---
title: "Data Visualizations: Box plots"
author: "Rubén F. Bustillo"
output:
flexdashboard::flex_dashboard:
orientation: columns
source_code: embed
vertical_layout: fill
theme: spacelab
---
```{r setup, include=FALSE}
# PACKAGES / LIBRARIES:
library(flexdashboard)
library(tidyverse)
library(gapminder)
library(ggthemes)
library(ggthemr)
# MAIN DATASET:
gapminder <- gapminder::gapminder
```
Sheet A
====================================================================================
Column
-----------------------------------------------------------------------
### `geom_boxplot()`
```{r}
# DATASET: GDP IN SELECTED COUNTRIES BY CONTINENT IN 2007
grafico_gdppercap <- gapminder %>%
filter(year == 2007) %>%
group_by(continent)
# GGTHEMR THEME: FLAT (Ful range of ggthemr themes in: https://rquer.netlify.com/ggplot_themes#themes-a)
ggthemr("flat")
# PLOT: BASIC BOXPLOT
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap,
fill = continent)) +
geom_boxplot() +
labs(title = "GDP per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita")
```
### `geom_boxplot(color = "blue")` | `coord_flip()`
```{r}
# PLOT: CHANGE COLOR TO BLUE:
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap,
fill = continent)) +
geom_boxplot(color = "blue") +
labs(title = "GDP per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita") +
coord_flip() +
scale_y_continuous(labels = scales::comma)
```
Column
-----------------------------------------------------------------------
### `scale_fill_brewer(palette = "Set2")` | `scale_x_discrete(limits = c("Europe", "Oceania", "Asia", "Americas", "Africa"))`
```{r}
#PLOT: PALETTE = SET2 . ORDER OF X-LABELS HAVE BEEN MODIFIED
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap,
fill = continent)) +
geom_boxplot() +
scale_fill_brewer(palette = "Set2") +
labs(title = "GDp per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita") +
scale_x_discrete(limits = c("Europe", "Oceania", "Asia", "Americas", "Africa"))
```
### `scale_fill_manual(values = c("lightblue", "green", "yellow", "red", "purple" ))`
```{r}
# PLOT: COLORS CHANGED MANUALLY AND LEGEND REMOVED
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap,
fill = continent)) +
geom_boxplot() +
scale_fill_manual(values = c("lightblue", "green", "yellow", "red", "purple" )) +
labs(title = "GDP percapita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita") +
theme(legend.position="none")
```
Column
-----------------------------------------------------------------------
### `geom_boxplot(fill="limegreen", alpha=0.2`
```{r}
# DEFINED BOXPLOT COLOR WITH FILL
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap)) +
geom_boxplot(fill="limegreen",
alpha=0.2) +
labs(title = "GDP percapita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita")
```
### `geom_boxplot(fill="cornflowerblue", color= "darkblue", alpha=0.2, notch = TRUE, notchwidth = 0.5, outlier.color = "firebrick1", outlier.fill = "red", outlier.size = 3)`
```{r}
# PLOT: WITH NOTCHS AND OUTLIERS HIGHLIGHTED
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap)) +
geom_boxplot(fill="cornflowerblue",
color= "darkblue",
alpha=0.2,
notch = TRUE,
notchwidth = 0.5,
outlier.color = "firebrick1",
outlier.fill = "red",
outlier.size = 4) +
labs(title = "GDP percapita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita")
```
Sheet B
====================================================================================
Column
-----------------------------------------------------------------------
### `grafico_gdppercap$type=factor(ifelse(grafico_gdppercap$continent=="Europe","A","B"))` | `labs(fill= NULL)`
```{r}
# PLOT WITH ONE CONTINENT HIGHLIGHTED
grafico_gdppercap$type=factor(ifelse(grafico_gdppercap$continent=="Europe","A","B"))
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap,
fill = type)) +
geom_boxplot() +
labs(title = "GDP per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita",
fill = NULL)
```
### `scale_fill_manual(values = c("cornflowerblue", "firebrick1")) + scale_alpha_manual(values = c(0.6, 0.6))` |
```{r}
# PLOT: COLORS SELECTED MANUALLY
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap,
fill = type,
alpha = type)) +
geom_boxplot() +
labs(title = "GDP per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita") +
scale_fill_manual(values = c("cornflowerblue", "firebrick1")) +
scale_alpha_manual(values = c(0.6, 0.6))
```
Column
-----------------------------------------------------------------------
### `ggplot(data=gapminder_b, aes (x=continent, y=lifeExp, fill=year))`
```{r}
# PLOT: COMPARING DATES (1952, 1977 AND 2007). LEGEND MOVED TO BOTTOM.
gapminder_b<- gapminder%>%
filter(year == 1952 | year == 1977 | year == 2007) %>%
mutate(year = factor(year))
ggplot(data=gapminder_b, aes (x=continent,
y=lifeExp,
fill=year)) +
geom_boxplot()+
labs(title = "Life expectancy of selected countries by continent",
x = "",
y = "Life Expectancy") +
theme(legend.position = "bottom",
legend.title = element_blank(),
plot.title = element_text(hjust = 0.5),
plot.subtitle = element_text(hjust = 0.5))
```
### `geom_boxplot(varwidth = TRUE, alpha = 0.3)` | `scale_y_continuous(labels = scales::dollar)`
```{r}
# PLOT: X-LABELS INDICATING THE NUMBER OF COUNTRIES IN EACH BOX AND BARS WIDTH INDICATING THE SIZE. X-AXIS INDICATING THE $ SIGN.
x_labels <- paste(levels(grafico_gdppercap$continent),"\n(N=", table(grafico_gdppercap$continent),")",sep="")
ggplot(grafico_gdppercap, aes(x = continent, y = gdpPercap, fill = continent)) +
geom_boxplot(varwidth = TRUE, alpha = 0.3) +
labs(title = "GDP per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita") +
scale_y_continuous(labels = scales::dollar) +
scale_x_discrete(labels=x_labels)
```
Column
-----------------------------------------------------------------------
### `x = reorder(continent, -pop)`
```{r}
# PLOT: REORDER CONTINENTS BY POPULATION (DESCENDING ORDER)
ggplot(grafico_gdppercap, aes(x = reorder(continent, -pop),
y = gdpPercap,
fill = continent)) +
geom_boxplot() +
labs(title = "GDP per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita")
```
### continuous variable: `aes(group = cut_width(lifeExp, 5))`
```{r}
# PLOT: DEALING WITH CONTINUOS VARIABLES (RANGES CREATED)
ggplot(grafico_gdppercap, aes(x=lifeExp,
y=gdpPercap)) +
geom_boxplot(fill="orange", aes(group = cut_width(lifeExp, 5))) +
labs(title = "GDP per capita by ranges of life expectancy",
subtitle = "year: 2007",
x = "life Expectancy ranges",
y = "GDP per capita") +
scale_x_continuous(breaks = seq(40, 80, 5))
```
Sheet C
=============================================================
Column
-----------------------------------------------------------------------
### `facet_wrap(~year, ncol=3)`
```{r, fig.height= 8, fig.width= 7}
# PLOT: FACETS AND X-LABELS CHANGED TO SHORT NAMES
ggplot(gapminder, aes(x=continent,
y=lifeExp)) +
geom_boxplot() +
facet_wrap(~year, ncol=3) +
labs(title = "Life expectancy by continent and year",
x = NULL,
y = "Life Expectancy") +
scale_x_discrete(labels = c("AFR", "AME", "ASI", "EUR", "OCE"))
```
Column
-----------------------------------------------------------------------
### `facet_wrap(~year, ncol=3, scale="free")`
```{r, fig.height= 7, fig.width= 7}
# PLOT: FACETS WITH SCALE= FREE AND X-LABELS ROTATED
ggplot(gapminder, aes(x=continent,
y=lifeExp)) +
geom_boxplot() +
facet_wrap(~year,
ncol=3,
scale="free")+
labs(title = "Life expectancy by continent and year",
x = NULL,
y = "Life Expectancy") +
theme(axis.text.x = element_text(size = rel(0.7),
angle = 45,
hjust = 1),
axis.text.y = element_text(size = rel(0.7)))
```
Sheet D
=============================================================
Column
-----------------------------------------------------------------------
### `facet_wrap(~year, ncol=2)` | `scale_fill_brewer(palette = "OrRd")`
```{r, fig.height= 8, fig.width= 7}
# PLOT: FACETS BY CONTINENT AND YEAR. COLOR PALETTE = OrRd
ggplot(gapminder_b, aes(x=year,
y=lifeExp,
fill=year)) +
geom_boxplot() +
facet_wrap(~continent,
ncol=2) +
labs(title = "Life expectancy by continent and year",
x = NULL,
y = "Life Expectancy") +
scale_fill_brewer(palette = "OrRd")
```
Column
-----------------------------------------------------------------------
### `facet_wrap(~year, ncol=2, scale="free")` | `scale_fill_brewer(palette = "OrRd")`
```{r, fig.height= 7, fig.width= 7}
# PLOT: FACETS WITH SCALE =FREE.
ggplot(gapminder_b, aes(x=year,
y=lifeExp,
fill=continent)) +
geom_boxplot() +
facet_wrap(~continent,
ncol=2,
scale="free") +
labs(title = "Life expectancy by continent and year",
x = NULL,
y = "Life Expectancy") +
scale_fill_brewer(palette = "OrRd")
```
Sheet E
==============================================================================
Column
-----------------------------------------------------------------------
### `stat_summary(fun.y = mean, geom = "point", shape = 20, size = 5, color = "brown", fill = "black")`
```{r}
# PLOT WITH STAT_SUMMARY INDICATING THE MEAN OF EACH BOX
ggplot(grafico_gdppercap, aes(x = continent, y = gdpPercap, fill = continent)) +
geom_boxplot() +
labs(title = "GDP per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita") +
stat_summary(fun.y = mean, geom = "point", shape = 20, size = 5, color = "brown", fill = "black") +
theme(legend.position = "none")
```
### `geom_point(position = "jitter", color= "grey50", alpha= 0.6)`
```{r}
# PLOT: ALL COUNTRIES WITH POSITION = JITTER. PANEL BACKGROUND REMOVED
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap,
fill = continent)) +
geom_boxplot() +
geom_point(position = "jitter", color= "grey40", alpha= 0.6)+
labs(title = "GDP per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita") +
theme(legend.position = "none",
panel.background = element_blank())
```
Column
-----------------------------------------------------------------------
### `qplot( x=continent , y=gdpPercap , data=grafico_gdppercap , geom=c("boxplot","jitter") , fill=continent)`
```{r}
# PLOT: USING QPLOT
qplot( x=continent , y=gdpPercap , data=grafico_gdppercap , geom=c("boxplot","jitter") , fill=continent)
```
### `geom_hline(yintercept= 11680.07, linetype = "dashed", color = "red", size = 1)`
```{r}
# mean(grafico_gdppercap$gdpPercap) = 11680
# PLOT: INDICATING THE TOTAL MEAN WITH GEOM_HLINE
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap,
fill = continent)) +
geom_boxplot() +
geom_point(position = "jitter", color= "grey40", alpha= 0.6)+
labs(title = "GDP per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita") +
theme(legend.position = "none",
panel.background = element_blank()) +
geom_hline(yintercept= 11680.07,
linetype = "dashed",
color = "red",
size = 1.2)
```
Column
-----------------------------------------------------------------------
### `geom_jitter(position = position_jitter(0.2), color= "grey40", alpha= 0.6)`
```{r}
#PLOT: ALL COUNTRIES WITH GEOM_JITTER
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap,
fill = continent)) +
geom_boxplot() +
geom_jitter(position = position_jitter(0.2),
color= "grey40",
alpha= 0.6)+
labs(title = "GDP per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita") +
theme(legend.position = "none",
panel.background = element_blank())
```
### `geom_dotplot(binaxis='y', stackdir='center', dotsize=1)`
```{r}
#PLOT: ALL COUNTRIES WITH GEOM_DOTPLOT
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap,
fill = continent)) +
geom_boxplot() +
geom_dotplot(binaxis='y',
stackdir='center',
dotsize=1)+
labs(title = "GDP per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita") +
theme(legend.position = "none",
panel.background = element_blank())
ggthemr_reset()
```
Sheet F
===================================================================
Column
-----------------------------------------------------------
### You can customize the graph to your liking using the function `theme()`
```{r, fig.width=8, fig.height=6}
# TEXT FONTS:
library(extrafont)
loadfonts(device = "win")
# PLOT: YOU CAN CUSTOMIZE THE GRAPH TO YOUR LIKING. AN EXAMPLE:
ggplot(grafico_gdppercap, aes(x = continent,
y = gdpPercap,
fill = continent)) +
geom_boxplot(size = 1) +
labs(title = "GDP per capita of selected countries by continent",
subtitle = "year: 2007",
x = "",
y = "GDP per capita\n (US Dollars)") +
scale_y_continuous(labels = scales::comma) +
theme(legend.position = "none",
plot.title=element_text(size = 18,
family= "Modern No. 20",
hjust = 0.5),
plot.subtitle = element_text(size = 14,
family = "Modern No. 20",
hjust = 0.5),
text = element_text(size = 16,
family="Modern No. 20"),
axis.line.x = element_line(size = 1.1,
colour = "black"),
axis.line.y = element_line(size = 1.1,
colour = "black"),
panel.grid.major = element_blank(),
panel.grid.minor = element_blank(),
panel.background = element_blank(),
axis.text.x=element_text(colour="black",
size = 16),
axis.text.y=element_text(colour="black",
size = 10))
```
