Tablas y gráficos descriptivos en R
Orlando Moscote Flórez
5/2/2022
library(summarytools)
library(plotrix)
library(gmodels)
library(agricolae)1. variable cualitativa
Los datos corresponden a la marca de auto que poseen 50 personas.
Marca<-c("Chevrolet","Ford","Kia","Mazda","Renault","Renault","Chevrolet","Chevrolet","Mazda","Ford","Mazda","Chevrolet","Renault","Chevrolet","Ford","Chevrolet","Renault","Ford","Mazda","Chevrolet","Renault","Mazda","Chevrolet","Ford","Renault","Chevrolet","Renault","Mazda","Ford","Kia","Renault","Mazda","Mazda","Chevrolet","Kia","Renault","Chevrolet","Chevrolet","Mazda","Ford","Kia","Renault","Chevrolet","Chevrolet","Renault","Renault","Mazda","Ford","Chevrolet","Mazda")1.1 Tabla de distribución de frecuencias.
T1<-table(Marca)
Personas<-c(T1)
Porcentaje<-round(prop.table(T1)*100,1)
t1<-sum(Personas)
t2<-sum(Porcentaje)
Tabla<-cbind(Personas,Porcentaje)
Suma<-cbind(t1,t2)
rownames(Suma)<-c("Total")
Tabla2<-rbind(Tabla,Suma)
Tabla2## Personas Porcentaje
## Chevrolet 15 30
## Ford 8 16
## Kia 4 8
## Mazda 11 22
## Renault 12 24
## Total 50 1001.2 Utilizando el paquete summarytools
freq(Marca,style="rmarkdown", report.nas = FALSE, headings = FALSE)## setting plain.ascii to FALSE##
## | | Freq | % | % Cum. |
## |--------------:|-----:|-------:|-------:|
## | **Chevrolet** | 15 | 30.00 | 30.00 |
## | **Ford** | 8 | 16.00 | 46.00 |
## | **Kia** | 4 | 8.00 | 54.00 |
## | **Mazda** | 11 | 22.00 | 76.00 |
## | **Renault** | 12 | 24.00 | 100.00 |
## | **Total** | 50 | 100.00 | 100.00 |1.3 Gráfico de barras
barpos<-barplot(T1,main="Marca del auto",col="lightblue")
barlabels(barpos,T1)
1.4 Gráfico de sectores (pie chart)
lab<-c("Chevrolet","Ford","Kia","Mazda","Renault")
lab<-paste(lab,Porcentaje)
lab <- paste(lab,"%",sep="")
pie(T1,labels=lab,radius=1,col=3:7)
2. Dos variables cualitativas (tablas de contingencia)
Se agrega la variable: forma de tenencia de la vivienda donde residen las personas.
Vivienda<-c("Propia","Arriendo","Familiar","Propia","Propia","Arriendo","Familiar","Arriendo","Arriendo","Arriendo","Familiar","Propia","Propia","Propia","Arriendo","Familiar","Propia","Propia","Arriendo","Arriendo","Familiar","Familiar","Propia","Propia","Arriendo","Arriendo","Arriendo","Familiar","Propia","Propia","Propia","Arriendo","Familiar","Familiar","Propia","Propia","Arriendo","Arriendo","Familiar","Propia","Arriendo","Familiar","Familiar","Propia","Arriendo","Propia","Arriendo","Familiar","Propia","Propia")2.1 Tabla de contingencia
T2<-table(Marca,Vivienda)
addmargins(T2)## Vivienda
## Marca Arriendo Familiar Propia Sum
## Chevrolet 5 4 6 15
## Ford 3 1 4 8
## Kia 1 1 2 4
## Mazda 4 5 2 11
## Renault 4 2 6 12
## Sum 17 13 20 50addmargins(prop.table(T2)*100)## Vivienda
## Marca Arriendo Familiar Propia Sum
## Chevrolet 10 8 12 30
## Ford 6 2 8 16
## Kia 2 2 4 8
## Mazda 8 10 4 22
## Renault 8 4 12 24
## Sum 34 26 40 100t1<-prop.table(T2,1)
t2<-round(prop.table(T2,2),3)
addmargins(prop.table(T2,1),2)## Vivienda
## Marca Arriendo Familiar Propia Sum
## Chevrolet 0.3333333 0.2666667 0.4000000 1.0000000
## Ford 0.3750000 0.1250000 0.5000000 1.0000000
## Kia 0.2500000 0.2500000 0.5000000 1.0000000
## Mazda 0.3636364 0.4545455 0.1818182 1.0000000
## Renault 0.3333333 0.1666667 0.5000000 1.00000002.2 utilizando el paquete summarytools
ctable(x ="Marca",
y = "Vivienda",
prop = "r")## Cross-Tabulation, Row Proportions
## Marca * Vivienda
##
## ------- ---------- ------------ ------------
## Vivienda Vivienda Total
## Marca
## Marca 1 (100.0%) 1 (100.0%)
## Total 1 (100.0%) 1 (100.0%)
## ------- ---------- ------------ ------------2.3 Utilizando el paquete gmodels
T4<-CrossTable(Marca,Vivienda, prop.chisq=FALSE)##
##
## Cell Contents
## |-------------------------|
## | N |
## | N / Row Total |
## | N / Col Total |
## | N / Table Total |
## |-------------------------|
##
##
## Total Observations in Table: 50
##
##
## | Vivienda
## Marca | Arriendo | Familiar | Propia | Row Total |
## -------------|-----------|-----------|-----------|-----------|
## Chevrolet | 5 | 4 | 6 | 15 |
## | 0.333 | 0.267 | 0.400 | 0.300 |
## | 0.294 | 0.308 | 0.300 | |
## | 0.100 | 0.080 | 0.120 | |
## -------------|-----------|-----------|-----------|-----------|
## Ford | 3 | 1 | 4 | 8 |
## | 0.375 | 0.125 | 0.500 | 0.160 |
## | 0.176 | 0.077 | 0.200 | |
## | 0.060 | 0.020 | 0.080 | |
## -------------|-----------|-----------|-----------|-----------|
## Kia | 1 | 1 | 2 | 4 |
## | 0.250 | 0.250 | 0.500 | 0.080 |
## | 0.059 | 0.077 | 0.100 | |
## | 0.020 | 0.020 | 0.040 | |
## -------------|-----------|-----------|-----------|-----------|
## Mazda | 4 | 5 | 2 | 11 |
## | 0.364 | 0.455 | 0.182 | 0.220 |
## | 0.235 | 0.385 | 0.100 | |
## | 0.080 | 0.100 | 0.040 | |
## -------------|-----------|-----------|-----------|-----------|
## Renault | 4 | 2 | 6 | 12 |
## | 0.333 | 0.167 | 0.500 | 0.240 |
## | 0.235 | 0.154 | 0.300 | |
## | 0.080 | 0.040 | 0.120 | |
## -------------|-----------|-----------|-----------|-----------|
## Column Total | 17 | 13 | 20 | 50 |
## | 0.340 | 0.260 | 0.400 | |
## -------------|-----------|-----------|-----------|-----------|
##
## 2.4 Gráfico de barras compuestas
bar<-barplot(T2,col=c(3,4,5,6,7))
barlabels(bar,T2)## Warning in rep(xpos, each = length(ypos)/length(xpos)) + rep(c(-offset, :
## longitud de objeto mayor no es múltiplo de la longitud de uno menorlegend("top",legend=c("Chevrolet","Ford","Kia","Mazda","Renault"),
col=c(3,4,5,6,7),lty=1:4,lwd=3)
2.5 Gráfico de barras agrupadas
barpos<-barplot(T2,main="Marca vs Vivienda",col=c("darkblue","red","green","yellow"),
beside=TRUE)
barlabels(barpos,T2)
legend("top",legend=c("Chevrolet","Ford","Kia","Mazda","Renault"),
col=c("darkblue","red","green","yellow"),lty=1:4,lwd=3)
2.6 barras compuestas en proporciones
barplot(t2,col=c(1,2,3,4,5),ylim=c(0,1.5))
barlabels(bar,t2)## Warning in rep(xpos, each = length(ypos)/length(xpos)) + rep(c(-offset, :
## longitud de objeto mayor no es múltiplo de la longitud de uno menorlegend("top",legend=c("Chevrolet","Ford","Kia","Mazda","Renault"),
col=c(1,2,3,4,5),lty=1:4,lwd=3)
3 Variable cuantitativa discreta
Se utilizan datos correspondientes al número de defectos encontrados en una muestra de 50 piezas elaboradas en un proceso de producción.
defectos<-c(3,1,2,0,1,2,1,0,1,0,2,1,0,1,2,5,1,2,3,2,1,0,1,2,1,1,2,5,4,1,2,3,0,
0,1,2,4,3,1,0,2,1,4,3,1,0,1,1,2,4)3.1 Tabla de distribución de frecuencias.
T10<-table(defectos)
num<-c(T10)
por<-round(prop.table(T10)*100,1)
nunacu<-cumsum(num)
poracu<-cumsum(por)
Tabla11<-cbind(num,por,nunacu,poracu)
colnames(Tabla11)<-c("n°piezas","por. piezas","num. ac. piezas","por.ac.piezas")
Tabla11## n°piezas por. piezas num. ac. piezas por.ac.piezas
## 0 9 18 9 18
## 1 18 36 27 54
## 2 12 24 39 78
## 3 5 10 44 88
## 4 4 8 48 96
## 5 2 4 50 100t4<-sum(num)
t5<-sum(por)
Suma<-cbind(t4,t5,0,0)
rownames(Suma)<-c("Total")
Tabla12<-rbind(Tabla11,Suma)
Tabla12## n°piezas por. piezas num. ac. piezas por.ac.piezas
## 0 9 18 9 18
## 1 18 36 27 54
## 2 12 24 39 78
## 3 5 10 44 88
## 4 4 8 48 96
## 5 2 4 50 100
## Total 50 100 0 03.2 Gráfico de barra
plot(T10,xlab="Número de defectos",ylab="Número de piezas")
3.3 Gráfico escalonado
plot(ecdf(defectos),xlab="Número de defectos",ylab="Proporción de piezas")
## 4. Variable cuantitativa continua
Se utilizan datos referentes al tiempo que se require para realizar una tarea por parte de50 operarios.
tiempo<-c(21.3,25.8,26.7,28.6,29.3,24.2,25.0,19.7,24.7,26.2,27.1,28.3,26.1,
23.6,26.4,20.0,22.6,27.7,25.8,25.9,30.2,31.4,26.7,22.4,23.0,28.3,26.5,29.1,
32.6,24.6,26.9,27.1,27.2,28.2,25.8,24.2,25.5,26.6,27.7,27.3,21.6,22.4,25.4,
23.1,24.7,26.5,22.8,27.7,25.9,27.2)4.1 Distribución de frecuencias
min(tiempo)## [1] 19.7max(tiempo)## [1] 32.6c<-round(((max(tiempo)-min(tiempo))/6),1)
a<-seq(min(tiempo),6*c+min(tiempo),c)
T5<-table(cut(tiempo,breaks=c(a),include.lowest=TRUE,right=FALSE))
T5##
## [19.7,21.9) [21.9,24.1) [24.1,26.3) [26.3,28.5) [28.5,30.7) [30.7,32.9]
## 4 7 15 18 4 2nu<-c(T5)
porc<-round(nu/sum(nu)*100,1)
freac<-cumsum(nu)
poracu<-cumsum(freac)
t11<-sum(nu)
t12<-sum(porc)
Tabla6<-cbind(T5,porc,freac,poracu)
colnames(Tabla6)<-c("n.operar.","Por.operar.","n.ac.operar.","Por.ac.operar.")
Tabla6## n.operar. Por.operar. n.ac.operar. Por.ac.operar.
## [19.7,21.9) 4 8 4 4
## [21.9,24.1) 7 14 11 15
## [24.1,26.3) 15 30 26 41
## [26.3,28.5) 18 36 44 85
## [28.5,30.7) 4 8 48 133
## [30.7,32.9] 2 4 50 183Suma1<-cbind(t11,t12,NA ,NA)
rownames(Suma1)<-c("Total")
Tabla7<-rbind(Tabla6,Suma1)
Tabla7## n.operar. Por.operar. n.ac.operar. Por.ac.operar.
## [19.7,21.9) 4 8 4 4
## [21.9,24.1) 7 14 11 15
## [24.1,26.3) 15 30 26 41
## [26.3,28.5) 18 36 44 85
## [28.5,30.7) 4 8 48 133
## [30.7,32.9] 2 4 50 183
## Total 50 100 NA NA4.2 Histograma
h1<-hist(tiempo,breaks=c(a),xlab="Tiempo",ylab="n° de operarios",main="distribución",col="green",xaxt="n",
include.lowest=TRUE,right=FALSE,border="red",xlim=c(18,34))
axis(1,c(a))
4.3 Polígono de frecuencias
p<-c(h1$mids)
p1<-c(18.6,p,34.0)
k<-c(nu)
k1<-c(0,k,0)
data.frame(p1,k1)## p1 k1
## 1 18.6 0
## 2 20.8 4
## 3 23.0 7
## 4 25.2 15
## 5 27.4 18
## 6 29.6 4
## 7 31.8 2
## 8 34.0 0plot(p1,k1,type="l",lwd=2,xaxt="n",xlab="tiempo",ylab="número operarios")
axis(1,c(p1))
4.4 Histograma y polígono de frecuencias.
h1<-hist(tiempo,breaks=c(a),xlab="Tiempo",ylab="n° de operarios", main="distribución",col="green",xaxt="n",
include.lowest=TRUE,right=FALSE,border="red",xlim=c(18,34))
axis(1,c(a))
lines(p1,k1,type="l",lwd=2,xlab="tiempo",ylab="número operarios")
4.5 Ojiva
q1<-c(0,freac);q1## [19.7,21.9) [21.9,24.1) [24.1,26.3) [26.3,28.5) [28.5,30.7)
## 0 4 11 26 44 48
## [30.7,32.9]
## 50plot(a,q1,type="b",pch=16,xlab="Tiempo",ylab="número ac. operarios",lwd=2,xaxt="n")
axis(1,c(a))
4.6 Utilizando el paquete agricolae
ta<-table.freq(h1);ta## Lower Upper Main Frequency Percentage CF CPF
## 1 19.7 21.9 20.8 4 8 4 8
## 2 21.9 24.1 23.0 7 14 11 22
## 3 24.1 26.3 25.2 15 30 26 52
## 4 26.3 28.5 27.4 18 36 44 88
## 5 28.5 30.7 29.6 4 8 48 96
## 6 30.7 32.9 31.8 2 4 50 100ogive.freq(h1)
## x RCF
## 1 19.7 0.00
## 2 21.9 0.08
## 3 24.1 0.22
## 4 26.3 0.52
## 5 28.5 0.88
## 6 30.7 0.96
## 7 32.9 1.00
## 8 35.1 1.00h1<-hist(tiempo,breaks=c(a),xlab="Tiempo",ylab="n° de operarios", main="distribución",col="green",xaxt="n",
include.lowest=TRUE,right=FALSE,border="red",xlim=c(18,34))
axis(1,c(a))
polygon.freq(h1,lwd=2)
5. Tallos y hojas
stem(tiempo,scale=2)##
## The decimal point is at the |
##
## 19 | 7
## 20 | 0
## 21 | 36
## 22 | 4468
## 23 | 016
## 24 | 22677
## 25 | 04588899
## 26 | 124556779
## 27 | 11223777
## 28 | 2336
## 29 | 13
## 30 | 2
## 31 | 4
## 32 | 6- Boxplot
boxplot(tiempo,col="red",horizontal=T,notch=F,border="green")