Package: probably 1.0.3.9001
Max Kuhn
probably: Tools for Post-Processing Predicted Values
Models can be improved by post-processing class probabilities, by: recalibration, conversion to hard probabilities, assessment of equivocal zones, and other activities. 'probably' contains tools for conducting these operations as well as calibration tools and conformal inference techniques for regression models.
Authors:
probably_1.0.3.9001.tar.gz
probably_1.0.3.9001.zip(r-4.5)probably_1.0.3.9001.zip(r-4.4)probably_1.0.3.9001.zip(r-4.3)
probably_1.0.3.9001.tgz(r-4.4-any)probably_1.0.3.9001.tgz(r-4.3-any)
probably_1.0.3.9001.tar.gz(r-4.5-noble)probably_1.0.3.9001.tar.gz(r-4.4-noble)
probably_1.0.3.9001.tgz(r-4.4-emscripten)probably_1.0.3.9001.tgz(r-4.3-emscripten)
probably.pdf |probably.html✨
probably/json (API)
NEWS
| # Install 'probably' in R: |
| install.packages('probably', repos = c('https://tidymodels.r-universe.dev', 'https://cloud.r-project.org')) |
Bug tracker:https://github.com/tidymodels/probably/issues
- boosting_predictions_oob - Boosted regression trees predictions
- boosting_predictions_test - Boosted regression trees predictions
- segment_logistic - Image segmentation predictions
- segment_naive_bayes - Image segmentation predictions
- species_probs - Predictions on animal species
Last updated 1 months agofrom:369cef329e. Checks:OK: 7. Indexed: yes.
| Target | Result | Date |
|---|---|---|
| Doc / Vignettes | OK | Nov 15 2024 |
| R-4.5-win | OK | Nov 15 2024 |
| R-4.5-linux | OK | Nov 15 2024 |
| R-4.4-win | OK | Nov 15 2024 |
| R-4.4-mac | OK | Nov 15 2024 |
| R-4.3-win | OK | Nov 15 2024 |
| R-4.3-mac | OK | Nov 15 2024 |
Exports:.cal_table_breaks.cal_table_logistic.cal_table_windowedany_equivocalappend_class_predas_class_predas.factoras.orderedaugmentbound_predictioncal_applycal_estimate_betacal_estimate_isotoniccal_estimate_isotonic_bootcal_estimate_linearcal_estimate_logisticcal_estimate_multinomialcal_plot_breakscal_plot_logisticcal_plot_regressioncal_plot_windowedcal_validate_betacal_validate_isotoniccal_validate_isotonic_bootcal_validate_linearcal_validate_logisticcal_validate_multinomialclass_predcollect_metricscollect_predictionscontrol_conformal_fullfitint_conformal_cvint_conformal_fullint_conformal_quantileint_conformal_splitis_class_predis_equivocalmake_class_predmake_two_class_predreportable_raterequired_pkgsthreshold_perfwhich_equivocal
Dependencies:butcherclasscliclockcodetoolscolorspacecpp11crayondata.tablediagramdialsDiceDesigndigestdoFuturedplyrfansifarverforeachfurrrfuturefuture.applygenericsggplot2globalsgluegowerGPfitgtablehardhatipredisobanditeratorsKernSmoothlabelinglatticelavalhslifecyclelistenvlobstrlubridatemagrittrMASSMatrixmgcvmodelenvmunsellnlmennetnumDerivparallellyparsnippillarpkgconfigprettyunitsprodlimprogressrpurrrR6RColorBrewerRcpprecipesrlangrpartrsamplescalessfdshapeslidersparsevctrsSQUAREMstringistringrsurvivaltailortibbletidyrtidyselecttimechangetimeDatetunetzdbutf8vctrsviridisLitewarpwithrworkflowsyardstick
Readme and manuals
Help Manual
| Help page | Topics |
|---|---|
| Add a 'class_pred' column | append_class_pred |
| Coerce to a 'class_pred' object | as_class_pred |
| Boosted regression trees predictions | boosting_predictions boosting_predictions_oob boosting_predictions_test |
| Truncate a numeric prediction column | bound_prediction |
| Applies a calibration to a set of existing predictions | cal_apply cal_apply.cal_object cal_apply.data.frame cal_apply.tune_results |
| Uses a Beta calibration model to calculate new probabilities | cal_estimate_beta cal_estimate_beta.data.frame cal_estimate_beta.grouped_df cal_estimate_beta.tune_results |
| Uses an Isotonic regression model to calibrate model predictions. | cal_estimate_isotonic cal_estimate_isotonic.data.frame cal_estimate_isotonic.grouped_df cal_estimate_isotonic.tune_results |
| Uses a bootstrapped Isotonic regression model to calibrate probabilities | cal_estimate_isotonic_boot cal_estimate_isotonic_boot.data.frame cal_estimate_isotonic_boot.grouped_df cal_estimate_isotonic_boot.tune_results |
| Uses a linear regression model to calibrate numeric predictions | cal_estimate_linear cal_estimate_linear.data.frame cal_estimate_linear.grouped_df cal_estimate_linear.tune_results |
| Uses a logistic regression model to calibrate probabilities | cal_estimate_logistic cal_estimate_logistic.data.frame cal_estimate_logistic.grouped_df cal_estimate_logistic.tune_results |
| Uses a Multinomial calibration model to calculate new probabilities | cal_estimate_multinomial cal_estimate_multinomial.data.frame cal_estimate_multinomial.grouped_df cal_estimate_multinomial.tune_results |
| Probability calibration plots via binning | cal_plot_breaks cal_plot_breaks.data.frame cal_plot_breaks.grouped_df cal_plot_breaks.tune_results |
| Probability calibration plots via logistic regression | cal_plot_logistic cal_plot_logistic.data.frame cal_plot_logistic.grouped_df cal_plot_logistic.tune_results |
| Regression calibration plots | cal_plot_regression cal_plot_regression.data.frame cal_plot_regression.grouped_df cal_plot_regression.tune_results |
| Probability calibration plots via moving windows | cal_plot_windowed cal_plot_windowed.data.frame cal_plot_windowed.grouped_df cal_plot_windowed.tune_results |
| Measure performance with and without using Beta calibration | cal_validate_beta cal_validate_beta.resample_results cal_validate_beta.rset cal_validate_beta.tune_results |
| Measure performance with and without using isotonic regression calibration | cal_validate_isotonic cal_validate_isotonic.resample_results cal_validate_isotonic.rset cal_validate_isotonic.tune_results |
| Measure performance with and without using bagged isotonic regression calibration | cal_validate_isotonic_boot cal_validate_isotonic_boot.resample_results cal_validate_isotonic_boot.rset cal_validate_isotonic_boot.tune_results |
| Measure performance with and without using linear regression calibration | cal_validate_linear cal_validate_linear.resample_results cal_validate_linear.rset |
| Measure performance with and without using logistic calibration | cal_validate_logistic cal_validate_logistic.resample_results cal_validate_logistic.rset cal_validate_logistic.tune_results |
| Measure performance with and without using multinomial calibration | cal_validate_multinomial cal_validate_multinomial.resample_results cal_validate_multinomial.rset cal_validate_multinomial.tune_results |
| Create a class prediction object | class_pred |
| Obtain and format metrics produced by calibration validation | collect_metrics.cal_rset |
| Obtain and format predictions produced by calibration validation | collect_predictions.cal_rset |
| Controlling the numeric details for conformal inference | control_conformal_full |
| Prediction intervals via conformal inference CV+ | int_conformal_cv int_conformal_cv.default int_conformal_cv.resample_results int_conformal_cv.tune_results |
| Prediction intervals via conformal inference | int_conformal_full int_conformal_full.default int_conformal_full.workflow |
| Prediction intervals via conformal inference and quantile regression | int_conformal_quantile int_conformal_quantile.workflow |
| Prediction intervals via split conformal inference | int_conformal_split int_conformal_split.default int_conformal_split.workflow |
| Test if an object inherits from 'class_pred' | is_class_pred |
| Extract 'class_pred' levels | levels.class_pred |
| Locate equivocal values | any_equivocal is_equivocal locate-equivocal which_equivocal |
| Create a 'class_pred' vector from class probabilities | make_class_pred make_two_class_pred |
| Prediction intervals from conformal methods | predict.int_conformal_cv predict.int_conformal_full predict.int_conformal_quantile predict.int_conformal_split |
| Calculate the reportable rate | reportable_rate |
| Image segmentation predictions | segment_logistic segment_naive_bayes |
| Predictions on animal species | species_probs |
| Generate performance metrics across probability thresholds | threshold_perf threshold_perf.data.frame |
