In ModelOriented/forester: Quick and Simple Tools for Training and Testing of Tree-Based Models

Setup

knitr::opts_chunk$set(echo = TRUE)
library(forester)

Data preparation

data(lisbon)

lisbon_prep  <- custom_preprocessing(data = lisbon,
                                     y = 'Price',
                                     na_indicators = c(''),
                                     removal_parameters = list(
                                       active_modules = c(duplicate_cols = TRUE, id_like_cols    = TRUE,
                                                          static_cols    = TRUE, sparse_cols     = TRUE,
                                                          corrupt_rows   = TRUE, correlated_cols = TRUE),
                                       id_names = c('id', 'nr', 'number', 'idx', 'identification', 'index'),
                                       static_threshold           = 0.99,
                                       sparse_columns_threshold   = 0.3,
                                       sparse_rows_threshold      = 0.3,
                                       high_correlation_threshold = 0.7
                                     ),
                                     imputation_parameters = list(
                                       imputation_method = 'median-other',
                                       k = 10,
                                       m = 5
                                     ),
                                     feature_selection_parameters = list(
                                       feature_selection_method = 'none',
                                       max_features = 'default',
                                       nperm = 1,
                                       cutoffPermutations = 20,
                                       threadsNumber = NULL,
                                       method = 'estevez'
                                     ),
                                     verbose = TRUE)

Training

train_out <- train(data        = lisbon,
      y                          = 'Price', 
      time                       = NULL,
      status                     = NULL,
      type                       = "auto",
      engine                     = c("ranger", "xgboost", "decision_tree", "lightgbm", "catboost"),
      verbose                    = TRUE,
      train_test_split           = c(0.6, 0.2, 0.2),
      split_seed                 = NULL,
      bayes_iter                 = 0,
      random_evals               = 2,
      metrics                    = "auto",
      sort_by                    = "auto",
      metric_function            = NULL,
      metric_function_name       = NULL,
      metric_function_decreasing = TRUE,
      best_model_number          = 5,
      custom_preprocessing       = NULL
)

train_out_1 <- train(data        = lisbon_prep$data,
      y                          = 'Price', 
      time                       = NULL,
      status                     = NULL,
      type                       = "auto",
      engine                     = c("ranger", "xgboost", "decision_tree", "lightgbm", "catboost"),
      verbose                    = TRUE,
      train_test_split           = c(0.6, 0.2, 0.2),
      split_seed                 = NULL,
      bayes_iter                 = 0,
      random_evals               = 2,
      metrics                    = "auto",
      sort_by                    = "auto",
      metric_function            = NULL,
      metric_function_name       = NULL,
      metric_function_decreasing = TRUE,
      best_model_number          = 5,
      custom_preprocessing       = lisbon_prep
)

train_out_2 <- train(data        = lisbon_prep$data,
      y                          = 'Price', 
      time                       = NULL,
      status                     = NULL,
      type                       = "auto",
      engine                     = c("ranger", "xgboost", "decision_tree", "lightgbm", "catboost"),
      verbose                    = TRUE,
      train_test_split           = c(0.6, 0.2, 0.2),
      split_seed                 = NULL,
      bayes_iter                 = 4,
      random_evals               = 0,
      metrics                    = "auto",
      sort_by                    = "auto",
      metric_function            = NULL,
      metric_function_name       = NULL,
      metric_function_decreasing = TRUE,
      best_model_number          = 5,
      custom_preprocessing       = lisbon_prep
)

Report

report(train_output = train_out_1, 
       output_file  = 'regression_test_1',
       output_dir   = getwd(),
       check_data   = TRUE)

report(train_output = train_out_2, 
       output_file  = 'regression_test_2',
       output_dir   = getwd(),
       check_data   = TRUE)

ModelOriented/forester documentation built on June 6, 2024, 7:29 a.m.