FittedGridSearchCV is an object containing fitted predictive models across
a tuning grid of hyper-parameters returned by GridSearchCV$fit() as well as
relevant model information such as the best performing model, best
hyper-parameters, etc.
best_idxAn integer specifying the index of $models that
contains the best-performing model.
best_metricThe average performance metric of the best model across cross-validation folds.
best_modelThe best performing predictive model.
best_paramsA named list of the hyper-parameters that result in the optimal predictive model.
foldsA list of length $models where each element contains a
list of the cross-validation indices for each fold.
tune_paramsA data.frame of the full hyper-parameter grid.
modelsList of predictive models at every value of $tune_params.
metricsNumeric list; Cross-validation performance metrics for
every model in $models.
predictionsA list containing the cross-validation fold
predictions for each model in $models.
new()Create a new FittedGridSearchCV object.
FittedGridSearchCV$new(
tune_params,
models,
folds,
metrics,
predictions,
optimize_score
)tune_paramsData.frame of the full hyper-parameter grid.
modelsList of predictive models at every value of $tune_params.
foldsList of cross-validation indices at every value of
$tune_params.
metricsList of cross-validation performance metrics for
every model in $models.
predictionsA list containing the predicted values on the
cross-validation folds for every model in $models.
optimize_scoreEither "max" or "min" indicating whether or not the specified performance metric was maximized or minimized to find the optimal predictive model.
An object of class FittedGridSearchCV.
clone()The objects of this class are cloneable with this method.
FittedGridSearchCV$clone(deep = FALSE)deepWhether to make a deep clone.