package prc

  1. Overview
  2. Docs
Utilities for precision-recall curves

Install 

dune-project
 Dependency

github.com Readme Edit opam file Versions (2)

Authors

  1. P
    Philippe Veber

Maintainers

  1. P
    philippe.veber@gmail.com

Sources

prc-0.1.0.tbz
sha256=898322ef7f722e37f332362a24c1ad5f1bf8f8bb396cdb549fb44d59fc4f769a
sha512=c85fc65530195913b20c7b0e1763938f3d45187ca5510a37514f5dec5b4b903a9e40b7621ce8509cf023f1ccb1045fc09b362d716b2e6340cbd5960919a65efc

doc/prc/Prc/index.html

Module PrcSource

Precision-Recall curve construction and AUC computation

References: 1 The binormal assumption on precision-recall curves. Kay H. Brodersen, Cheng Soon Ong, Klaas E. Stephan and Joachim M. Buhmann

2 Area Under the Precision-Recall Curve: Point Estimates and Confidence Intervals. Kendrick Boyd, Kevin H. Eng and C. David Page

3 Precision-Recall-Gain Curves: PR Analysis Done Right. Peter A. Flach and Meelis Kull

4 The Relationship Between Precision-Recall and ROC Curves. Jesse Davis and Mark Goadrich

5 Realisable Classifiers: Improving Operating Performance on Variable Cost Problems. M.J.J. Scott, M. Niranjan, R.W. Prager

Sourcetype dataset =
  1. | Dataset of (float * bool) list
    (*

    Binary prediction scores with associated labels

    *)
Sourceval n_pos : dataset -> int

Number of positive items in the dataset

Sourceval operating_points : dataset -> (float * float * float) list

operating_points d computes the list of score threshold, recall and precision triplets, sorted by decreasing threshold.

Sourceval auc_trapezoidal_lt : dataset -> float

AUC lower triangular estimator (see 2 for reference)

Sourceval auc_average_precision : dataset -> float

AUC average precision (see 2 for reference)

Sourceval logit_confidence_interval : alpha:float -> theta_hat:float -> n_pos:int -> float * float

logit_confidence_interval ~alpha ~theta_hat ~n computes an asymptotically valid confidence interval at level 1 - alpha, when the estimate theta_hat was obtained from a sample with n_pos positive observations.

Sourceval bootstrap_confidence_interval : ?niter:int -> alpha:float -> Gsl.Rng.t -> dataset -> f:(dataset -> float) -> float * float

bootstrap_confidence_interval ?niter ~alpha rng d ~f computes a bootstrap confidence interval at level 1 - alpha for the values produces by f, using n_iter bootstrap iterations.

Sourcemodule Binormal_model : sig ... end

Binormal model