TrabajoClase28DeOctubre

# JUAN DIEGO BARRERO GONZALEZ
# Visualización de datos en R y con ggplot2

library(gapminder)
library(ggplot2)
library(DT)
library(hrbrthemes)
library(ggplotlyExtra)
library(plotly)

## 
## Attaching package: 'plotly'

## The following object is masked from 'package:ggplot2':
## 
##     last_plot

## The following object is masked from 'package:stats':
## 
##     filter

## The following object is masked from 'package:graphics':
## 
##     layout

library(knitr)

str(gapminder)

## tibble [1,704 × 6] (S3: tbl_df/tbl/data.frame)
##  $ country  : Factor w/ 142 levels "Afghanistan",..: 1 1 1 1 1 1 1 1 1 1 ...
##  $ continent: Factor w/ 5 levels "Africa","Americas",..: 3 3 3 3 3 3 3 3 3 3 ...
##  $ year     : int [1:1704] 1952 1957 1962 1967 1972 1977 1982 1987 1992 1997 ...
##  $ lifeExp  : num [1:1704] 28.8 30.3 32 34 36.1 ...
##  $ pop      : int [1:1704] 8425333 9240934 10267083 11537966 13079460 14880372 12881816 13867957 16317921 22227415 ...
##  $ gdpPercap: num [1:1704] 779 821 853 836 740 ...

datatable(gapminder) # crea tabla interactiva para visualizar base de datos

## Gráficos paso a paso ##

ggplot(data=gapminder) # crear objeto ggplot

#### atributos estéticos ####

#Elegimos las variables gdpPercap, lifeExp y continent,
# donde la primera estará asignada a ‘x’, la segunda a ‘y’ y 
# la última al atributo color

p <- ggplot(data = gapminder,mapping = aes(x = gdpPercap,y = lifeExp, color=continent))
p

#### Función Geom ####

# Queremos graficar un diagrama de dispersión o scatterplot, entonces elegimos 
# la función geom_point y le pasamos como argumento size= 3, con esto le 
# indicamos a ggplot el tamaño de los puntos que se aplicará al gráfico.

p + geom_point(size=3)

#### Sistemas de coordenadas y escalas ####

# se grafica con escala logarítmica para que los datos estén mejores distribuidos

p <- ggplot(data = gapminder,mapping = aes(x = gdpPercap,y = lifeExp,color = continent)) +
  geom_point(size=3) +
  coord_cartesian() +
  scale_x_log10(labels= scales::dollar)

p

#### Paleta de colores ####

# utilizamos la función scale_color_brewer con Set2

pSet2 <- ggplot(data = gapminder,mapping = aes(x = gdpPercap,y = lifeExp,color= continent)) + 
  geom_point(size=3) +
  scale_color_brewer(palette="Set2") +
  coord_cartesian() +
  scale_x_log10(labels= scales::dollar) +
  labs(x = "Ingreso (GDP) Per Cápita", y = "Esperanza de vida",
       title = "Crecimiento económico y esperanza de vida",
       subtitle = "Los puntos se representan por año-país",
       caption = "DataSource: Gapminder - Link: https://www.gapminder.org", color=" ") +
  guides(color = guide_legend(override.aes = list(size = 5)))

pSet2

# utilizamos la función scale_color_brewer con Dark2

pdark2 <- ggplot(data = gapminder,mapping = aes(x = gdpPercap,y = lifeExp,color = continent)) + 
  geom_point(size=3)+
  scale_color_brewer(palette="Dark2") +
  coord_cartesian() +
  scale_x_log10(labels= scales::dollar) +
  labs(x = "Ingreso (GDP) Per Cápita", y = "Esperanza de vida",
       title = "Crecimiento económico y esperanza de vida",
       subtitle = "Los puntos se representan por año-país",
       caption = "DataSource: Gapminder - Link: https://www.gapminder.org", color=" ") +
  guides(color = guide_legend(override.aes = list(size = 5)))

pdark2 

# Ahora utilizamos una escala manual de colores, donde especificamos los colores 
# elegidos y las etiquetas de cada uno de ellos

pmanual <- ggplot(data = gapminder,mapping = aes(x = gdpPercap,y = lifeExp,color = continent)) + 
  geom_point(size=3) +
  scale_color_manual(values = c("#41b6a6", "#f6e37c",   "#f5a26b","#51b8df","#713580"), labels = c("Africa", "América","Asia",  "Europa", "Oceanía")) +
  coord_cartesian() +
  scale_x_log10(labels= scales::dollar) +
  labs(x = "Ingreso (GDP) Per Cápita", y = "Esperanza de vida",
       title = "Crecimiento económico y esperanza de vida",
       subtitle = "Los puntos se representan por año-país",
       caption = "DataSource: Gapminder - Link: https://www.gapminder.org", color=" ") +
  guides(color = guide_legend(override.aes = list(size = 5)))

pmanual

#### Temas ####

# Para cambiar la apariencia del gráfico podemos agregar otra capa con un tema 
# en particular, existen temas que vienen ya incluidos en ggplot2


## Theme_gray
p_theme_bw <- ggplot(data = gapminder,mapping = aes(x = gdpPercap,y = lifeExp,color = continent)) + 
  geom_point(size=3)+
  scale_color_manual(values = c("#41b6a6", "#f6e37c",   "#f5a26b","#51b8df","#713580"), labels = c("Africa", "América","Asia",  "Europa", "Oceanía")) +
  coord_cartesian() +
  scale_x_log10(labels= scales::dollar) +
  labs(x = "Ingreso (GDP) Per Cápita", y = "Esperanza de vida",
       title = "Crecimiento económico y esperanza de vida",
       subtitle = "Los puntos se representan por año-país",
       caption = "DataSource: Gapminder - Link: https://www.gapminder.org", color=" ") +
  guides(color = guide_legend(override.aes = list(size = 5))) +
  theme_grey()

p_theme_bw

## Theme_classic
ptheme_classic <- ggplot( data = gapminder,mapping = aes(x = gdpPercap,y = lifeExp,color = continent)) + 
  geom_point(size=3) +
  scale_color_manual(values = c("#41b6a6", "#f6e37c","#f5a26b","#51b8df","#713580"), labels = c("Africa", "América","Asia",  "Europa", "Oceanía")) +
  coord_cartesian() +
  scale_x_log10(labels= scales::dollar) +
  labs(x = "Ingreso (GDP) Per Cápita", y = "Esperanza de vida",
       title = "Crecimiento económico y esperanza de vida",
       subtitle = "Los puntos se representan por año-país",
       caption = "DataSource: Gapminder - Link: https://www.gapminder.org", color=" ") +
  guides(color = guide_legend(override.aes = list(size = 5))) +
  theme_classic()

ptheme_classic

#### customizacion de theme ####

# definiremos dos parámetros text_size y margin_size, que luego utilizaremos
# para modificar el tamaño del título, subtítulo y leyenda.

# Con legend.position= "bottom" cambiamos la posición de la leyenda 
# correspondiente a continente, en este caso, le indicamos a R que la leyenda 
# estará ubicada en la parte inferior del gráfico.

# Con legend.key= element_rect(fill= 'NA') eliminamos el recuadro gris de las leyendas.

# Con legend.text= element_text(color= "#2c204d", size= text_size) 
# especificamos el color y el tamaño del texto de la leyenda.

# Con plot.title= element_text(size = text_size * 1.8,family= "Garamond", 
# hjust = 0.5,vjust = 1,colour = "#2c204d", ...) 
# especificamos el tamaño, fuente, ubicación y color del título.


# Con plot.subtitle= element_text(size = text_size * 1.3, family= "Garamond", 
# hjust = 0.5,vjust = 1,colour = "#2c204d", ...) 
# especificamos el tamaño, fuente, ubicación y color del título.

# Con plot.caption= element_text(size = 11,family = "Garamond", hjust = 1, 
# vjust = 1, colour = "#2c204d",...) 
# especificamos el tamaño, fuente, ubicación y color del título.

# Para no repetir los mismos valores de tamaño del texto en el theme, 
# defino un parámetro: text_size y una variable: margin_size.

text_size <-16   # tamaño base del texto
margin_size <- text_size/2  #de los margenes

pTheme_customizado <- ggplot(data=gapminder, mapping=aes(x= gdpPercap, y= lifeExp, color= continent)) +
  geom_point(size=3,alpha=0.6)+
  scale_x_log10(labels= scales::dollar) +
  scale_color_manual(values= c("#41b6a6", "#f6e37c","#f5a26b","#51b8df","#713580"), labels= c("Africa", "America", "Asia","Europa", "Oceanía")) +
  labs(x="Ingreso (PBI) Per Capita", y="Esperanza de vida en años",
       title ="Crecimiento económico y esperanza de vida", 
       subtitle ="Los puntos se representan por año-país", 
       caption = "DataSource: Gapminder- Link: https://www.gapminder.org.", color= '')+
  guides(color = guide_legend(override.aes = list(size = 5))) +
  theme_light() +
  theme(legend.position="bottom", legend.key= element_rect(fill='NA'),
        legend.text= element_text(color="#2c204d", 
                                  size= text_size), 
        legend.justification = "center",
        
        plot.title = element_text(size=(text_size * 1.8),family ="Garamond",    
                                  hjust = 0.5,vjust = 1,
                                  colour = "#2c204d", #
                                  face = 'bold', 
                                  margin = margin(b = margin_size * 1.2)),
        plot.subtitle = element_text(size = text_size * 1.3,
                                     family ="Garamond", hjust = 0.5, vjust = 1, 
                                     colour = "#2c204d",
                                     margin = margin(b = margin_size * 0.9)),
        plot.caption = element_text(size = 11,family ="Garamond",
                                    hjust = 1, vjust = 1,
                                    colour = "#2c204d", 
                                    face='bold',
                                    margin = margin(t = margin_size * 0.9)),
        panel.background = element_rect(fill = "white"),
        panel.grid.major = element_line(color = "gray90", size = 0.5),
        panel.grid.minor = element_line(color = "gray90", size = 0.25))

## Warning: The `size` argument of `element_line()` is deprecated as of ggplot2 3.4.0.
## ℹ Please use the `linewidth` argument instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

pTheme_customizado

## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family
## not found in Windows font database

## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family
## not found in Windows font database
## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family
## not found in Windows font database

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database

## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## font family not found in Windows font database
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## font family not found in Windows font database
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## font family not found in Windows font database

#### ¿Cómo guardamos lo hecho hasta aquí? ####

# Utilizamos la sentencia ggsave ("nombre.extension", height= n, width= m, 
# units= "in", type= ' '), como argumento le pasamos el nombre del gráfico 
# con la extensión deseada (png, pdf, svg, entre otras), dimensiones del 
# gráfico con height y width o con dpiy unidades con units en “in”,“cm” o “mm”).

ggsave("grafico_scatterplot1.png", height = 8, width = 10, units = "in", type= 'cairo')


#### Agregar una nueva capa ####

# El objetivo es agregar al gráfico, una curva suavizada correspondiente a una 
# función de regresión, entonces vamos a utilizar la funcion geom_smooth.

# geom_smooth(method = "gam")
# geom_smooth(method = "lm")
# geom_smooth(method = "glm")
# geom_smooth(method = "loess")


text_size <-14              # tamaño base del texto
margin_size <- text_size/2  # para el margen

# Asignamos el gráfico `ggplot' al objeto p_capa_smooth
p_capa_smooth <- ggplot(data=gapminder, mapping=aes(x= gdpPercap, y= lifeExp)) +
  geom_point(aes(color=continent),size=3,alpha=0.6) +
  geom_smooth(method = 'gam', col = "#2c204d", size = 0.7,
              fill = "gray60", alpha = 0.2) +
  scale_x_log10(labels= scales::dollar) +
  scale_color_manual(values= c("#41b6a6", "#f6e37c","#f5a26b","#51b8df","#713580"), labels= c("Africa", "America", "Asia","Europa", "Oceanía")) +
  labs(x="Ingreso (PBI) Per Capita", y="Esperanza de vida en años",
       title ="Crecimiento económico y esperanza de vida",
       subtitle ="Los puntos se representan por año-país" , 
       caption = "DataSource: Gapminder- Link: https://www.gapminder.org.", 
       color= '', fill="Población") +
  guides(color = guide_legend(override.aes = list(size = 5))) +
  theme_light() +
  theme(legend.position="bottom", legend.key= element_rect(fill='NA'),
        legend.text= element_text(color="#2c204d", 
                                  size= text_size), 
        legend.justification = "center",
        plot.title = element_text(size=(text_size * 1.8),family ="Garamond",    
                                  hjust = 0.5,vjust = 1,
                                  colour = "#2c204d", #
                                  face = 'bold', 
                                  margin = margin(b = margin_size * 1.2)),
        plot.subtitle = element_text(size = text_size * 1.3,
                                     family ="Garamond", hjust = 0.5, vjust = 1, 
                                     colour = "#2c204d",
                                     margin = margin(b = margin_size * 0.9)),
        plot.caption = element_text(size = 11,family ="Garamond",
                                    hjust = 1, vjust = 1,
                                    colour = "#2c204d", 
                                    face='bold',
                                    margin = margin(t = margin_size * 0.9)),
        panel.background = element_rect(fill = "white"),
        panel.grid.major = element_line(color = "gray90", size = 0.5),
        panel.grid.minor = element_line(color = "gray90", size = 0.25))

## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.

# llamamos al objeto p_capa_smooth
p_capa_smooth

## `geom_smooth()` using formula = 'y ~ s(x, bs = "cs")'

## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family
## not found in Windows font database

## Warning in grid.Call(C_stringMetric, as.graphicsAnnot(x$label)): font family
## not found in Windows font database

## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database
## Warning in grid.Call(C_textBounds, as.graphicsAnnot(x$label), x$x, x$y, : font
## family not found in Windows font database

## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## font family not found in Windows font database
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## font family not found in Windows font database
## Warning in grid.Call.graphics(C_text, as.graphicsAnnot(x$label), x$x, x$y, :
## font family not found in Windows font database

# Guardamos el gráfico  con ggsave
ggsave("grafico_smooth.png", height = 8, width = 10, units = "in", type='cairo')

## `geom_smooth()` using formula = 'y ~ s(x, bs = "cs")'

#### Facetas ####

# Vamos a separar por columnas con facet_wrap teniendo en cuenta la variable continente

p_facet <- ggplot(data=gapminder, mapping=aes(x= gdpPercap, y= lifeExp, color=continent))+
  geom_point(size=3,alpha=0.6)+
  geom_smooth(method = 'gam', col = "#2c204d", size = 0.7,
              fill = "gray60", alpha = 0.2)+
  scale_x_log10(labels= scales::dollar)+
  scale_color_manual(values= c("#41b6a6", "#f6e37c","#f5a26b","#51b8df","#713580"), labels= c("Africa", "America", "Asia","Europa", "Oceanía"))+
  labs(x="Ingreso (PBI) Per Capita", y="Esperanza de vida en años",
       title ="Crecimiento económico y esperanza de vida", 
       subtitle ="Los puntos se representan por año-país" , 
       caption = "DataSource: Gapminder- Link: https://www.gapminder.org.", color= '')+
  guides(color = guide_legend(override.aes = list(size = 5)))+
  theme_bw()+
  theme(legend.position="bottom")+
  facet_wrap(~continent, ncol = 2, scales="free")

p_facet

## `geom_smooth()` using formula = 'y ~ s(x, bs = "cs")'

# Guardamos el gráfico
ggsave("grafico_facet.png", height = 8, width = 10, units = "in", type='cairo')

## `geom_smooth()` using formula = 'y ~ s(x, bs = "cs")'

#### Themes personalizados con el paquete hrbrthemes ####

# El paquete hrbrthemes ofrece varias opciones de temas para aplicar a un gráfico, algunas son:
  
# theme_ipsum()
# theme_ft_rc()
# theme_ipsum_ps()
# theme_ipsum_rc()
# theme_ipsum_tw()
# Entonces, en lugar de utilizar un theme customizado, 
# eligiremos la última opción theme_ipsum_tw(), así obtendremos el siguiente gráfico:


p_facet_ipsum_tw <- ggplot(data=gapminder, mapping=aes(x= gdpPercap, y= lifeExp, color=continent))+
  geom_point(size=3,alpha=0.6)+
  scale_x_log10(labels= scales::dollar)+
  scale_color_manual(values= c("#41b6a6", "#f6e37c","#f5a26b","#51b8df","#713580"), labels= c("Africa", "America", "Asia","Europa", "Oceanía"))+
  labs(x="Ingreso (PBI) Per Capita", y="Esperanza de vida en años",
       title ="Crecimiento económico y esperanza de vida",
       subtitle ="Los puntos se representan por año-país" , 
       caption = "DataSource: Gapminder- Link: https://www.gapminder.org.", color= '')+
  guides(color = guide_legend(override.aes = list(size = 5)))+
  theme(legend.position="bottom")+
  facet_wrap(~continent, ncol = 2, scales="free") 

p_facet_ipsum_tw

# Guardamos el gráfico
ggsave("grafico_facet_ipsum_tw.png", height = 8, width = 10, units = "in", type='cairo')

#### Gráficos combinados con el Paquete patchwork ####

text_size <-16   # tamaño base del texto

p1 <- ggplot(data=gapminder, mapping=aes(x= gdpPercap, y= lifeExp))+
  geom_point(aes(color=continent),size=3,alpha=0.6)+
  geom_smooth(method = 'gam', col = "#2c204d", size = 0.7,
              fill = "gray60", alpha = 0.2)+
  scale_x_log10(labels= scales::dollar)+
  scale_color_manual(values= c("#41b6a6", "#f6e37c","#f5a26b","#51b8df","#713580"), labels= c("Africa", "America", "Asia","Europa", "Oceanía"))+
  labs(x="Ingreso (PBI) Per Capita", y="Esperanza de vida en años", color= '')+
  guides(color = guide_legend(override.aes = list(size = 5)))+
  theme(legend.position="bottom", legend.key= element_rect(fill='NA'),
        legend.text= element_text(color="#2c204d", size= text_size), 
        legend.justification = "center",
        panel.background = element_rect(fill = "white"),
        panel.grid.major = element_line(color = "gray90", size = 0.5),
        panel.grid.minor = element_line(color = "gray90", size = 0.25))

p1

## `geom_smooth()` using formula = 'y ~ s(x, bs = "cs")'

p2 <-ggplot(data=gapminder, mapping=aes(x= gdpPercap, y= lifeExp, color=continent))+
  geom_point(size=3,alpha=0.6)+
  scale_x_log10(labels= scales::dollar)+
  scale_color_manual(values= c("#41b6a6", "#f6e37c","#f5a26b","#51b8df","#713580"), labels= c("Africa", "America", "Asia","Europa", "Oceanía"))+
  labs(x="", y="Esperanza de vida en años", color= '')+
  guides(color = guide_legend(override.aes = list(size = 5)))+
  theme(legend.position="none", axis.text.y = element_text(size = 12))+
  # con legend.position= "none", elimino las leyenda correspondiente a la variable de continente 
  facet_wrap(~continent, ncol = 2, scales="free") # 
p2

ggsave("grafico_p2.png", height = 8, width = 10, units = "in", type='cairo')

# Podemos elegir combinar los dos figuras así:
  
# p1 + p2, una figura a continuación de la otra
# p1 / p2, la primera figura en la parte superior y la segunda en la parte inferior.
# Con plot_annotation() agrego título, subtítulo y caption al gráfico 
# combinado y con el theme defino el tamaño de las etiquetas.


#### Gráficos interactivos con plotly ####

# Utilizamos la librería plotly para convertir gráficos estáticos generados 
# con ggplot2 en gráficos interactivos.
# Con la sentencia ggplotly(p_capa_smooth, tooltip = "text") convierto 
# la figura anterior en una interactiva y con ‘tooltip = “text”’ le indicó que 
# me muestre las variables con el formato especificado anteriormente.

p_facet_dark <- ggplot(data=gapminder, mapping=aes(x= gdpPercap, y= lifeExp, color=continent, text = paste('<b>Continente:</b> ' , continent,'<br />','<b>Ingreso per cápita:</b> ','$', round(gdpPercap,2),'<br>', '<b>Expectativa de vida:</b> ', round(lifeExp,1)))) +
  geom_point(size=3,alpha=0.6)+
  scale_x_log10(labels= scales::dollar)+
  scale_color_manual(values= c("#41b6a6", "#f6e37c","#f5a26b","#51b8df","#713580"), labels= c("Africa", "America", "Asia","Europa", "Oceanía"))+
  labs(x="Ingreso (PBI) Per Capita", y="Esperanza de vida en años",
       title ="Crecimiento económico y esperanza de vida", subtitle ="Los puntos se representan por año-país" , caption = "DataSource: Gapminder- Link: https://www.gapminder.org.", color= '')+
  guides(color = guide_legend(override.aes = list(size = 5)))+
  theme_ft_rc()+
  theme(legend.position="bottom")+
  facet_wrap(~continent, ncol = 2, scales="free") 



ggplotly(p_facet_dark, tooltip = "text")