Package: tune 1.2.1.9000

Max Kuhn

tune: Tidy Tuning Tools

The ability to tune models is important. 'tune' contains functions and classes to be used in conjunction with other 'tidymodels' packages for finding reasonable values of hyper-parameters in models, pre-processing methods, and post-processing steps.

Authors:Max Kuhn [aut, cre], Posit Software, PBC [cph, fnd]

tune_1.2.1.9000.tar.gz
tune_1.2.1.9000.zip(r-4.5)tune_1.2.1.9000.zip(r-4.4)tune_1.2.1.9000.zip(r-4.3)
tune_1.2.1.9000.tgz(r-4.4-any)tune_1.2.1.9000.tgz(r-4.3-any)
tune_1.2.1.9000.tar.gz(r-4.5-noble)tune_1.2.1.9000.tar.gz(r-4.4-noble)
tune_1.2.1.9000.tgz(r-4.4-emscripten)tune_1.2.1.9000.tgz(r-4.3-emscripten)
tune.pdf |tune.html
tune/json (API)
NEWS

# Install 'tune' in R:
install.packages('tune', repos = c('https://tidymodels.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Bug tracker:https://github.com/tidymodels/tune/issues

Datasets:

On CRAN:

111 exports 274 stars 7.23 score 84 dependencies 34 dependents 8 mentions 724 scripts 28.0k downloads

Last updated 2 days agofrom:5737af77bc. Checks:OK: 7. Indexed: yes.

TargetResultDate
Doc / VignettesOKSep 18 2024
R-4.5-winOKSep 18 2024
R-4.5-linuxOKSep 18 2024
R-4.4-winOKSep 18 2024
R-4.4-macOKSep 18 2024
R-4.3-winOKSep 18 2024
R-4.3-macOKSep 18 2024

Exports:.catch_and_log.catch_and_log_fit.config_key_from_metrics.estimate_metrics.filter_perf_metrics.get_extra_col_names.get_fingerprint.get_tune_eval_time_target.get_tune_eval_times.get_tune_metric_names.get_tune_metrics.get_tune_outcome_names.get_tune_parameter_names.get_tune_parameters.get_tune_workflow.load_namespace.stash_last_result.use_case_weights_with_yardstickaugmentautoplotcheck_eval_time_argcheck_initialcheck_metric_in_tune_resultscheck_metricscheck_metrics_argcheck_parameterscheck_rsetcheck_timecheck_workflowchoose_eval_timechoose_metriccollect_extractscollect_metricscollect_notescollect_predictionscompute_metricsconf_boundconf_mat_resampledcontrol_bayescontrol_gridcontrol_last_fitcontrol_resamplescoord_obs_predempty_ellipsesencode_setestimate_tune_resultsexp_improveexpo_decayextract_fit_engineextract_fit_parsnipextract_modelextract_moldextract_parameter_set_dialsextract_preprocessorextract_recipeextract_spec_parsnipextract_workflowfilter_parametersfinalize_modelfinalize_recipefinalize_workflowfinalize_workflow_preprocessorfirst_eval_timefirst_metricfit_bestfit_max_valuefit_resamplesforge_from_workflowget_metric_timeget_tune_colorsinitialize_catalogint_pctlis_preprocessoris_recipeis_workflowlast_fitload_pkgsmaybe_choose_eval_timemessage_wrapmetrics_infomin_gridmin_grid.boost_treemin_grid.C5_rulesmin_grid.cubist_rulesmin_grid.linear_regmin_grid.logistic_regmin_grid.marsmin_grid.multinom_regmin_grid.nearest_neighbormin_grid.plsmin_grid.poisson_regmin_grid.rule_fitnew_backend_optionsnew_iteration_resultsoutcome_namesparametersprob_improvepull_rset_attributesrequired_pkgsselect_bestselect_by_one_std_errselect_by_pct_lossshow_bestshow_notestunabletunetune_argstune_bayestune_gridval_class_and_singleval_class_or_null

Dependencies:classcliclockcodetoolscolorspacecpp11data.tablediagramdialsDiceDesigndigestdoFuturedplyrfansifarverforeachfurrrfuturefuture.applygenericsggplot2globalsgluegowerGPfitgtablehardhatipredisobanditeratorsKernSmoothlabelinglatticelavalhslifecyclelistenvlubridatemagrittrMASSMatrixmgcvmodelenvmunsellnlmennetnumDerivparallellyparsnippillarpkgconfigprettyunitsprodlimprogressrpurrrR6RColorBrewerRcpprecipesrlangrpartrsamplescalessfdshapeslidersparsevctrsSQUAREMstringistringrsurvivaltibbletidyrtidyselecttimechangetimeDatetzdbutf8vctrsviridisLitewarpwithrworkflowsyardstick

Readme and manuals

Help Manual

Help pageTopics
Save most recent results to search path.stash_last_result
Determine if case weights should be passed on to yardstick.use_case_weights_with_yardstick .use_case_weights_with_yardstick.hardhat_frequency_weights .use_case_weights_with_yardstick.hardhat_importance_weights
Augment data with holdout predictionsaugment.last_fit augment.resample_results augment.tune_results
Plot tuning search resultsautoplot.tune_results
Obtain and format results produced by tuning functionscollect_extracts collect_extracts.tune_results collect_metrics collect_metrics.tune_results collect_notes collect_notes.tune_results collect_predictions collect_predictions.default collect_predictions.tune_results
Calculate and format metrics from tuning functionscompute_metrics compute_metrics.default compute_metrics.tune_results
Compute average confusion matrix across resamplesconf_mat_resampled
Control aspects of the Bayesian search processcontrol_bayes
Control aspects of the last fit processcontrol_last_fit
Use same scale for plots of observed vs predicted valuescoord_obs_pred
Example Analysis of Ames Housing Dataames_grid_search ames_iter_search ames_wflow example_ames_knn
Exponential decay functionexpo_decay
Convenience functions to extract modelextract_model
Extract elements of 'tune' objectsextract-tune extract_fit_engine.tune_results extract_fit_parsnip.tune_results extract_mold.tune_results extract_preprocessor.tune_results extract_recipe.tune_results extract_spec_parsnip.tune_results extract_workflow.last_fit extract_workflow.tune_results
Remove some tuning parameter resultsfilter_parameters
Splice final parameters into objectsfinalize_model finalize_recipe finalize_workflow
Fit a model to the numerically optimal configurationfit_best fit_best.default fit_best.tune_results
Fit multiple models via resamplingfit_resamples fit_resamples.model_spec fit_resamples.workflow
Bootstrap confidence intervals for performance metricsint_pctl.tune_results
Fit the final best model to the training set and evaluate the test setlast_fit last_fit.model_spec last_fit.workflow
Write a message that respects the line widthmessage_wrap
Support for parallel processing in tuneparallelism
Acquisition function for scoring parameter combinationsconf_bound exp_improve prob_improve
Investigate best tuning parametersselect_best select_best.default select_best.tune_results select_by_one_std_err select_by_one_std_err.default select_by_one_std_err.tune_results select_by_pct_loss select_by_pct_loss.default select_by_pct_loss.tune_results show_best show_best.default show_best.tune_results
Display distinct errors from tune objectsshow_notes
Bayesian optimization of model parameters.tune_bayes tune_bayes.model_spec tune_bayes.workflow
Model tuning via grid searchtune_grid tune_grid.model_spec tune_grid.workflow