Man pages for SchlossLab/mikropml
User-Friendly R Package for Supervised Machine Learning Pipelines
| abort_packages_not_installed | Throw error if required packages are not installed. |
| bootstrap_performance | Calculate a bootstrap confidence interval for the performance... |
| bounds | Get the lower and upper bounds for an empirical confidence... |
| calc_balanced_precision | Calculate balanced precision given actual and baseline... |
| calc_baseline_precision | Calculate the fraction of positives, i.e. baseline precision... |
| calc_mean_perf | Generic function to calculate mean performance curves for... |
| calc_perf_bootstrap_split | Calculate performance for a single split from... |
| calc_perf_metrics | Get performance metrics for test data |
| calc_pvalue | Calculate the p-value for a permutation test |
| change_to_num | Change columns to numeric if possible |
| check_all | Check all params that don't return a value |
| check_cat_feats | Check if any features are categorical |
| check_corr_thresh | check that corr_thresh is either NULL or a number between 0... |
| check_dataset | Check that the dataset is not empty and has more than 1... |
| check_features | Check features |
| check_group_partitions | Check the validity of the group_partitions list |
| check_groups | Check grouping vector |
| check_kfold | Check that kfold is an integer of reasonable size |
| check_method | Check if the method is supported. If not, throws error. |
| check_ntree | Check ntree |
| check_outcome_column | Check that outcome column exists. Pick outcome column if not... |
| check_outcome_value | Check that the outcome variable is valid. Pick outcome value... |
| check_packages_installed | Check whether package(s) are installed |
| check_perf_metric_function | Check perf_metric_function is NULL or a function |
| check_perf_metric_name | Check perf_metric_name is NULL or a function |
| check_permute | Check that permute is a logical |
| check_remove_var | Check remove_var |
| check_seed | check that the seed is either NA or a number |
| check_training_frac | Check that the training fraction is between 0 and 1 |
| check_training_indices | Check the validity of the training indices |
| cluster_corr_mat | Cluster a matrix of correlated features |
| collapse_correlated_features | Collapse correlated features |
| combine_hp_performance | Combine hyperparameter performance metrics for multiple... |
| compare_models | Perform permutation tests to compare the performance metric... |
| create_grouped_data_partition | Split into train and test set while splitting by groups. When... |
| create_grouped_k_multifolds | Splitting into folds for cross-validation when using groups |
| define_cv | Define cross-validation scheme and training parameters |
| find_permuted_perf_metric | Get permuted performance metric difference for a single... |
| flatten_corr_mat | Flatten correlation matrix to pairs |
| get_binary_corr_mat | Identify correlated features as a binary matrix |
| get_caret_dummyvars_df | Get dummyvars dataframe (i.e. design matrix) |
| get_caret_processed_df | Get preprocessed dataframe for continuous variables |
| get_corr_feats | Identify correlated features |
| get_difference | Calculate the difference in the mean of the metric for two... |
| get_feature_importance | Get feature importance using the permutation method |
| get_groups_from_clusters | Assign features to groups |
| get_hp_performance | Get hyperparameter performance metrics |
| get_hyperparams_from_df | Split hyperparameters dataframe into named lists for each... |
| get_hyperparams_list | Set hyperparameters based on ML method and dataset... |
| get_outcome_type | Get outcome type. |
| get_partition_indices | Select indices to partition the data into training & testing... |
| get_perf_metric_fn | Get default performance metric function |
| get_perf_metric_name | Get default performance metric name |
| get_performance_tbl | Get model performance metrics as a one-row tibble |
| get_seeds_trainControl | Get seeds for 'caret::trainControl()' |
| get_tuning_grid | Generate the tuning grid for tuning hyperparameters |
| group_correlated_features | Group correlated features |
| is_whole_number | Check whether a numeric vector contains whole numbers. |
| keep_groups_in_cv_partitions | Whether groups can be kept together in partitions during... |
| mikropml-package | mikropml: User-Friendly R Package for Robust Machine Learning... |
| mutate_all_types | Mutate all columns with 'utils::type.convert()'.' |
| otu_data_preproc | Mini OTU abundance dataset - preprocessed |
| otu_mini_bin | Mini OTU abundance dataset |
| otu_mini_bin_results_glmnet | Results from running the pipeline with L2 logistic regression... |
| otu_mini_bin_results_rf | Results from running the pipeline with random forest on... |
| otu_mini_bin_results_rpart2 | Results from running the pipeline with rpart2 on... |
| otu_mini_bin_results_svmRadial | Results from running the pipeline with svmRadial on... |
| otu_mini_bin_results_xgbTree | Results from running the pipeline with xbgTree on... |
| otu_mini_cont_results_glmnet | Results from running the pipeline with glmnet on... |
| otu_mini_cont_results_nocv | Results from running the pipeline with glmnet on... |
| otu_mini_cv | Cross validation on 'train_data_mini' with grouped features. |
| otu_mini_multi | Mini OTU abundance dataset with 3 categorical variables |
| otu_mini_multi_group | Groups for otu_mini_multi |
| otu_mini_multi_results_glmnet | Results from running the pipeline with glmnet on... |
| otu_small | Small OTU abundance dataset |
| pbtick | Update progress if the progress bar is not 'NULL'. |
| permute_p_value | Calculated a permuted p-value comparing two models |
| plot_curves | Plot ROC and PRC curves |
| plot_hp_performance | Plot hyperparameter performance metrics |
| plot_model_performance | Plot performance metrics for multiple ML runs with different... |
| preprocess_data | Preprocess data prior to running machine learning |
| process_cat_feats | Process categorical features |
| process_cont_feats | Preprocess continuous features |
| process_novar_feats | Process features with no variation |
| radix_sort | Call 'sort()' with 'method = 'radix" |
| randomize_feature_order | Randomize feature order to eliminate any position-dependent... |
| reexports | caret contr.ltfr |
| remove_singleton_columns | Remove columns appearing in only 'threshold' row(s) or fewer. |
| replace_spaces | Replace spaces in all elements of a character vector with... |
| rm_missing_outcome | Remove missing outcome values |
| run_ml | Run the machine learning pipeline |
| select_apply | Use future apply if available |
| sensspec | Calculate and summarize performance for ROC and PRC plots |
| set_hparams_glmnet | Set hyperparameters for regression models for use with glmnet |
| set_hparams_rf | Set hyparameters for random forest models |
| set_hparams_rpart2 | Set hyperparameters for decision tree models |
| set_hparams_svmRadial | Set hyperparameters for SVM with radial kernel |
| set_hparams_xgbTree | Set hyperparameters for SVM with radial kernel |
| shared_ggprotos | Get plot layers shared by 'plot_mean_roc' and 'plot_mean_prc' |
| shuffle_group | Shuffle the rows in a column |
| split_outcome_features | Split dataset into outcome and features |
| tidy_perf_data | Tidy the performance dataframe |
| train_model | Train model using 'caret::train()'. |
