Choose the bests models, according to the score data frame

Choose the bests models, according to the score data frame

choose_best_models(models, engine, score, number)

Arguments

models

A list of models trained by `train_models()` function.

engine

A vector of tree-based models that shall be tested. Possible values are: `ranger`, `xgboost`, `decision_tree`, `lightgbm`, `catboost`.

score

A data frame with metrics values for given models, by `score_models`.

number

The number of models to return.

Value

The list of chosen best models.

Examples

data(iris)
iris_bin          <- iris[1:100, ]
iris_bin$Species  <- factor(iris_bin$Species)
type              <- guess_type(iris_bin, 'Species')
preprocessed_data <- preprocessing(iris_bin, 'Species', type)
#> Error in if (advanced) {    del_cor <- delete_correlated_values(pre_data, y, verbose = verbose)    pre_data <- del_cor$data    pre_data <- delete_id_columns(pre_data)    pre_data <- boruta_selection(pre_data, y)}: argument is not interpretable as logical
preprocessed_data <- preprocessed_data$data
#> Error in eval(expr, envir, enclos): object 'preprocessed_data' not found
split_data <-
  train_test_balance(preprocessed_data,
                     'Species',
                     balance = FALSE)
#> Error in train_test_balance(preprocessed_data, "Species", balance = FALSE): object 'preprocessed_data' not found
train_data <-
  prepare_data(split_data$train,
               'Species',
               engine = c('ranger', 'xgboost', 'decision_tree', 'lightgbm', 'catboost'))
#> Error in as.data.frame(unclass(data), stringsAsFactors = TRUE): object 'split_data' not found
test_data <-
  prepare_data(split_data$test,
               'Species',
               engine = c('ranger', 'xgboost', 'decision_tree', 'lightgbm', 'catboost'),
               predict = TRUE,
               train = split_data$train)
#> Error in as.data.frame(unclass(data), stringsAsFactors = TRUE): object 'split_data' not found

model <-
  train_models(train_data,
               'Species',
               engine = c('ranger', 'xgboost', 'decision_tree', 'lightgbm', 'catboost'),
               type = type)
#> Error in ranger::ranger(dependent.variable.name = y, data = data$ranger_data,     classification = TRUE, probability = TRUE): object 'train_data' not found
predictions <-
  predict_models(model,
                 test_data,
                 'Species',
                 engine = c('ranger', 'xgboost', 'decision_tree', 'lightgbm', 'catboost'),
                 type = type)
#> Error in predict(models[[i]], data$ranger_data): object 'model' not found
score <-
  score_models(model,
               predictions,
               observed = split_data$test$Species,
               type = type)
#> Error in matrix(nrow = length(models), ncol = length(metrics_binary_clf) +     nr_add_col): object 'model' not found
best_models <-
  choose_best_models(model,
                     score = score,
                     number = 3)
#> Error in choose_best_models(model, score = score, number = 3): object 'model' not found