppv().
npv(data, ...)
# S3 method for class 'data.frame'
npv(
data,
truth,
estimate,
prevalence = NULL,
estimator = NULL,
na_rm = TRUE,
case_weights = NULL,
event_level = yardstick_event_level(),
...
)
npv_vec(
truth,
estimate,
prevalence = NULL,
estimator = NULL,
na_rm = TRUE,
case_weights = NULL,
event_level = yardstick_event_level(),
...
)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.
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.
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.
A numeric value for the rate of the "positive" class of the data.
One of: "binary", "macro", "macro_weighted",
or "micro" to specify the type of averaging to be done. "binary" is
only relevant for the two class case. The other three are general methods
for calculating multiclass metrics. The default will automatically choose
"binary" or "macro" based on estimate.
A logical value indicating whether NA
values should be stripped before the computation proceeds.
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().
A single string. Either "first" or "second" to specify
which level of truth to consider as the "event". This argument is only
applicable when estimator = "binary". The default uses an internal helper
that defaults to "first".
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 npv_vec(), a single numeric value (or NA).
The positive predictive value (ppv()) is defined as the percent of
predicted positives that are actually positive while the
negative predictive value (npv()) is defined as the percent of negative
positives that are actually negative.
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.
Macro, micro, and macro-weighted averaging is available for this metric.
The default is to select macro averaging if a truth factor with more
than 2 levels is provided. Otherwise, a standard binary calculation is done.
See vignette("multiclass", "yardstick") for more information.
Suppose a 2x2 table with notation:
| Reference | ||
| Predicted | Positive | Negative |
| Positive | A | B |
| Negative | C | D |
The formulas used here are:
$$Sensitivity = A/(A+C)$$ $$Specificity = D/(B+D)$$ $$Prevalence = (A+C)/(A+B+C+D)$$ $$PPV = (Sensitivity * Prevalence) / ((Sensitivity * Prevalence) + ((1-Specificity) * (1-Prevalence)))$$ $$NPV = (Specificity * (1-Prevalence)) / (((1-Sensitivity) * Prevalence) + ((Specificity) * (1-Prevalence)))$$
See the references for discussions of the statistics.
Altman, D.G., Bland, J.M. (1994) “Diagnostic tests 2: predictive values,” British Medical Journal, vol 309, 102.
# Two class
data("two_class_example")
npv(two_class_example, truth, predicted)
#> # A tibble: 1 × 3
#> .metric .estimator .estimate
#> <chr> <chr> <dbl>
#> 1 npv binary 0.861
# Multiclass
library(dplyr)
data(hpc_cv)
hpc_cv %>%
filter(Resample == "Fold01") %>%
npv(obs, pred)
#> # A tibble: 1 × 3
#> .metric .estimator .estimate
#> <chr> <chr> <dbl>
#> 1 npv macro 0.906
# Groups are respected
hpc_cv %>%
group_by(Resample) %>%
npv(obs, pred)
#> # A tibble: 10 × 4
#> Resample .metric .estimator .estimate
#> <chr> <chr> <chr> <dbl>
#> 1 Fold01 npv macro 0.906
#> 2 Fold02 npv macro 0.901
#> 3 Fold03 npv macro 0.917
#> 4 Fold04 npv macro 0.897
#> 5 Fold05 npv macro 0.897
#> 6 Fold06 npv macro 0.892
#> 7 Fold07 npv macro 0.882
#> 8 Fold08 npv macro 0.902
#> 9 Fold09 npv macro 0.879
#> 10 Fold10 npv macro 0.890
# Weighted macro averaging
hpc_cv %>%
group_by(Resample) %>%
npv(obs, pred, estimator = "macro_weighted")
#> # A tibble: 10 × 4
#> Resample .metric .estimator .estimate
#> <chr> <chr> <chr> <dbl>
#> 1 Fold01 npv macro_weighted 0.896
#> 2 Fold02 npv macro_weighted 0.890
#> 3 Fold03 npv macro_weighted 0.905
#> 4 Fold04 npv macro_weighted 0.878
#> 5 Fold05 npv macro_weighted 0.878
#> 6 Fold06 npv macro_weighted 0.871
#> 7 Fold07 npv macro_weighted 0.853
#> 8 Fold08 npv macro_weighted 0.885
#> 9 Fold09 npv macro_weighted 0.845
#> 10 Fold10 npv macro_weighted 0.864
# Vector version
npv_vec(
two_class_example$truth,
two_class_example$predicted
)
#> [1] 0.8609865
# Making Class2 the "relevant" level
npv_vec(
two_class_example$truth,
two_class_example$predicted,
event_level = "second"
)
#> [1] 0.8194946