#install.packages("gapminder")
#install.packages("GGally")
suppressMessages(suppressWarnings(library(gapminder)))
suppressMessages(suppressWarnings(library(ggplot2)))
suppressMessages(suppressWarnings(library(GGally)))
data(gapminder)
head(gapminder)
## # A tibble: 6 × 6
## country continent year lifeExp pop gdpPercap
## <fct> <fct> <int> <dbl> <int> <dbl>
## 1 Afghanistan Asia 1952 28.8 8425333 779.
## 2 Afghanistan Asia 1957 30.3 9240934 821.
## 3 Afghanistan Asia 1962 32.0 10267083 853.
## 4 Afghanistan Asia 1967 34.0 11537966 836.
## 5 Afghanistan Asia 1972 36.1 13079460 740.
## 6 Afghanistan Asia 1977 38.4 14880372 786.
tail(gapminder)
## # A tibble: 6 × 6
## country continent year lifeExp pop gdpPercap
## <fct> <fct> <int> <dbl> <int> <dbl>
## 1 Zimbabwe Africa 1982 60.4 7636524 789.
## 2 Zimbabwe Africa 1987 62.4 9216418 706.
## 3 Zimbabwe Africa 1992 60.4 10704340 693.
## 4 Zimbabwe Africa 1997 46.8 11404948 792.
## 5 Zimbabwe Africa 2002 40.0 11926563 672.
## 6 Zimbabwe Africa 2007 43.5 12311143 470.
#Gráfico evolución esperanza de vida en Colombia
plot(lifeExp ~ year, data = gapminder[gapminder$country == "Colombia", ],
type = "b", xlab = "A\u00f1o", ylab = "Esperanza de Vida")
#Filtramos por el año 2007
gap <- gapminder[gapminder$year==2007,]
head(gap)
## # A tibble: 6 × 6
## country continent year lifeExp pop gdpPercap
## <fct> <fct> <int> <dbl> <int> <dbl>
## 1 Afghanistan Asia 2007 43.8 31889923 975.
## 2 Albania Europe 2007 76.4 3600523 5937.
## 3 Algeria Africa 2007 72.3 33333216 6223.
## 4 Angola Africa 2007 42.7 12420476 4797.
## 5 Argentina Americas 2007 75.3 40301927 12779.
## 6 Australia Oceania 2007 81.2 20434176 34435.
dim(gap)
## [1] 142 6
names(gap)
## [1] "country" "continent" "year" "lifeExp" "pop" "gdpPercap"
gap$ingreso <- as.factor(ifelse(gap$gdpPercap < 1035, 'Bajo',
ifelse(gap$gdpPercap < 4085, 'Medio Bajo',
ifelse(gap$gdpPercap < 12615, 'Medio Alto', 'Alto'))))
head(gap)
## # A tibble: 6 × 7
## country continent year lifeExp pop gdpPercap ingreso
## <fct> <fct> <int> <dbl> <int> <dbl> <fct>
## 1 Afghanistan Asia 2007 43.8 31889923 975. Bajo
## 2 Albania Europe 2007 76.4 3600523 5937. Medio Alto
## 3 Algeria Africa 2007 72.3 33333216 6223. Medio Alto
## 4 Angola Africa 2007 42.7 12420476 4797. Medio Alto
## 5 Argentina Americas 2007 75.3 40301927 12779. Alto
## 6 Australia Oceania 2007 81.2 20434176 34435. Alto
summary(gap)
## country continent year lifeExp
## Afghanistan: 1 Africa :52 Min. :2007 Min. :39.61
## Albania : 1 Americas:25 1st Qu.:2007 1st Qu.:57.16
## Algeria : 1 Asia :33 Median :2007 Median :71.94
## Angola : 1 Europe :30 Mean :2007 Mean :67.01
## Argentina : 1 Oceania : 2 3rd Qu.:2007 3rd Qu.:76.41
## Australia : 1 Max. :2007 Max. :82.60
## (Other) :136
## pop gdpPercap ingreso
## Min. :1.996e+05 Min. : 277.6 Alto :42
## 1st Qu.:4.508e+06 1st Qu.: 1624.8 Bajo :20
## Median :1.052e+07 Median : 6124.4 Medio Alto:42
## Mean :4.402e+07 Mean :11680.1 Medio Bajo:38
## 3rd Qu.:3.121e+07 3rd Qu.:18008.8
## Max. :1.319e+09 Max. :49357.2
##
summary(gap[,4:6])
## lifeExp pop gdpPercap
## Min. :39.61 Min. :1.996e+05 Min. : 277.6
## 1st Qu.:57.16 1st Qu.:4.508e+06 1st Qu.: 1624.8
## Median :71.94 Median :1.052e+07 Median : 6124.4
## Mean :67.01 Mean :4.402e+07 Mean :11680.1
## 3rd Qu.:76.41 3rd Qu.:3.121e+07 3rd Qu.:18008.8
## Max. :82.60 Max. :1.319e+09 Max. :49357.2
promedio=function(x){sum(x)/length(x)}
media_lifeexp_2007 <- promedio(gap$lifeExp)
media_gdpper_2007 <- promedio(gap$gdpPercap)
media_pop_2007 <- mean(gap$pop)
cbind(media_lifeexp_2007,media_gdpper_2007,media_pop_2007)
## media_lifeexp_2007 media_gdpper_2007 media_pop_2007
## [1,] 67.00742 11680.07 44021220
gdpTotal=gap$gdpPercap* gap$pop
sum(gdpTotal)/sum(gap$pop)
## [1] 9295.987
attach(gap)
mean(lifeExp)
## [1] 67.00742
sum(lifeExp)
## [1] 9515.054
length(lifeExp)
## [1] 142
quantile(lifeExp, c(.25, .5, .75))
## 25% 50% 75%
## 57.16025 71.93550 76.41325
min(lifeExp)
## [1] 39.613
max(lifeExp)
## [1] 82.603
tabla <- data.frame(
Medida = c("Media", "Suma", "Tamaño", "Cuartil 25%", "Mediana", "Cuartil 75%", "Mínimo", "Máximo"),
Valor = c(mean(lifeExp, na.rm = TRUE),
sum(lifeExp, na.rm = TRUE),
length(lifeExp),
quantile(lifeExp, 0.25, na.rm = TRUE),
quantile(lifeExp, 0.50, na.rm = TRUE),
quantile(lifeExp, 0.75, na.rm = TRUE),
min(lifeExp, na.rm = TRUE),
max(lifeExp, na.rm = TRUE))
)
print(tabla)
## Medida Valor
## 1 Media 67.00742
## 2 Suma 9515.05400
## 3 Tamaño 142.00000
## 4 Cuartil 25% 57.16025
## 5 Mediana 71.93550
## 6 Cuartil 75% 76.41325
## 7 Mínimo 39.61300
## 8 Máximo 82.60300
#Tabla de frecuencias
table(continent,ingreso)
## ingreso
## continent Alto Bajo Medio Alto Medio Bajo
## Africa 1 18 12 21
## Americas 6 0 15 4
## Asia 10 2 8 13
## Europe 23 0 7 0
## Oceania 2 0 0 0
tapply(lifeExp,continent,promedio)
## Africa Americas Asia Europe Oceania
## 54.80604 73.60812 70.72848 77.64860 80.71950
xtabs(lifeExp~continent+ingreso)
## ingreso
## continent Alto Bajo Medio Alto Medio Bajo
## Africa 56.735 910.571 727.653 1154.955
## Americas 461.333 0.000 1109.303 269.567
## Asia 784.191 105.897 566.998 876.954
## Europe 1812.380 0.000 517.078 0.000
## Oceania 161.439 0.000 0.000 0.000
xtabs(lifeExp~continent+ingreso)/table(continent,ingreso)
## ingreso
## continent Alto Bajo Medio Alto Medio Bajo
## Africa 56.73500 50.58728 60.63775 54.99786
## Americas 76.88883 73.95353 67.39175
## Asia 78.41910 52.94850 70.87475 67.45800
## Europe 78.79913 73.86829
## Oceania 80.71950
Datos07=data.frame(lifeExp,gap$pop,gdpPercap)
cov(Datos07)
## lifeExp gap.pop gdpPercap
## lifeExp 1.457578e+02 8.475088e+07 105368
## gap.pop 8.475088e+07 2.179208e+16 -105694667829
## gdpPercap 1.053680e+05 -1.056947e+11 165377988
cor(Datos07)
## lifeExp gap.pop gdpPercap
## lifeExp 1.00000000 0.04755312 0.6786624
## gap.pop 0.04755312 1.00000000 -0.0556756
## gdpPercap 0.67866240 -0.05567560 1.0000000
ggpairs(Datos07)
summary(glm(lifeExp~continent+gdpPercap))
##
## Call:
## glm(formula = lifeExp ~ continent + gdpPercap)
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 5.374e+01 9.284e-01 57.881 < 2e-16 ***
## continentAmericas 1.606e+01 1.662e+00 9.663 < 2e-16 ***
## continentAsia 1.267e+01 1.557e+00 8.137 2.27e-13 ***
## continentEurope 1.523e+01 1.956e+00 7.786 1.57e-12 ***
## continentOceania 1.665e+01 4.974e+00 3.348 0.00105 **
## gdpPercap 3.466e-04 5.674e-05 6.109 9.89e-09 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## (Dispersion parameter for gaussian family taken to be 43.22029)
##
## Null deviance: 20552 on 141 degrees of freedom
## Residual deviance: 5878 on 136 degrees of freedom
## AIC: 945.66
##
## Number of Fisher Scoring iterations: 2
# función básica
boxplot(gap$gdpPercap,
main = "Boxplot - GDP per cápita",
xlab = "GDP per cápita",
ylab = "Valor",
col = "pink",
border = "red",
horizontal = TRUE) #si se quiere vertical eliminar este argumento
