Skip to main content
Help us improve PyPI by participating in user testing. All experience levels needed!

Creates the Precision-Recall-Gain curve and calculates the area under the curve

Project description

What are the Precision-Recall-Gain curves?

Please see http://www.cs.bris.ac.uk/~flach/PRGcurves/.

Contents

This package provides the following 6 functions:

precision_gain(TP,FN,FP,TN)
recall_gain(TP,FN,FP,TN)
create_prg_curve(labels,pos_scores)
calc_auprg(prg_curve)
prg_convex_hull(prg_curve)
plot_prg(prg_curve)

Installation

This package can be installed using pip from command line:

pip install pyprg

Usage

Detailed information about the usage can be seen in the manual pages of the individual functions, e.g. by typing ?prg.create_prg_curve after importing with from pyprg import prg. The example usage is as follows:

from pyprg import prg
import numpy as np
labels = np.array([1,1,1,0,1,1,1,1,1,1,0,1,1,1,0,1,0,0,1,0,0,0,1,0,1], dtype='int')
scores = np.arange(1,26)[::-1]
prg_curve = prg.create_prg_curve(labels, scores, create_crossing_points=True)
auprg = prg.calc_auprg(prg_curve)
print(auprg)
prg.plot_prg(prg_curve)

Authors

This package has been written by Meelis Kull, Telmo de Menezes e Silva Filho, Miquel Perello Nieto, based on work by Peter Flach and Meelis Kull, see http://www.cs.bris.ac.uk/~flach/PRGcurves/.

Project details


Release history Release notifications

History Node

0.1.1b7

History Node

0.1.1b6

History Node

0.1.1b5

History Node

0.1.1b4

History Node

0.1.1b3

History Node

0.1.1b2

History Node

0.1.1b1

This version
History Node

0.1

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging CloudAMQP CloudAMQP RabbitMQ AWS AWS Cloud computing Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page