Package index • probably

Thresholds

threshold_perf(): Generate performance metrics across probability thresholds

Create class predictions

append_class_pred(): Add a class_pred column

make_class_pred() make_two_class_pred(): Create a class_pred vector from class probabilities

Class predictions

class_pred(): Create a class prediction object

as_class_pred(): Coerce to a class_pred object

is_class_pred(): Test if an object inherits from class_pred

reportable_rate(): Calculate the reportable rate

is_equivocal() which_equivocal() any_equivocal(): Locate equivocal values

levels(<class_pred>): Extract class_pred levels

Regression predictions

int_conformal_cv(): Prediction intervals via conformal inference CV+

int_conformal_full(): Prediction intervals via conformal inference

int_conformal_quantile(): Prediction intervals via conformal inference and quantile regression

int_conformal_split(): Prediction intervals via split conformal inference

control_conformal_full(): Controlling the numeric details for conformal inference

predict(<int_conformal_cv>) predict(<int_conformal_full>) predict(<int_conformal_quantile>) predict(<int_conformal_split>): Prediction intervals from conformal methods

bound_prediction(): Truncate a numeric prediction column

Data

segment_naive_bayes segment_logistic: Image segmentation predictions

species_probs: Predictions on animal species

boosting_predictions boosting_predictions_oob boosting_predictions_test: Boosted regression trees predictions

Calibration

cal_estimate_beta(): Uses a Beta calibration model to calculate new probabilities

cal_estimate_isotonic(): Uses an Isotonic regression model to calibrate model predictions.

cal_estimate_isotonic_boot(): Uses a bootstrapped Isotonic regression model to calibrate probabilities

cal_estimate_linear(): Uses a linear regression model to calibrate numeric predictions

cal_estimate_logistic(): Uses a logistic regression model to calibrate probabilities

cal_estimate_multinomial(): Uses a Multinomial calibration model to calculate new probabilities

cal_estimate_none(): Do not calibrate model predictions.

cal_apply(): Applies a calibration to a set of existing predictions

Calibration Validation

cal_validate_beta(): Measure performance with and without using Beta calibration

cal_validate_isotonic(): Measure performance with and without using isotonic regression calibration

cal_validate_isotonic_boot(): Measure performance with and without using bagged isotonic regression calibration

cal_validate_linear(): Measure performance with and without using linear regression calibration

cal_validate_logistic(): Measure performance with and without using logistic calibration

cal_validate_multinomial(): Measure performance with and without using multinomial calibration

cal_validate_none(): Measure performance without using calibration

collect_metrics(<cal_rset>): Obtain and format metrics produced by calibration validation

collect_predictions(<cal_rset>): Obtain and format predictions produced by calibration validation

Calibration Plots

cal_plot_breaks(): Probability calibration plots via binning

cal_plot_logistic(): Probability calibration plots via logistic regression

cal_plot_regression(): Regression calibration plots

cal_plot_windowed(): Probability calibration plots via moving windows