orangeec <- read.csv("orangeec.csv")
summary(orangeec)
## Country GDP.PC GDP.US.bill GDP.Growth..
## Length:17 Min. : 5600 Min. : 13.7 Min. :0.800
## Class :character 1st Qu.: 8300 1st Qu.: 37.1 1st Qu.:2.000
## Mode :character Median :13300 Median : 75.7 Median :2.800
## Mean :14053 Mean : 188693.0 Mean :2.959
## 3rd Qu.:19900 3rd Qu.: 309.2 3rd Qu.:4.200
## Max. :25400 Max. :2055000.0 Max. :5.400
##
## Services...GDP Creat.Ind...GDP Inflation Unemployment
## Min. :50.00 Min. :1.000 Min. : 0.400 Min. : 2.300
## 1st Qu.:56.90 1st Qu.:2.000 1st Qu.: 1.600 1st Qu.: 5.500
## Median :62.20 Median :2.600 Median : 3.400 Median : 6.700
## Mean :62.64 Mean :3.291 Mean : 4.365 Mean : 6.794
## 3rd Qu.:64.90 3rd Qu.:3.950 3rd Qu.: 4.300 3rd Qu.: 8.100
## Max. :82.00 Max. :7.400 Max. :25.700 Max. :11.800
## NA's :6
## X..pop.below.poverty.line Internet.penetration...population Median.age
## Min. : 4.20 Min. :38.20 Min. :22.10
## 1st Qu.:21.70 1st Qu.:57.70 1st Qu.:25.70
## Median :25.70 Median :69.70 Median :28.20
## Mean :27.65 Mean :68.42 Mean :28.28
## 3rd Qu.:32.70 3rd Qu.:79.90 3rd Qu.:31.30
## Max. :59.30 Max. :93.10 Max. :35.00
##
## X..pop.25.54 Education.invest...GDP
## Min. :34.12 Min. :2.800
## 1st Qu.:39.23 1st Qu.:4.400
## Median :40.19 Median :5.000
## Mean :39.88 Mean :5.082
## 3rd Qu.:41.08 3rd Qu.:5.900
## Max. :44.03 Max. :7.400
##
pairs(orangeec[,6:10])
library(ggplot2)
## Warning: package 'ggplot2' was built under R version 4.5.3
ggplot() +
geom_histogram(data=orangeec,
aes(x=Internet.penetration...population), # queremos ver la variable PIB PER CAPITA
fill="red", # barritas de color azul
color="yellow", # y un contorno rojo
binwidth = 5) + # valor en porcentaje (vamos de a 5% por barra)
labs(x="penetración de internet como (%) de la población",
y="cantidad de paises",
title="penetración de internet en paises de latam") +
xlim(30,100) + # numeramos del 30% al 100%
ylim(0,4) + # ponemos en el eje Y valores del 0 al 4
scale_x_continuous(breaks = seq(30,100,by=5)) + # le colocamos valores a cada barras (que van del 30% al 100%) cada 5%
theme(legend.position = "none") +
theme(panel.background = element_blank(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank())
## Scale for x is already present.
## Adding another scale for x, which will replace the existing scale.
library(dplyr)
## Warning: package 'dplyr' was built under R version 4.5.3
##
## 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
economy <- mean(orangeec$GDP.PC)
economy
## [1] 14052.94
orangeec <- orangeec %>%
mutate(strong_economy = ifelse(GDP.PC < economy,
"Por debajo del promedio en PIB per cápita",
"Sobre-Arriba promedio en PIB per cápita"))
ggplot(orangeec,
aes(x=strong_economy, y=Creat.Ind...GDP, fill = strong_economy)) +
geom_boxplot(alpha=0.4) +
labs(x="Tipo de país", y="Aporte economia naranja al PIB",
title="Aporte economia naranja en PIB paises latam con alto y bajo PIB per cápita")+
theme(panel.background = element_blank(),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank())
## Warning: Removed 6 rows containing non-finite outside the scale range
## (`stat_boxplot()`).
El boxplot indica que los paises por encima del promedio del PIB tienen una dispersión mucho mas alta en relación a los aportes de la economía naranja al PIB del país. CUIDADO, contrastar con desviación estándar.