print.PRROC: printing PRROC objects

In PRROC: Precision-Recall and ROC Curves for Weighted and Unweighted Data

Description

Prints a PRROC object.

Usage

## S3 method for class 'PRROC'
print(x, ...)

Arguments

x	a PRROC object obtained from pr.curve or roc.curve
...	see print

Details

The print method for PRROC objects prints the area under the (PR or ROC) curve, and (if curve=TRUE in pr.curve or roc.curve) the range of classification scores. If also max.compute=TRUE, min.compute=TRUE, and/or rand.compute=TRUE when the PRROC object has been computes using pr.curve or roc.curve, a relative area under curve is reported, i.e., the minimal AUC subtracted from the original AUC and the result divided by the difference of maximum and minimum AUC.

Author(s)

Jan Grau and Jens Keilwagen

See Also

pr.curve

roc.curve

Examples

# create artificial scores as random numbers
x <- rnorm( 1000 );
y <- rnorm( 1000, -1 );
# compute area under PR curve
pr <- pr.curve( x, y );
print( pr );

# compute area under ROC curve
roc <- roc.curve( x, y );
print( roc );

Example output

  Precision-recall curve

    Area under curve (Integral):
     0.7473201 

    Area under curve (Davis & Goadrich):
     0.7473196 

    Curve not computed ( can be done by using curve=TRUE )

  ROC curve

    Area under curve:
     0.760709 

    Curve not computed ( can be done by using curve=TRUE )

PRROC documentation built on May 1, 2019, 9:19 p.m.