Datos

Kelly Johanna Bojaca

2024-11-16

R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF,
and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the
output of any embedded R code chunks within the document. You can embed an R code chunk like this:

summary(cars)

## speed dist
## Min. : 4.0 Min. : 2.00
## 1st Qu.:12.0 1st Qu.: 26.00
## Median :15.0 Median : 36.00
## Mean :15.4 Mean : 42.98
## 3rd Qu.:19.0 3rd Qu.: 56.00
## Max. :25.0 Max. :120.00

Including Plots

You can also embed plots, for example:

1
 800
600
pressure

400
200
0

0 50 100 150 200 250 300 350

temperature

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that
generated the plot.

install.packages("dplyr", repos = "https://cran.rstudio.com/")

## Installing package into ’C:/Users/kelly/AppData/Local/R/win-library/4.4’

## (as ’lib’ is unspecified)

## package ’dplyr’ successfully unpacked and MD5 sums checked

## Warning: cannot remove prior installation of package ’dplyr’

## Warning in file.copy(savedcopy, lib, recursive = TRUE): problema al copiar

## C:\Users\kelly\AppData\Local\R\win-library\4.4\00LOCK\dplyr\libs\x64\dplyr.dll
## a C:\Users\kelly\AppData\Local\R\win-library\4.4\dplyr\libs\x64\dplyr.dll:
## Permission denied

## Warning: restored ’dplyr’

##
## The downloaded binary packages are in
## C:\Users\kelly\AppData\Local\Temp\RtmpCu35v5\downloaded_packages

2
library(ggplot2)
library(dplyr)

## Warning: package ’dplyr’ was built under R version 4.4.2

##
## Adjuntando el paquete: ’dplyr’

## The following objects are masked from ’package:stats’:

##
## filter, lag

## The following objects are masked from ’package:base’:

##
## intersect, setdiff, setequal, union

install.packages("titanic", repos = "https://cran.rstudio.com/")

## Installing package into ’C:/Users/kelly/AppData/Local/R/win-library/4.4’

## (as ’lib’ is unspecified)

## package ’titanic’ successfully unpacked and MD5 sums checked

##
## The downloaded binary packages are in
## C:\Users\kelly\AppData\Local\Temp\RtmpCu35v5\downloaded_packages

install.packages("cowplot", repos = "https://cran.rstudio.com/")

## Installing package into ’C:/Users/kelly/AppData/Local/R/win-library/4.4’

## (as ’lib’ is unspecified)

## package ’cowplot’ successfully unpacked and MD5 sums checked

##
## The downloaded binary packages are in
## C:\Users\kelly\AppData\Local\Temp\RtmpCu35v5\downloaded_packages

library(titanic)

## Warning: package ’titanic’ was built under R version 4.4.2

library(cowplot)

## Warning: package ’cowplot’ was built under R version 4.4.2

library(tidyr)
df<-titanic_train

3
df[1,1]<- NA
nadf1 <- df[!complete.cases(df), ]
nadf2 <- df[!complete.cases(df$Age), ]
ndf <- df[complete.cases(df$Age), ]
df <- titanic_train #Retomemos la base riginal sin modifica

ndf<-df%>%drop_na()
ndf<-na.omit(df)

h1<-ggplot(ndf,aes(x=Age))+
geom_histogram(fill="#ad1538", color="#000000",position="identity",bins=30) +
ggtitle("Originaldistribution") +
theme_classic()
plot_grid(h1,nrow=1,ncol=1)

Originaldistribution

60

40
count

20

0 20 40 60 80
Age

install.packages("simputation", repos = "https://cran.rstudio.com/")

## Installing package into ’C:/Users/kelly/AppData/Local/R/win-library/4.4’

## (as ’lib’ is unspecified)

## package ’simputation’ successfully unpacked and MD5 sums checked

##
## The downloaded binary packages are in
## C:\Users\kelly\AppData\Local\Temp\RtmpCu35v5\downloaded_packages

4
library(simputation)

## Warning: package ’simputation’ was built under R version 4.4.2

RHD<- impute_rhd(df, Age ~ Sex )

SHD<- impute_shd(df, Age ~ Parch , order ="locf") #opcion de order: "nocb"
4

## [1] 4

PMM<-impute_pmm(df,Age~Parch,predictor=impute_lm)
KNN<-impute_knn(df,Age~Parch,k=5)

h1<-ggplot(ndf,aes(x=Age))+
geom_histogram(fill="#ad1538", color="#000000",position="identity",bins=30) +
ggtitle("Originaldistribution") +
theme_classic()
h2<-ggplot(RHD,aes(x=Age))+
geom_histogram(fill="#15ad4f", color="#000000",position="identity",bins=30) +
ggtitle("RHD")+
theme_classic()
h3<-ggplot(SHD,aes(x=Age))+
geom_histogram(fill="#1543ad", color="#000000",position="identity",bins=30) +
ggtitle("SHD")+
theme_classic()
h4<-ggplot(PMM,aes(x=Age))+
geom_histogram(fill="#ad8415", color="#000000",position="identity",bins=30) +
ggtitle("PMM")+
theme_classic()
h5<-ggplot(KNN,aes(x=Age))+
geom_histogram(fill="#4515ad", color="#000000",position="identity",bins=30) +
ggtitle("KNN")+
theme_classic()
plot_grid(h1,h2,h3,h4,h5,nrow=3,ncol=2)

5
 Originaldistribution RHD
60 75
count

count
40 50
20 25
0 0
0 20 40 60 80 0 20 40 60 80
Age Age

SHD PMM
75 200
count

count
150
50
100
25 50
0 0
0 20 40 60 80 0 20 40 60 80
Age Age

KNN

100
count

50
0
0 20 40 60 80
Age

value_imputed <- data.frame(

original = titanic_train$Age,
imputed_zero = replace(titanic_train$Age, is.na(titanic_train$Age), 0),
imputed_mean = replace(titanic_train$Age, is.na(titanic_train$Age), mean(titanic_train$Age, na.rm = TR
imputed_median = replace(titanic_train$Age, is.na(titanic_train$Age), median(titanic_train$Age, na.rm
)

h1<-ggplot(value_imputed,aes(x=original))+
geom_histogram(fill="#ad1538", color="#000000",position="identity",bins=30) +
ggtitle("Originaldistribution") +
theme_classic()
h2<-ggplot(value_imputed,aes(x=imputed_zero))+
geom_histogram(fill="#15ad4f", color="#000000",position="identity",bins=30) +
ggtitle("Zero-imputeddistribution")+
theme_classic()
h3<-ggplot(value_imputed,aes(x=imputed_mean))+
geom_histogram(fill="#1543ad", color="#000000",position="identity",bins=30) +
ggtitle("Mean-imputeddistribution")+
theme_classic()
h4<-ggplot(value_imputed,aes(x=imputed_median))+
geom_histogram(fill="#ad8415", color="#000000",position="identity",bins=30) +
ggtitle("Median-imputeddistribution")+
theme_classic()
plot_grid(h1,h2,h3,h4,nrow=2,ncol=2)

## Warning: Removed 177 rows containing non-finite outside the scale range

6
## (‘stat_bin()‘).

Originaldistribution Zero−imputeddistribution
200

60 150
count

count
40 100

20 50

0 0
0 20 40 60 80 0 20 40 60 80
original imputed_zero

Mean−imputeddistribution Median−imputeddistribution
250
200
200
150
150
count

count

100 100

50 50

0 0
0 20 40 60 80 0 20 40 60 80
imputed_mean imputed_median

install.packages("mice", repos = "https://cran.rstudio.com/")

## Installing package into ’C:/Users/kelly/AppData/Local/R/win-library/4.4’

## (as ’lib’ is unspecified)

## package ’mice’ successfully unpacked and MD5 sums checked

##
## The downloaded binary packages are in
## C:\Users\kelly\AppData\Local\Temp\RtmpCu35v5\downloaded_packages

library(mice)

## Warning: package ’mice’ was built under R version 4.4.2

##
## Adjuntando el paquete: ’mice’

## The following object is masked from ’package:stats’:

##
## filter

7
## The following objects are masked from ’package:base’:
##
## cbind, rbind

titanic_numeric <- df %>%

select(Survived, Pclass, SibSp, Parch, Age)
md.pattern(titanic_numeric)

Survived Pclass SibSp Parch Age

714 0

177 1

0 0 0 0 177 177

## Survived Pclass SibSp Parch Age

## 714 1 1 1 1 1 0
## 177 1 1 1 1 0 1
## 0 0 0 0 177 177

mice_imputed <- data.frame(

original = titanic_train$Age,
imputed_pmm = complete(mice(titanic_numeric, method = "pmm"))$Age,
imputed_cart = complete(mice(titanic_numeric, method = "cart"))$Age,
imputed_lasso = complete(mice(titanic_numeric, method = "lasso.norm"))$Age
)

##
## iter imp variable
## 1 1 Age
## 1 2 Age

8
## 1 3 Age
## 1 4 Age
## 1 5 Age
## 2 1 Age
## 2 2 Age
## 2 3 Age
## 2 4 Age
## 2 5 Age
## 3 1 Age
## 3 2 Age
## 3 3 Age
## 3 4 Age
## 3 5 Age
## 4 1 Age
## 4 2 Age
## 4 3 Age
## 4 4 Age
## 4 5 Age
## 5 1 Age
## 5 2 Age
## 5 3 Age
## 5 4 Age
## 5 5 Age
##
## iter imp variable
## 1 1 Age
## 1 2 Age
## 1 3 Age
## 1 4 Age
## 1 5 Age
## 2 1 Age
## 2 2 Age
## 2 3 Age
## 2 4 Age
## 2 5 Age
## 3 1 Age
## 3 2 Age
## 3 3 Age
## 3 4 Age
## 3 5 Age
## 4 1 Age
## 4 2 Age
## 4 3 Age
## 4 4 Age
## 4 5 Age
## 5 1 Age
## 5 2 Age
## 5 3 Age
## 5 4 Age
## 5 5 Age
##
## iter imp variable
## 1 1 Age
## 1 2 Age

9
## 1 3 Age
## 1 4 Age
## 1 5 Age
## 2 1 Age
## 2 2 Age
## 2 3 Age
## 2 4 Age
## 2 5 Age
## 3 1 Age
## 3 2 Age
## 3 3 Age
## 3 4 Age
## 3 5 Age
## 4 1 Age
## 4 2 Age
## 4 3 Age
## 4 4 Age
## 4 5 Age
## 5 1 Age
## 5 2 Age
## 5 3 Age
## 5 4 Age
## 5 5 Age

head(mice_imputed)

## original imputed_pmm imputed_cart imputed_lasso

## 1 22 22 22.0 22.00000
## 2 38 38 38.0 38.00000
## 3 26 26 26.0 26.00000
## 4 35 35 35.0 35.00000
## 5 35 35 35.0 35.00000
## 6 NA 53 24.5 19.90163

h1 <- ggplot(mice_imputed, aes(x = original)) +

geom_histogram(fill = "#ad1538", color = "#000000", position = "identity",bins=30) +
ggtitle("Original distribution") +
theme_classic()
h2 <- ggplot(mice_imputed, aes(x = imputed_pmm)) +
geom_histogram(fill = "#15ad4f", color = "#000000", position = "identity",bins=30) +
ggtitle("PMM-imputed distribution") +
theme_classic()
h3 <- ggplot(mice_imputed, aes(x = imputed_cart)) +
geom_histogram(fill = "#1543ad", color = "#000000", position = "identity",bins=30) +
ggtitle("CART-imputed distribution") +
theme_classic()
h4 <- ggplot(mice_imputed, aes(x = imputed_lasso)) +
geom_histogram(fill = "#ad8415", color = "#000000", position = "identity",bins=30) +
ggtitle("Lasso-imputed distribution") +
theme_classic()
plot_grid(h1, h2, h3, h4, nrow = 2, ncol = 2)

## Warning: Removed 177 rows containing non-finite outside the scale range
## (‘stat_bin()‘).

10
 Original distribution PMM−imputed distribution

60 90
count

count
40 60

20 30

0 0
0 20 40 60 80 0 20 40 60 80
original imputed_pmm

CART−imputed distribution Lasso−imputed distribution

75 75
count

count
50 50

25 25

0 0
0 20 40 60 80 0 20 40 60 80
imputed_cart imputed_lasso

install.packages("missForest", repos = "https://cran.rstudio.com/")

## Installing package into ’C:/Users/kelly/AppData/Local/R/win-library/4.4’

## (as ’lib’ is unspecified)

## package ’missForest’ successfully unpacked and MD5 sums checked

##
## The downloaded binary packages are in
## C:\Users\kelly\AppData\Local\Temp\RtmpCu35v5\downloaded_packages

library(missForest)

## Warning: package ’missForest’ was built under R version 4.4.2

missForest_imputed<-data.frame(
original=titanic_numeric$Age,
imputed_missForest=missForest(titanic_numeric)$ximp$Age
)
head(missForest_imputed)

## original imputed_missForest
## 1 22 22.00000
## 2 38 38.00000

11
## 3 26 26.00000
## 4 35 35.00000
## 5 35 35.00000
## 6 NA 29.25033

h1<-ggplot(missForest_imputed,aes(x=original))+
geom_histogram(fill="#ad1538", color="#000000",position="identity",bins=30)+
ggtitle("Originaldistribution") +
theme_classic()
h2<-ggplot(missForest_imputed,aes(x=imputed_missForest))+
geom_histogram(fill="#15ad4f", color="#000000",position="identity",bins=30)+
ggtitle("MissForest-imputeddistribution")+
theme_classic()
plot_grid(h1,h2,nrow=1,ncol=2)

## Warning: Removed 177 rows containing non-finite outside the scale range
## (‘stat_bin()‘).

Originaldistribution MissForest−imputeddistribution
150

60

100

40
count

count

50

20

0 0

0 20 40 60 80 0 20 40 60 80
original imputed_missForest

Titanic<- titanic_train
Titanic$Survived <- as.factor(ifelse(Titanic$Survived=="0","No","Yes"))
Titanic$Sex <- as.factor(Titanic$Sex)
Titanic$PClass <- as.factor(Titanic$Pclass)
Titanic <- Titanic[,c("Survived","PClass","Sex","Age")]
with(Titanic,{
print(table(Sex))

12
print(table(PClass))
print(table(Survived))
})

## Sex
## female male
## 314 577
## PClass
## 1 2 3
## 216 184 491
## Survived
## No Yes
## 549 342

cat ("Proporción Female:", table(Titanic$Sex)[1]/length(Titanic$Sex))

## Proporción Female: 0.352413

cat ("Proporción Male:", table(Titanic$Sex)[2]/length(Titanic$Sex))

## Proporción Male: 0.647587

cat ("Proporción Clase 1:", table(Titanic$PClass)[1]/length(Titanic$PClass))

## Proporción Clase 1: 0.2424242

cat ("Proporción Clase 2:", table(Titanic$PClass)[2]/length(Titanic$PClass))

## Proporción Clase 2: 0.2065095

cat ("Proporción Clase 3:", table(Titanic$PClass)[3]/length(Titanic$PClass))

## Proporción Clase 3: 0.5510662

cat ("Proporción Sobrevivió:", table(Titanic$Survived)[1]/length(Titanic$Survived))

## Proporción Sobrevivió: 0.6161616

cat ("Proporción Murió:", table(Titanic$Survived)[2]/length(Titanic$Survived))

## Proporción Murió: 0.3838384

install.packages("caret", repos = "https://cran.rstudio.com/")

## Installing package into ’C:/Users/kelly/AppData/Local/R/win-library/4.4’

## (as ’lib’ is unspecified)

13
## package ’caret’ successfully unpacked and MD5 sums checked

## Warning: cannot remove prior installation of package ’caret’

## Warning in file.copy(savedcopy, lib, recursive = TRUE): problema al copiar

## C:\Users\kelly\AppData\Local\R\win-library\4.4\00LOCK\caret\libs\x64\caret.dll
## a C:\Users\kelly\AppData\Local\R\win-library\4.4\caret\libs\x64\caret.dll:
## Permission denied

## Warning: restored ’caret’

##
## The downloaded binary packages are in
## C:\Users\kelly\AppData\Local\Temp\RtmpCu35v5\downloaded_packages

library(caret)

## Warning: package ’caret’ was built under R version 4.4.2

## Cargando paquete requerido: lattice

table(Titanic$Sex)

##
## female male
## 314 577

Titanic.down <- downSample(Titanic[,-1],Titanic$Sex,yname="Sex")

table(Titanic.down$Sex)

##
## female male
## 314 314

table(Titanic$Sex)

##
## female male
## 314 577

Titanic.up <- upSample(Titanic[,-1],Titanic$Sex,yname="Sex")

table(Titanic.up$Sex)

##
## female male
## 577 577

14
NF <- sample_n(filter(Titanic, Sex == "female"), 36)
OverT <- rbind(Titanic,NF)
table(OverT$Sex)

##
## female male
## 350 577

remover <- sample(which(Titanic$Sex=="male"),77)

UnderT <- Titanic[-remover,]
table(UnderT$Sex)

##
## female male
## 314 500

install.packages("scutr", repos = "https://cran.rstudio.com/")

## Installing package into ’C:/Users/kelly/AppData/Local/R/win-library/4.4’

## (as ’lib’ is unspecified)

## package ’scutr’ successfully unpacked and MD5 sums checked

##
## The downloaded binary packages are in
## C:\Users\kelly\AppData\Local\Temp\RtmpCu35v5\downloaded_packages

library(scutr)

## Warning: package ’scutr’ was built under R version 4.4.2

Titanic<- titanic_train[,c(1,2,3,5,6,7,8,10)]
Titanic<-na.omit(Titanic)
Tsmote<-SCUT(Titanic, "Sex",oversample = oversample_smote)
table(Tsmote$Sex)

##
## female male
## 357 357

15