MachineShop (version 3.8.0)

performance: Model Performance Metrics

Description

Compute measures of model performance.

Usage

performance(x, ...)
# S3 method for BinomialVariate
performance(
  x,
  y,
  weights = NULL,
  metrics = MachineShop::settings("metrics.numeric"),
  na.rm = TRUE,
  ...
)
# S3 method for factor
performance(
  x,
  y,
  weights = NULL,
  metrics = MachineShop::settings("metrics.factor"),
  cutoff = MachineShop::settings("cutoff"),
  na.rm = TRUE,
  ...
)
# S3 method for matrix
performance(
  x,
  y,
  weights = NULL,
  metrics = MachineShop::settings("metrics.matrix"),
  na.rm = TRUE,
  ...
)
# S3 method for numeric
performance(
  x,
  y,
  weights = NULL,
  metrics = MachineShop::settings("metrics.numeric"),
  na.rm = TRUE,
  ...
)
# S3 method for Surv
performance(
  x,
  y,
  weights = NULL,
  metrics = MachineShop::settings("metrics.Surv"),
  cutoff = MachineShop::settings("cutoff"),
  na.rm = TRUE,
  ...
)
# S3 method for ConfusionList
performance(x, ...)
# S3 method for ConfusionMatrix
performance(x, metrics = MachineShop::settings("metrics.ConfusionMatrix"), ...)
# S3 method for MLModel
performance(x, ...)
# S3 method for Resample
performance(x, ...)
# S3 method for TrainingStep
performance(x, ...)

Arguments

x

observed responses; or confusion, trained model fit, resample, or rfe result.

...

arguments passed from the Resample method to the response type-specific methods or from the method for ConfusionList to ConfusionMatrix. Elliptical arguments in the response type-specific methods are passed to metrics supplied as a single MLMetric function and are ignored otherwise.

y

predicted responses if not contained in x.

weights

numeric vector of non-negative case weights for the observed x responses [default: equal weights].

metrics

metric function, function name, or vector of these with which to calculate performance.

na.rm

logical indicating whether to remove observed or predicted responses that are NA when calculating metrics.

cutoff

numeric (0, 1) threshold above which binary factor probabilities are classified as events and below which survival probabilities are classified.

See Also

plot, summary

Examples

# \donttest{
## Requires prior installation of suggested package gbm to run

res <- resample(Species ~ ., data = iris, model = GBMModel)
(perf <- performance(res))
summary(perf)
plot(perf)

## Survival response example
library(survival)

gbm_fit <- fit(Surv(time, status) ~ ., data = veteran, model = GBMModel)

obs <- response(gbm_fit, newdata = veteran)
pred <- predict(gbm_fit, newdata = veteran)
performance(obs, pred)
# }