Code Review Fixes

ModelOriented · Feb 20, 2024 · 745a570 · 745a570
1 parent 733527d
commit 745a570
Show file tree

Hide file tree

Showing 6 changed files with 12 additions and 11 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -11,7 +11,7 @@ Authors@R:
 Description: The forester package is an open-source AutoML package implemented in R designed for
     training high-quality tree-based models on tabular data. It fully supports regression, binary
     classification, and multiclass classification tasks, and provides a limited support for
-    teh sruvival analysis task. A single line of code allows the use of unprocessed datasets, informs
+    the survival analysis task. A single line of code allows the use of unprocessed datasets, informs
     about potential issues concerning them, and handles feature engineering automatically.
     Moreover, hyperparameter tuning is performed by Bayesian optimization, which provides
     high-quality outcomes. The results are later served as a ranked list of models. Finally, the

diff --git a/R/custom_preprocessing.R b/R/custom_preprocessing.R
@@ -137,8 +137,8 @@ custom_preprocessing <- function(data,
                                  type = 'auto',
                                  na_indicators = c(''),
                                  removal_parameters = list(
-                                   active_modules = c(duplicate_cols = TRUE, id_like_cols    = TRUE,
-                                                      static_cols    = TRUE, sparse_cols     = TRUE,
+                                   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,

diff --git a/R/plot_classification.R b/R/plot_classification.R
@@ -83,7 +83,7 @@ plot.binary_clf <- function(x,
     test_y         <- data.frame(metric = rownames(test_scores), value = unlist(test_scores))
     test_data      <- x$score_test[1:10, ]
     test_data$name <- factor(test_data$name, levels = unique(test_data$name))
-    test_all       <- cbind(test_data[rep(seq_len(nrow(test_data)), each = 3),],
+    test_all       <- cbind(test_data[rep(seq_len(nrow(test_data)), each = 3), ],
                             data.frame(metric = rownames(test_scores), value = unlist(test_scores)))
     test_all       <- test_all[, c('name', 'engine', 'tuning', 'metric', 'value')]
 
@@ -92,7 +92,7 @@ plot.binary_clf <- function(x,
     valid_y         <- data.frame(metric = rownames(valid_scores), value = unlist(valid_scores))
     valid_data      <- x$score_valid[1:10, ]
     valid_data$name <- factor(valid_data$name, levels = unique(valid_data$name))
-    valid_all       <- cbind(valid_data[rep(seq_len(nrow(valid_data)), each = 3),],
+    valid_all       <- cbind(valid_data[rep(seq_len(nrow(valid_data)), each = 3), ],
                             data.frame(metric = rownames(valid_scores), value = unlist(valid_scores)))
     valid_all       <- valid_all[, c('name', 'engine', 'tuning', 'metric', 'value')]
 
@@ -124,7 +124,7 @@ plot.binary_clf <- function(x,
       return(p)
     }
 
-    plot_test  <- comparison_plot(TRUE , test_all)
+    plot_test  <- comparison_plot(TRUE, test_all)
     plot_valid <- comparison_plot(FALSE, valid_all)
     return(patchwork::wrap_plots(list(plot_test, plot_valid), ncol = 1))
   }

diff --git a/R/plot_multiclass.R b/R/plot_multiclass.R
@@ -83,7 +83,7 @@ plot.multiclass <- function(x,
     test_y         <- data.frame(metric = rownames(test_scores), value = unlist(test_scores))
     test_data      <- x$score_test[1:10, ]
     test_data$name <- factor(test_data$name, levels = unique(test_data$name))
-    test_all       <- cbind(test_data[rep(seq_len(nrow(test_data)), each = 4),],
+    test_all       <- cbind(test_data[rep(seq_len(nrow(test_data)), each = 4), ],
                             data.frame(metric = rownames(test_scores), value = unlist(test_scores)))
     test_all       <- test_all[, c('name', 'engine', 'tuning', 'metric', 'value')]
 
@@ -92,7 +92,7 @@ plot.multiclass <- function(x,
     valid_y         <- data.frame(metric = rownames(valid_scores), value = unlist(valid_scores))
     valid_data      <- x$score_valid[1:10, ]
     valid_data$name <- factor(valid_data$name, levels = unique(valid_data$name))
-    valid_all       <- cbind(valid_data[rep(seq_len(nrow(valid_data)), each = 4),],
+    valid_all       <- cbind(valid_data[rep(seq_len(nrow(valid_data)), each = 4), ],
                              data.frame(metric = rownames(valid_scores), value = unlist(valid_scores)))
     valid_all       <- valid_all[, c('name', 'engine', 'tuning', 'metric', 'value')]
 

diff --git a/R/report.R b/R/report.R
@@ -36,7 +36,7 @@ report <- function(train_output,
                   'guides for installation from GitHub repository README. The',
                   'report() fucntion is unable to work properly wihtout it. \n\n',
                   verbose = TRUE)
-      stop('Package not found: tinytex, to use it please follow guides for installation from GitHub repository README. The report() fucntion is unable to work properly wihtout it. \n\n')
+      stop('Package not found: tinytex, to use it please follow guides for installation from GitHub repository README. The report() function is unable to work properly wihtout it. \n\n')
     })
     if (train_output$type == 'regression') {
       input_file_path <- system.file('rmd', 'report_regression.Rmd', package = 'forester')

diff --git a/misc/old_tests_03_02_2023/testthat/test-predict_models_all.R b/misc/old_tests_03_02_2023/testthat/test-predict_models_all.R
@@ -103,14 +103,15 @@ test_that('test-predict_models_all', {
   )
   test_data <-
     prepare_data(split_data$test,
-                 y       = 'Price',c('ranger', 'xgboost', 'decision_tree','lightgbm', 'catboost'),
+                 y       = 'Price',
+                 engine  = c('ranger', 'xgboost', 'decision_tree', 'lightgbm', 'catboost'),
                  predict = TRUE,
                  train   = split_data$train)
   suppressWarnings(
     model <-
       train_models(train_data,
                    y      = 'Price',
-                   engine = c('ranger', 'xgboost', 'decision_tree','lightgbm', 'catboost'),
+                   engine = c('ranger', 'xgboost', 'decision_tree', 'lightgbm', 'catboost'),
                    type   = type)
   )
   suppressWarnings(