{"Type":"Package","Package":"yardstick","Title":"Tidy Characterizations of Model Performance","Version":"1.3.2","Authors@R":"c(\nperson(\"Max\", \"Kuhn\", , \"max@posit.co\", role = \"aut\"),\nperson(\"Davis\", \"Vaughan\", , \"davis@posit.co\", role = \"aut\"),\nperson(\"Emil\", \"Hvitfeldt\", , \"emil.hvitfeldt@posit.co\", role = c(\"aut\", \"cre\"),\ncomment = c(ORCID = \"0000-0002-0679-1945\")),\nperson(\"Posit Software, PBC\", role = c(\"cph\", \"fnd\"))\n)","Description":"Tidy tools for quantifying how well model fits to a data set\nsuch as confusion matrices, class probability curve summaries, and\nregression metrics (e.g., RMSE).","License":"MIT + file LICENSE","URL":"https://github.com/tidymodels/yardstick,\nhttps://yardstick.tidymodels.org","BugReports":"https://github.com/tidymodels/yardstick/issues","Depends":"R (>= 3.6.0)","Imports":"cli, dplyr (>= 1.1.0), generics (>= 0.1.2), hardhat (>=\n1.3.0), lifecycle (>= 1.0.3), rlang (>= 1.1.4), tibble,\ntidyselect (>= 1.2.0), utils, vctrs (>= 0.5.0), withr","Suggests":"covr, crayon, ggplot2, knitr, probably (>= 1.0.0), rmarkdown,\nsurvival (>= 3.5-0), testthat (>= 3.0.0), tidyr","VignetteBuilder":"knitr","Config/Needs/website":"tidyverse/tidytemplate","Config/testthat/edition":"3","Config/usethis/last-upkeep":"2024-10-24","Encoding":"UTF-8","LazyData":"true","RoxygenNote":"7.3.2","Collate":"'aaa-metrics.R' 'import-standalone-types-check.R' 'aaa-new.R'\n'aaa.R' 'check-metric.R' 'class-accuracy.R'\n'class-bal_accuracy.R' 'class-detection_prevalence.R'\n'class-f_meas.R' 'class-j_index.R' 'class-kap.R' 'class-mcc.R'\n'class-npv.R' 'class-ppv.R' 'class-precision.R'\n'class-recall.R' 'class-sens.R' 'class-spec.R' 'conf_mat.R'\n'data.R' 'deprecated-prob_helpers.R' 'deprecated-template.R'\n'estimator-helpers.R' 'event-level.R' 'fair-aaa.R'\n'fair-demographic_parity.R' 'fair-equal_opportunity.R'\n'fair-equalized_odds.R' 'import-standalone-obj-type.R'\n'import-standalone-survival.R' 'metric-tweak.R' 'misc.R'\n'missings.R' 'num-ccc.R' 'num-huber_loss.R' 'num-iic.R'\n'num-mae.R' 'num-mape.R' 'num-mase.R' 'num-mpe.R' 'num-msd.R'\n'num-poisson_log_loss.R' 'num-pseudo_huber_loss.R' 'num-rmse.R'\n'num-rpd.R' 'num-rpiq.R' 'num-rsq.R' 'num-rsq_trad.R'\n'num-smape.R' 'prob-average_precision.R'\n'prob-binary-thresholds.R' 'prob-brier_class.R'\n'prob-classification_cost.R' 'prob-gain_capture.R'\n'prob-gain_curve.R' 'prob-helpers.R' 'prob-lift_curve.R'\n'prob-mn_log_loss.R' 'prob-pr_auc.R' 'prob-pr_curve.R'\n'prob-roc_auc.R' 'prob-roc_aunp.R' 'prob-roc_aunu.R'\n'prob-roc_curve.R' 'reexports.R' 'surv-brier_survival.R'\n'surv-brier_survival_integrated.R'\n'surv-concordance_survival.R' 'surv-roc_auc_survival.R'\n'surv-roc_curve_survival.R' 'template.R' 'validation.R'\n'yardstick-package.R'","NeedsCompilation":"yes","Packaged":"2025-01-22 22:14:06 UTC; emilhvitfeldt","Author":"Max Kuhn [aut],\nDavis Vaughan [aut],\nEmil Hvitfeldt [aut, cre] (),\nPosit Software, PBC [cph, fnd]","Maintainer":"Emil Hvitfeldt ","Repository":"CRAN","Date/Publication":"2025-01-22 23:10:02 UTC","repoType":"cran","tarballUrl":"ftp://cran.r-project.org/pub/R/src/contrib/yardstick_1.3.2.tar.gz","jsonAuthors":[{"name":"Max Kuhn","email":"max@posit.co","maintainer":false},{"name":"Davis Vaughan","email":"davis@posit.co","maintainer":false},{"name":"Emil Hvitfeldt","email":"emil.hvitfeldt@posit.co","maintainer":true},{"name":"Posit Software, PBC ","email":null,"maintainer":false}],"readme":"\n# yardstick

\n\n\n\n[![Coverage\nStatus](https://img.shields.io/codecov/c/github/tidymodels/yardstick/main.svg)](https://app.codecov.io/github/tidymodels/yardstick?branch=main)\n[![CRAN_Status_Badge](https://www.r-pkg.org/badges/version/yardstick)](https://CRAN.R-project.org/package=yardstick)\n[![Downloads](https://cranlogs.r-pkg.org/badges/yardstick)](https://CRAN.R-project.org/package=yardstick)\n[![R-CMD-check](https://github.com/tidymodels/yardstick/actions/workflows/R-CMD-check.yaml/badge.svg)](https://github.com/tidymodels/yardstick/actions/workflows/R-CMD-check.yaml)\n\n\n## Overview\n\n`yardstick` is a package to estimate how well models are working using\n[tidy data](https://doi.org/10.18637/jss.v059.i10) principles. See the\n[package webpage](https://yardstick.tidymodels.org/) for more\ninformation.\n\n## Installation\n\nTo install the package:\n\n``` r\ninstall.packages(\"yardstick\")\n\n# Development version:\n# install.packages(\"pak\")\npak::pak(\"tidymodels/yardstick\")\n```\n\n## Two class metric\n\nFor example, suppose you create a classification model and predict on a\nnew data set. You might have data that looks like this:\n\n``` r\nlibrary(yardstick)\nlibrary(dplyr)\n\nhead(two_class_example)\n#> truth Class1 Class2 predicted\n#> 1 Class2 0.00359 0.996411 Class2\n#> 2 Class1 0.67862 0.321379 Class1\n#> 3 Class2 0.11089 0.889106 Class2\n#> 4 Class1 0.73516 0.264838 Class1\n#> 5 Class2 0.01624 0.983760 Class2\n#> 6 Class1 0.99928 0.000725 Class1\n```\n\nYou can use a `dplyr`-like syntax to compute common performance\ncharacteristics of the model and get them back in a data frame:\n\n``` r\nmetrics(two_class_example, truth, predicted)\n#> # A tibble: 2 × 3\n#> .metric .estimator .estimate\n#> \n#> 1 accuracy binary 0.838\n#> 2 kap binary 0.675\n\n# or\n\ntwo_class_example %>%\n roc_auc(truth, Class1)\n#> # A tibble: 1 × 3\n#> .metric .estimator .estimate\n#> \n#> 1 roc_auc binary 0.939\n```\n\n## Multiclass metrics\n\nAll classification metrics have at least one multiclass extension, with\nmany of them having multiple ways to calculate multiclass metrics.\n\n``` r\ndata(\"hpc_cv\")\nhpc_cv <- as_tibble(hpc_cv)\nhpc_cv\n#> # A tibble: 3,467 × 7\n#> obs pred VF F M L Resample\n#> \n#> 1 VF VF 0.914 0.0779 0.00848 0.0000199 Fold01 \n#> 2 VF VF 0.938 0.0571 0.00482 0.0000101 Fold01 \n#> 3 VF VF 0.947 0.0495 0.00316 0.00000500 Fold01 \n#> 4 VF VF 0.929 0.0653 0.00579 0.0000156 Fold01 \n#> 5 VF VF 0.942 0.0543 0.00381 0.00000729 Fold01 \n#> 6 VF VF 0.951 0.0462 0.00272 0.00000384 Fold01 \n#> 7 VF VF 0.914 0.0782 0.00767 0.0000354 Fold01 \n#> 8 VF VF 0.918 0.0744 0.00726 0.0000157 Fold01 \n#> 9 VF VF 0.843 0.128 0.0296 0.000192 Fold01 \n#> 10 VF VF 0.920 0.0728 0.00703 0.0000147 Fold01 \n#> # ℹ 3,457 more rows\n```\n\n``` r\n# Macro averaged multiclass precision\nprecision(hpc_cv, obs, pred)\n#> # A tibble: 1 × 3\n#> .metric .estimator .estimate\n#> \n#> 1 precision macro 0.631\n\n# Micro averaged multiclass precision\nprecision(hpc_cv, obs, pred, estimator = \"micro\")\n#> # A tibble: 1 × 3\n#> .metric .estimator .estimate\n#> \n#> 1 precision micro 0.709\n```\n\n## Calculating metrics on resamples\n\nIf you have multiple resamples of a model, you can use a metric on a\ngrouped data frame to calculate the metric across all resamples at once.\n\nThis calculates multiclass ROC AUC using the method described in Hand,\nTill (2001), and does it across all 10 resamples at once.\n\n``` r\nhpc_cv %>%\n group_by(Resample) %>%\n roc_auc(obs, VF:L)\n#> # A tibble: 10 × 4\n#> Resample .metric .estimator .estimate\n#> \n#> 1 Fold01 roc_auc hand_till 0.813\n#> 2 Fold02 roc_auc hand_till 0.817\n#> 3 Fold03 roc_auc hand_till 0.869\n#> 4 Fold04 roc_auc hand_till 0.849\n#> 5 Fold05 roc_auc hand_till 0.811\n#> 6 Fold06 roc_auc hand_till 0.836\n#> 7 Fold07 roc_auc hand_till 0.825\n#> 8 Fold08 roc_auc hand_till 0.846\n#> 9 Fold09 roc_auc hand_till 0.828\n#> 10 Fold10 roc_auc hand_till 0.812\n```\n\n## Autoplot methods for easy visualization\n\nCurve based methods such as `roc_curve()`, `pr_curve()` and\n`gain_curve()` all have `ggplot2::autoplot()` methods that allow for\npowerful and easy visualization.\n\n``` r\nlibrary(ggplot2)\n\nhpc_cv %>%\n group_by(Resample) %>%\n roc_curve(obs, VF:L) %>%\n autoplot()\n```\n\n $\"Faceted$ \n\n## Contributing\n\nThis project is released with a [Contributor Code of\nConduct](https://contributor-covenant.org/version/2/0/CODE_OF_CONDUCT.html).\nBy contributing to this project, you agree to abide by its terms.\n\n- For questions and discussions about tidymodels packages, modeling, and\n machine learning, please [post on RStudio\n Community](https://forum.posit.co/new-topic?category_id=15&tags=tidymodels,question).\n\n- If you think you have encountered a bug, please [submit an\n issue](https://github.com/tidymodels/yardstick/issues).\n\n- Either way, learn how to create and share a\n [reprex](https://reprex.tidyverse.org/articles/articles/learn-reprex.html)\n (a minimal, reproducible example), to clearly communicate about your\n code.\n\n- Check out further details on [contributing guidelines for tidymodels\n packages](https://www.tidymodels.org/contribute/) and [how to get\n help](https://www.tidymodels.org/help/).","jobInfo":{"package":"yardstick","version":"1.3.2","parsingStatus":"success","parserVersion":2,"parsedAt":"2025-01-23T00:29:54+0000"}}

Join us for RADAR: AI Edition

Description

Arguments

Value

Details

Examples

Join us for
RADAR: AI Edition