library(ggplot2)
library(gapminder)
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 ...
summary(gapminder)
## country continent year lifeExp
## Afghanistan: 12 Africa :624 Min. :1952 Min. :23.60
## Albania : 12 Americas:300 1st Qu.:1966 1st Qu.:48.20
## Algeria : 12 Asia :396 Median :1980 Median :60.71
## Angola : 12 Europe :360 Mean :1980 Mean :59.47
## Argentina : 12 Oceania : 24 3rd Qu.:1993 3rd Qu.:70.85
## Australia : 12 Max. :2007 Max. :82.60
## (Other) :1632
## pop gdpPercap
## Min. :6.001e+04 Min. : 241.2
## 1st Qu.:2.794e+06 1st Qu.: 1202.1
## Median :7.024e+06 Median : 3531.8
## Mean :2.960e+07 Mean : 7215.3
## 3rd Qu.:1.959e+07 3rd Qu.: 9325.5
## Max. :1.319e+09 Max. :113523.1
##
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.
gapminder
## # A tibble: 1,704 × 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.
## 7 Afghanistan Asia 1982 39.9 12881816 978.
## 8 Afghanistan Asia 1987 40.8 13867957 852.
## 9 Afghanistan Asia 1992 41.7 16317921 649.
## 10 Afghanistan Asia 1997 41.8 22227415 635.
## # ℹ 1,694 more rows
#exploring using various Alpha values
library(ggplot2)
ggplot(data = gapminder, aes(x = lifeExp, fill = continent)) +
geom_density(alpha = 0.5) +
labs(title = "Density Plot of Life Expectancy by Continent",
x = "Life Expectancy",
y = "Density") +
theme_minimal()
#exploring using various Alpha values
ggplot(data = gapminder, aes(x = lifeExp, fill = continent)) +
geom_density(alpha = 0.8) +
labs(title = "Density Plot of Life Expectancy by Continent",
x = "Life Expectancy",
y = "Density") +
theme_minimal()
#exploring using various Alpha values
ggplot(data = gapminder, aes(x = lifeExp, fill = continent)) +
geom_density(alpha = 0.2) +
labs(title = "Density Plot of Life Expectancy by Continent",
x = "Life Expectancy",
y = "Density") +
theme_minimal()
#Explore the relationship between life expectancy and GDP with a scatterplot
ggplot(data =gapminder, aes(x = gdpPercap, y = lifeExp)) +
geom_point() +
labs(title = "Scatterplot of Life Expectancy vs. GDP",
x = "GDP per Capita",
y = "Life Expectancy") +
theme_minimal()
#Explore the relationship between life expectancy and GDP with a scatterplot(added colors for better visualization)
ggplot(data = gapminder, aes(x = gdpPercap, y = lifeExp,color=year)) +
geom_point() +
labs(title = "Scatterplot of Life Expectancy vs. GDP",
x = "GDP per Capita",
y = "Life Expectancy") +
theme_minimal()
#Add scale_x_log10() using the “+” operator.
ggplot(data = gapminder, aes(x = gdpPercap, y = lifeExp,color=continent)) +
geom_point() +scale_x_log10()
labs(title = "Scatterplot of Life Expectancy vs. GDP",
x = "GDP per Capita",
y = "Life Expectancy") +
theme_minimal()
## NULL
# change the circles to semi-transparent using the alpha variable.
ggplot(data = gapminder, aes(x = gdpPercap, y = lifeExp)) +
geom_point(alpha = 0.5) + # Add alpha for transparency
scale_x_log10() +
labs(title = "Scatterplot of Life Expectancy vs. GDP",
x = "GDP per Capita",
y = "Life Expectancy") +
theme_minimal()
#Option 3: customize the theme for the plot.
library(ggplot2)
# Create a custom theme for the plot
custom_theme <- theme_minimal() +
theme(
plot.title = element_text(size = 22, face = "bold"),
axis.title.x = element_text(size = 12),
axis.title.y = element_text(size = 14),
axis.text.x = element_text(size = 15),
axis.text.y = element_text(size = 13),
legend.title = element_text(size = 18),
legend.text = element_text(size = 10)
)
# Create the scatterplot with the custom theme
ggplot(data = gapminder, aes(x = gdpPercap, y = lifeExp, color = continent)) +
geom_point(alpha = 0.5) +
scale_x_log10() +
labs(title = "Scatterplot of Life Expectancy vs. GDP",
x = "GDP per Capita",
y = "Life Expectancy") +
custom_theme
library(ggplot2)
# Create a scatterplot of life expectancy vs. GDP with color by continent and alpha
ggplot(data = gapminder, aes(x = gdpPercap, y = lifeExp, color = continent)) +
geom_point(alpha = 0.5) +
scale_x_log10(
breaks = c(100, 1000, 10000, 100000), # Define custom breaks
labels = scales::comma_format(scale = 0.001) # Format labels as thousands
) +
labs(title = "Scatterplot of Life Expectancy vs. GDP",
x = "GDP per Capita",
y = "Life Expectancy") +
theme_minimal()
# Try using encode the size of the point by variable “pop”.
library(ggplot2)
ggplot(data = gapminder, aes(x = gdpPercap, y = lifeExp, color = continent, size = pop)) +
geom_point(alpha = 0.5) +
scale_x_log10(
breaks = c(100, 1000, 10000, 100000), # Define custom breaks
labels = scales::comma_format(scale = 0.001) # Format labels as thousands
) +
labs(title = "Scatterplot of Life Expectancy vs. GDP (Size by Population)",
x = "GDP per Capita",
y = "Life Expectancy") +
theme_minimal()
