ROP-package: Regression Optimized: Numerical Approach for Multivariate...

In ROP: Regression Optimized: Numerical Approach for Multivariate Classification and Regression Trees

Description

Trees Classification and Regression using multivariate nodes calculated by an exhaustive numerical approach. We propose a new concept of decision tree, including multivariate knots and non hierarchical pathway. This package's model uses a multivariate nodes tree that calculates directly a risk score for each observation for the state Y observed. Nguyen JM, Gaultier A, Antonioli D (2015) <doi:10.1016/j.respe.2018.03.088> Castillo JM, Knol AC, Nguyen JM, Khammari A, Saint Jean M, Dreno B (2016) <doi:10.1684/ejd.2016.2826> Vildy S, Nguyen JM, Gaultier A, Khammari A, Dreno B (2017) <doi:10.1684/ejd.2016.2955> Nguyen JM, Gaultier A, Antonioli D (2018) <doi:10.1016/j.respe.2018.03.088>.

Details

The DESCRIPTION file: This package was not yet installed at build time.

Index: This package was not yet installed at build time.

Author(s)

Jean-Michel Nguyen [aut, cre], Daniel Antonioli [aut]

Maintainer: Jean-Michel Nguyen <[e-mail]>

Examples

rop(
  fic = system.file("extdata", "titanic.csv", package = "ROP"),
  output_folder = tempdir(),
  mini = -1,
  maxi = 1,
  nbCycles = 2,
  typesVariables = c(FALSE, FALSE, FALSE)
)

Example output

Loading required package: ROCR
=============================================================================
Factors :  Class Sexe Age 
=============================================================================
Cycle no. 1 
Step no. 1 
Number of observations  :  1046 
Coefficients :  0 1 1 
Threshold= 2     Se= 79.64459 Sp= 75.17564 AUC= 0.7707756 
=============================================================================
Cycle no. 1 
Step no. 2 
Number of observations  :  447 
Coefficients :  1 0 0 
Threshold= 3     Se= 86.50794 Sp= 73.52025 AUC= 0.8135044 
=============================================================================
*****************************************************************************
   ->  Sensitivity =  97.25363 Specificity =  55.26932 
*****************************************************************************
=============================================================================
Cycle no. 2 
Step no. 1 
Number of observations  :  793 
Coefficients :  0 1 1 
Threshold= 2     Se= 81.89369 Sp= 44.50262 AUC= 0.6339644 
=============================================================================
Cycle no. 2 
Step no. 2 
Number of observations  :  194 
Coefficients :  0 1 0 
Threshold= 1     Se= 26.6055 Sp= 84.70588 AUC= 0.5565569 
=============================================================================
*****************************************************************************
   ->  Sensitivity =  84.32956 Specificity =  72.13115 
*****************************************************************************
=============================================================================
Analysis performed in  2 cycles

ROP documentation built on May 2, 2019, 6:12 a.m.