Introduction | Gaussian Metrics | Binomial Metrics | Multinomial Metrics | External metrics

Introduction | Attach packages and set seed for reproducibility | Binomial data | Manually creating a two-class confusion matrix | Creating a confusion matrix with evaluate() | Multiclass confusion matrix with confusion_matrix() | Adding sum tiles | Tweaking plot_confusion_matrix()

Introduction | Attach packages | Prepare data | Predicting the score | Creating a model function | Creating a predict function | Cross-validating the functions | Passing hyperparameters | update_hyperparameters() | Specifying hyperparameters for grid search | Cross-validating hyperparameter combinations | Preprocessing within the cross-validation | Binomial example | Multinomial example

Introduction | Averaging | Voting | ID evaluation with evaluate() | Using voting | Per model | In 'gaussian' evaluation | Results for each ID

Introduction | Does it matter? | Multiple-k repeated cross-validation | Creating folds | Performing cross-validation | Inspecting the effect of k | Class level results

Introduction | groupdata2 functions in focus | What is cross-validation? | Why training and test sets? | The data | Creating train/test sets | What is leakage? | Creating folds for cross-validation | Cross-validation | Cross-validation function | Linear regression models | Outro

Installing groupdata2 | CRAN version | GitHub development version | Attach packages | General information | group_factor() | group() | splt() | fold() | partition() | collapse_groups() | balance() | Groups, windows or folds? | Introduction vignettes | Use of kable() | Grouping Methods | Method: 'greedy' | Method: 'n_dist' (Default) | Method: 'n_fill' | Method: 'n_last' | Method: 'n_rand' | Method: 'l_sizes' | Method: 'l_starts' | Skipping | Automatically find group starts | find_starts() | find_missing_starts() | Method: 'every' | Method: 'staircase' | Find remainder - %staircase% | Method: 'primes' | Find remainder - %primes% | Balancing ID Methods | ID method: 'n_ids' | ID method: 'n_rows_c' | ID method: 'distributed' | ID method: 'nested' | Arguments | Grouping arguments | data | n | method | starts_col | force_equal | allow_zero | descending | randomize | col_name | remove_missing_starts | k | p | cat_col | num_col | id_col | id_aggregation_fn | extreme_pairing_levels | num_fold_cols | unique_fold_cols_only | max_iters | handle_existing_fold_cols | parallel | list_out | Balancing arguments | size | id_method | mark_new_rows | new_rows_col_name | Using Functions | Extra arguments showcase | Examples of method differences | n_ methods | Vector with 57 elements divided into 6 groups | Vector with 117 elements divided into 11 groups | Greedy | Vector with 100 elements with sizes of 8, 15, 20 | Staircasing | Vector with 1000 elements with step sizes of 2, 5, 11 | Primes | Vector with 1000 elements with n (start at) as 2, 5, 11 | The End

Windowing time series | Attach packages | Load time series data | Reduce number of datapoints | Staircase groups | Outro

Installation | Main functions | Generator functions | Functions for use in tests | Helper functions | Addins | Using in packages | Examples | gxs_selection | Selection is a vector | Numeric vector | Factor | Long vector (sampling) | Selection is a data frame | Selection is a function call with side effects | gxs_function | RStudio Addins | How to set up a key command in RStudio | initializeGXSFunctionAddin | wrapStringAddin | initializeTestthatAddin | assertCollectionAddin | dputSelectedAddin | navigateTestFileAddin

Introduction | Attach packages | Data | Outro

Introduction | Use cases | Outro