#Importing inst100
inst100 <- read_csv("D:/Dropbox/MsC UABC/2o Semestre/Clases/Estadistica/Danisa/2. Tidy dataset/instancia 100.csv")
#Eliminando las columnas sin resultados
inst100 <- inst100[,-3]
inst100 <- inst100[,-4]
colnames(inst100) <- c("C1", "C2", "R2", "RC2")
histogram(~ C1 + C2 + R2 + RC2, data = inst100,
main="Histogramas de Resultados en Instancia 100 ",
xlab = "features")
#Anderson-Darling Normality Test
c1test<-RE.ADT(inst100$C1)
c1test
## [[1]]
## [1] "Anderson-Darling Test"
##
## $p
## [1] 0.3977163
c2_test <- RE.ADT(inst100$C2)
c2_test
## [[1]]
## [1] "Anderson-Darling Test"
##
## $p
## [1] 0.009035369
r2_test <- RE.ADT(inst100$R2)
r2_test
## [[1]]
## [1] "Anderson-Darling Test"
##
## $p
## [1] 0.2585398
rc2_test <- RE.ADT(inst100$RC2)
r2_test
## [[1]]
## [1] "Anderson-Darling Test"
##
## $p
## [1] 0.2585398
#Johnson Transformations
c1_johnson <- RE.Johnson(inst100$C1)
c2_johnson <- RE.Johnson(inst100$C2)
r2_johnson <- RE.Johnson(inst100$R2)
rc2_johnson <- RE.Johnson(inst100$RC2)
hist(c1_johnson$transformed,
col = "pink",
main = "Transformación de Johnson C1",
xlab = "Valores",
ylab = "Frecuencia")
hist(c2_johnson$transformed,
col = "pink",
main = "Transformación de Johnson C2",
xlab = "Valores",
ylab = "Frecuencia")
hist(r2_johnson$transformed,
col = "pink",
main = "Transformación de Johnson R2",
xlab = "Valores",
ylab = "Frecuencia")
hist(rc2_johnson$transformed,
col = "pink",
main = "Transformación de Johnson RC2",
xlab = "Valores",
ylab = "Frecuencia")
#C1
qqnorm(c1_johnson$transformed,
col = "navyblue",
main = "C1")
qqline(c1_johnson$transformed,
lwd = 3,
col = "red")
#C2
qqnorm(c2_johnson$transformed,
col = "navyblue",
main = "C2")
qqline(c2_johnson$transformed,
lwd = 3,
col = "red")
#R2
qqnorm(r2_johnson$transformed,
col = "navyblue",
main = "R2")
qqline(r2_johnson$transformed,
lwd = 3,
col = "red")
#RC2
qqnorm(rc2_johnson$transformed,
col = "navyblue",
main = "C1")
qqline(rc2_johnson$transformed,
lwd = 3,
col = "red")
En el test Anderson-Darling un valor p mayor es mejor
C1
ac1_johnson <- RE.ADT(c1_johnson$transformed)
ac1_johnson
## [[1]]
## [1] "Anderson-Darling Test"
##
## $p
## [1] 0.5190301
C2
ac2_johnson <- RE.ADT(c2_johnson$transformed)
ac2_johnson
## [[1]]
## [1] "Anderson-Darling Test"
##
## $p
## [1] 0.3500646
R2
ar2_johnson <- RE.ADT(r2_johnson$transformed)
ar2_johnson
## [[1]]
## [1] "Anderson-Darling Test"
##
## $p
## [1] 0.8400051
RC2
arc2_johnson <- RE.ADT(rc2_johnson$transformed)
arc2_johnson
## [[1]]
## [1] "Anderson-Darling Test"
##
## $p
## [1] 0.7858921
#Cargar dataset
dataset <- read_excel("D:/Dropbox/MsC UABC/2o Semestre/Clases/Estadistica/Danisa/1. Raw dataset/DATOS FINALES DOE.xlsx", col_names = FALSE)
#Cortar la base de datos
dataset <- dataset[-11:-36,-1:-13]
dataset <- dataset[-1:-2,-6]
colnames(dataset) <- c("Iteración", "veinticinco", "cincuenta", "cien", "Promedio")
dataset <- dataset[,-5]
Histograma
histogram(~ veinticinco + cincuenta + cien, data = dataset,
main="Histogramas de Resultados por Instancia ",
xlab = "features")
BoxPlots
boxplot(dataset[,2:4],
main = "Boxplot de Resultados por Instancia")
#Anderson-Darling Normality Test
test25<-RE.ADT(dataset$veinticinco)
test25
## [[1]]
## [1] "Anderson-Darling Test"
##
## $p
## [1] 0.4453185
#Anderson-Darling Normality Test
test50<-RE.ADT(dataset$cincuenta)
test50
## [[1]]
## [1] "Anderson-Darling Test"
##
## $p
## [1] 0.2479992
#Anderson-Darling Normality Test
test100<-RE.ADT(dataset$cien)
test100
## [[1]]
## [1] "Anderson-Darling Test"
##
## $p
## [1] 0.03106897
#Johnson Transformations
test25_johnson <- RE.Johnson(dataset$veinticinco)
test50_johnson <- RE.Johnson(dataset$cincuenta)
test100_johnson <- RE.Johnson(dataset$cien)
#25
hist(test25_johnson$transformed,
col = "pink",
prob = TRUE,
main = "Transformación de Johnson 25",
xlab = "Valores",
ylab = "Frecuencia")
lines(density(test25_johnson$transformed),
lwd = 3,
col = "red")
#50
hist(test50_johnson$transformed,
col = "pink",
prob = TRUE,
main = "Transformación de Johnson 50",
xlab = "Valores",
ylab = "Frecuencia")
lines(density(test50_johnson$transformed),
lwd = 3,
col = "red")
#100
hist(test100_johnson$transformed,
col = "pink",
prob = TRUE,
main = "Transformación de Johnson 100",
xlab = "Valores",
ylab = "Frecuencia")
lines(density(test100_johnson$transformed),
lwd = 3,
col = "red")
25
#25
qqnorm(test25_johnson$transformed,
col = "navyblue",
main = "Instancia 25")
qqline(test25_johnson$transformed,
lwd = 3,
col = "red")
50
#50
qqnorm(test50_johnson$transformed,
col = "navyblue",
main = "Instancia 50")
qqline(test50_johnson$transformed,
lwd = 3,
col = "red")
100
#100
qqnorm(test100_johnson$transformed,
col = "navyblue",
main = "Instancia 100")
qqline(test100_johnson$transformed,
lwd = 3,
col = "red")
#Valores 25
valores25 <- matrix(sort(test25_johnson$transformed, decreasing = TRUE),
nrow = 8,
ncol = 1)
colnames(valores25) <- c("Instancia 25")
#Valores 50
valores50 <- matrix(sort(test50_johnson$transformed, decreasing = TRUE),
nrow = 8,
ncol = 1)
colnames(valores50) <- c("Instancia 50")
#Valores 100
valores100 <- matrix(sort(test100_johnson$transformed, decreasing = TRUE),
nrow = 8,
ncol = 1)
colnames(valores100) <- c("Instancia 100")
##Combinando todo en una sola matriz
final <- cbind(valores25, valores50, valores100)
Se presenta una matriz con los resultados en orden descendente, obtenidos por transformación de datos de Johnson, de cada una de las instancias:
#write.csv(final, file = "Datos Transformados")
final
## Instancia 25 Instancia 50 Instancia 100
## [1,] 1.8600000 1.56000000 1.7383196
## [2,] 0.7469230 1.39252352 0.6621640
## [3,] 0.5589661 0.35671883 0.4957544
## [4,] -0.1771684 0.35669458 0.3543305
## [5,] -0.2776206 0.08227105 0.2840145
## [6,] -0.4015054 -0.46947451 -0.4933830
## [7,] -1.4208361 -0.97477719 -0.7736696
## [8,] -1.8600000 -1.56000000 -1.6302568
boxplot(final)
promgral <- matrix(c(18.86840375,13.55024,18.45171131,18.54769356,15.55413375,12.08616962,14.6371108,10.44505313,13.0532618),ncol=1,byrow=TRUE)
colnames(promgral) <- c("general")
promgral
## general
## [1,] 18.86840
## [2,] 13.55024
## [3,] 18.45171
## [4,] 18.54769
## [5,] 15.55413
## [6,] 12.08617
## [7,] 14.63711
## [8,] 10.44505
## [9,] 13.05326
boxplot(promgral,
main = "Boxplot del Promedio de Todas las Instancias Combinadas")
#log
boxplot(log(promgral),
main = "Log")
#sqrt
boxplot(sqrt(promgral),
main = "sqrt")
#1/x
boxplot(1/promgral,
main = "1/x")
#x^2
boxplot(promgral^2,
main = "x^2")