IRTF (Met) GA Models vs Modern Catalogues [Newton, Mann, Gaidos].

Introduction

After the modelling process from GA features, the outcome will be compared against catallogues from Gaidos, Mann and Newton.

## Loading required package: MASS
## Loading required package: Cubist
## Loading required package: lattice
## Loading required package: caret
## Loading required package: ggplot2
## Loading required package: xtable
## Loading required package: Peaks
## Loading required package: magic
## Loading required package: abind
## Loading required package: JADE
## Loading required package: doMC
## Loading required package: foreach
## Loading required package: iterators
## Loading required package: parallel
## Loading required package: segmented
## Loading required package: fftw
## Loading required package: FITSio
## Loading required package: stringr
## Loading required package: ztable
## Welcome to package ztable ver 0.1.5
## Loading required package: party
## Loading required package: grid
## Loading required package: mvtnorm
## Loading required package: modeltools
## Loading required package: stats4
## Loading required package: strucchange
## Loading required package: zoo
## 
## Attaching package: 'zoo'
## 
## The following objects are masked from 'package:base':
## 
##     as.Date, as.Date.numeric
## 
## Loading required package: sandwich
## 
## Attaching package: 'strucchange'
## 
## The following object is masked from 'package:stringr':
## 
##     boundary
## 
## Loading required package: signal
## 
## Attaching package: 'signal'
## 
## The following objects are masked from 'package:stats':
## 
##     filter, poly
## 
## Loading required package: e1071
## Loading required package: plyr
## 
## Attaching package: 'plyr'
## 
## The following object is masked from 'package:modeltools':
## 
##     empty
## 
## Loading required package: compare
## 
## Attaching package: 'compare'
## 
## The following object is masked from 'package:base':
## 
##     isTRUE
## 
## Loading required package: mgcv
## Loading required package: nlme
## This is mgcv 1.8-11. For overview type 'help("mgcv-package")'.
## 
## Attaching package: 'mgcv'
## 
## The following object is masked from 'package:magic':
## 
##     magic
## 
## Loading required package: elasticnet
## Loading required package: lars
## Loaded lars 1.2
## 
## Loading required package: pbapply
## Loading required package: nnet
## 
## Attaching package: 'nnet'
## 
## The following object is masked from 'package:mgcv':
## 
##     multinom
## 
## Loading required package: kernlab
## 
## Attaching package: 'kernlab'
## 
## The following object is masked from 'package:modeltools':
## 
##     prior
## 
## Loading required package: pls
## 
## Attaching package: 'pls'
## 
## The following object is masked from 'package:caret':
## 
##     R2
## 
## The following object is masked from 'package:stats':
## 
##     loadings
## 
## Loading required package: devtools
## Loading required package: caretEnsemble
## Loading required package: mlbench
## Loading required package: mclust
## Package 'mclust' version 5.1
## Type 'citation("mclust")' for citing this R package in publications.
## 
## Attaching package: 'mclust'
## 
## The following object is masked from 'package:mgcv':
## 
##     mvn
## 
## Loading required package: analogue
## Loading required package: vegan
## Loading required package: permute
## 
## Attaching package: 'permute'
## 
## The following object is masked from 'package:devtools':
## 
##     check
## 
## The following object is masked from 'package:kernlab':
## 
##     how
## 
## This is vegan 2.3-2
## 
## Attaching package: 'vegan'
## 
## The following object is masked from 'package:pls':
## 
##     scores
## 
## The following object is masked from 'package:caret':
## 
##     tolerance
## 
## This is analogue 0.16-3
## 
## Attaching package: 'analogue'
## 
## The following objects are masked from 'package:pls':
## 
##     crossval, pcr, RMSEP
## 
## The following object is masked from 'package:compare':
## 
##     compare
## 
## The following object is masked from 'package:plyr':
## 
##     join
## 
## Loading required package: cluster

Loading predictions from GA based models

Loading recent models

1 final-Gaidos2014-*.tsv contiene muchas columnas. En particular, la primera contiene el nombre de la estrella, la #34 contiene Fe/H y la #35 la temperatura efectiva.

2 final-Mann2015-*.tsv: la primera contiene el nombre de la estrella, la #11 contiene Fe/H y la #8 la temperatura efectiva.

3 final-Newton2014*.tsv: la primera contiene el nombre de la estrella y la #15 contiene Fe/H. En el fichero de IPAC hay dos estrellas que están repetidas: es porque tienen dos estimaciones.

Comparison Fe/H between sources

Gaidos

drmse dmae drmdse dmade
RF_Inf 0.79 0.75 0.74 0.74
GB_Inf 0.72 0.65 0.62 0.62
SVR_Inf 1.24 1.16 1.23 1.23
NNR_Inf 1.39 1.27 1.24 1.24
KNN_Inf 0.37 0.35 0.39 0.39
MARS_Inf 1.26 1.14 1.15 1.15
PLS_Inf 1.72 1.51 1.30 1.30
Rule-Regression_Inf 1.34 1.26 1.28 1.28
RF_10 0.48 0.41 0.38 0.38
GB_10 0.38 0.34 0.34 0.34
SVR_10 0.46 0.35 0.28 0.28
NNR_10 0.35 0.22 0.08 0.08
KNN_10 0.65 0.51 0.52 0.52
MARS_10 0.44 0.37 0.32 0.32
PLS_10 0.66 0.62 0.52 0.52
Rule-Regression_10 0.42 0.34 0.24 0.24
RF_50 0.44 0.40 0.38 0.38
GB_50 0.41 0.36 0.31 0.31
SVR_50 0.41 0.33 0.32 0.32
NNR_50 0.57 0.48 0.47 0.47
KNN_50 0.50 0.44 0.39 0.39
MARS_50 0.52 0.47 0.58 0.58
PLS_50 1.12 0.96 0.86 0.86
Rule-Regression_50 0.34 0.25 0.19 0.19
Chi2_inf 0.31 0.27 0.29 0.29
Chi2_10 0.49 0.39 0.36 0.36
Chi2_50 0.31 0.27 0.29 0.29
ICA_inf 0.36 0.27 0.20 0.20
ICA_10 0.29 0.20 0.14 0.14
ICA_50 0.60 0.47 0.51 0.51
M_teo
n_muestras
1 9

Mann

drmse dmae drmdse dmade
RF_Inf 0.91 0.87 0.81 0.81
GB_Inf 0.86 0.78 0.78 0.76
SVR_Inf 1.38 1.30 1.41 1.41
NNR_Inf 1.59 1.47 1.68 1.66
KNN_Inf 0.38 0.33 0.33 0.33
MARS_Inf 1.46 1.35 1.31 1.30
PLS_Inf 1.95 1.73 1.49 1.48
Rule-Regression_Inf 1.59 1.51 1.62 1.62
RF_10 0.33 0.27 0.21 0.20
GB_10 0.31 0.25 0.23 0.23
SVR_10 0.32 0.26 0.24 0.23
NNR_10 0.31 0.26 0.25 0.25
KNN_10 0.47 0.35 0.19 0.19
MARS_10 0.32 0.27 0.28 0.27
PLS_10 0.50 0.41 0.40 0.38
Rule-Regression_10 0.32 0.26 0.25 0.25
RF_50 0.75 0.48 0.25 0.25
GB_50 0.72 0.45 0.26 0.26
SVR_50 0.45 0.33 0.22 0.21
NNR_50 0.56 0.48 0.38 0.38
KNN_50 0.35 0.29 0.26 0.26
MARS_50 0.56 0.50 0.50 0.49
PLS_50 1.21 1.05 0.91 0.89
Rule-Regression_50 0.46 0.32 0.19 0.19
Chi2_inf 0.36 0.31 0.30 0.30
Chi2_10 0.54 0.35 0.24 0.23
Chi2_50 0.36 0.31 0.30 0.30
ICA_inf 0.41 0.33 0.24 0.24
ICA_10 0.22 0.15 0.08 0.08
ICA_50 0.41 0.34 0.31 0.30
M_teo 0.24 0.23 0.24 0.23
n_muestras
1 12

Newton

drmse dmae drmdse dmade
RF_Inf 0.65 0.57 0.64 0.64
GB_Inf 0.46 0.39 0.41 0.38
SVR_Inf 1.27 1.12 1.17 1.12
NNR_Inf 1.57 1.43 1.63 1.58
KNN_Inf 0.25 0.22 0.24 0.24
MARS_Inf 1.36 1.18 1.36 1.33
PLS_Inf 1.87 1.61 1.59 1.56
Rule-Regression_Inf 1.32 1.19 1.24 1.24
RF_10 0.27 0.23 0.23 0.23
GB_10 0.23 0.20 0.17 0.17
SVR_10 0.24 0.17 0.13 0.12
NNR_10 0.27 0.23 0.29 0.27
KNN_10 0.13 0.12 0.13 0.12
MARS_10 0.25 0.22 0.16 0.16
PLS_10 0.44 0.32 0.25 0.23
Rule-Regression_10 0.24 0.21 0.22 0.22
RF_50 0.29 0.26 0.27 0.27
GB_50 0.28 0.24 0.17 0.17
SVR_50 0.43 0.40 0.41 0.41
NNR_50 0.58 0.49 0.45 0.45
KNN_50 0.31 0.27 0.29 0.29
MARS_50 0.55 0.49 0.65 0.65
PLS_50 1.36 1.18 1.24 1.24
Rule-Regression_50 0.40 0.37 0.37 0.37
Chi2_inf 0.46 0.44 0.48 0.48
Chi2_10 0.35 0.32 0.36 0.35
Chi2_50 0.46 0.44 0.48 0.48
ICA_inf 0.37 0.34 0.37 0.36
ICA_10 0.14 0.11 0.13 0.11
ICA_50 0.44 0.42 0.44 0.44
M_teo
n_muestras
1 6