library(ggplot2)
library(dplyr)
##
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
##
## filter, lag
## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union
library(scales)
library(gapminder)
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(gganimate)
library(ggrepel)
# This is an Histogram showing the distribution of Life Expectancy in the dataset
ggplot(gapminder, aes(x=lifeExp))+
geom_histogram(binwidth = 5, fill = "skyblue", color = "black") +
theme_minimal()+
labs(title = "Distribution of Life Expectancy", x = "Life Expectancy", y = "Count")
# This is a Density plot showing a view of life expectancy distribution
ggplot(gapminder, aes(x = lifeExp)) +
geom_density(fill = "lightgreen", alpha = 0.5) +
theme_minimal() +
labs(title = "Density Plot of Life Expectancy", x = "Life Expectancy", y = "Density")
# This is a boxplot showing the continental expectancy
ggplot(gapminder, aes(x = continent, y = lifeExp)) +
geom_boxplot(fill = "lightcoral", color = "black") +
theme_minimal() +
labs(title = "Life Expectancy by Continent", x = "Continent", y = "Life Expectancy")
# This is a scatterplot showing the GDP per capita
ggplot(gapminder, aes(x = gdpPercap, y = lifeExp, color = continent)) +
geom_point(alpha = 0.6) +
scale_x_log10() + # Log scale for better visibility
geom_smooth(method = "lm") + # Adds a linear regression line
theme_minimal() +
labs(title = "Life Expectancy vs. GDP Per Capita",
x = "GDP Per Capita (Log Scale)",
y = "Life Expectancy")
## `geom_smooth()` using formula = 'y ~ x'
# this is a Line Plot - Trend over time
ggplot(gapminder, aes(x = year, y = lifeExp, group = country, color = continent)) +
geom_line(alpha = 0.5) +
theme_minimal() +
labs(title = "Life Expectancy Trends Over Time", x = "Year", y = "Life Expectancy")
# Bar chart - Average GDP per capita by continent
gapminder_summary <- gapminder %>%
group_by(continent) %>%
summarise(avg_gdp = mean(gdpPercap))
ggplot(gapminder_summary, aes(x = continent, y = avg_gdp, fill = continent)) +
geom_bar(stat = "identity") +
theme_minimal() +
labs(title = "Average GDP Per Capita by Continent", x = "Continent", y = "Average GDP Per Capita")
# 3D Scatter Plot - GDP Per Capita, Life Exp and Population
fig <- plot_ly(gapminder, x = ~gdpPercap, y = ~lifeExp, z = ~pop, color = ~continent, type = "scatter3d", mode = "markers")
fig <- fig %>% layout(title = "3D Scatter Plot: GDP vs Life Expectancy vs Population",
scene = list(xaxis = list(title = "GDP Per Capita"),
yaxis = list(title = "Life Expectancy"),
zaxis = list(title = "Population")))
fig
# Us Population Over time
gapminder %>%
filter(country == "United States") %>%
ggplot(aes(x = year, y = gdpPercap)) +
geom_point(color = "blue", alpha = 0.6) + # Scatter points
geom_line(color = "red") + # Line connecting points
theme_minimal() +
labs(title = "U.S. GDP Per Capita over Time",
x = "Year",
y = "Population")
# Greece life expectancy over time
gapminder %>%
filter(country == "Greece") %>%
ggplot(aes(x = year, y = lifeExp)) +
geom_point ( color= "red", alpha = 0.6) + #points
geom_line(color = "black") + #Line
theme_grey() +
labs(title= "Russia Life Expectancy Over Time",
x = "Year",
y = "Life Expectancy")
# This plot is showing the GDP per capita comparison between two countries
gapminder %>%
filter(country %in% c("United States", "Greece")) %>%
ggplot(aes(x = country, y = gdpPercap, fill = country)) +
geom_boxplot() +
theme_minimal() +
labs(title = "GDP Per Capita Comparison: U.S. vs. Greece",
x = "Country",
y = "GDP Per Capita")
# Relationship between life expectancy and GDP with scatterplot
ggplot(gapminder, aes(x = gdpPercap, y = lifeExp, color = continent)) +
geom_point(alpha = 0.6, size = 2) +
geom_smooth(method = "lm") +
scale_x_log10() + # Log transformation for GDP per capita
theme_minimal() +
labs(
title = "Life Expectancy vs. GDP Per Capita",
subtitle = "Colored by Continent (1952–2007)",
x = "GDP Per Capita (Log Scale)",
y = "Life Expectancy",
color = "Continent"
)
## `geom_smooth()` using formula = 'y ~ x'
# Other visualizations to explore but not needed for this article
library(hexbin)
ggplot(gapminder, aes(x = gdpPercap, y = lifeExp)) +
geom_hex(bins = 30) +
scale_x_log10() +
theme_minimal() +
labs(
title = "Hexbin Plot: Life Expectancy vs GDP Per Capita",
x = "GDP Per Capita (Log Scale)",
y = "Life Expectancy"
)
ggplot(gapminder, aes(x = gdpPercap, y = lifeExp)) +
stat_density_2d(aes(fill = after_stat(level)), geom = "polygon") +
scale_x_log10() +
theme_minimal() +
labs(
title = "2D Density Contour: GDP vs Life Expectancy",
x = "GDP Per Capita (Log Scale)",
y = "Life Expectancy"
)
ggplot(gapminder, aes(x = gdpPercap, y = lifeExp, size = pop, color = continent)) +
geom_point(alpha = 0.5) +
scale_size(range = c(1, 10)) +
scale_x_log10() +
theme_minimal() +
labs(
title = "Bubble Plot: GDP vs Life Expectancy (Sized by Population)",
x = "GDP Per Capita (Log Scale)",
y = "Life Expectancy",
size = "Population"
)
# Time Series
countries <- c("United States", "Greece")
gapminder %>%
filter(country %in% countries) %>%
ggplot(aes(x = year, y = pop, color = country)) +
geom_line(size = 1) +
geom_point(size = 2, alpha = 0.7) +
theme_minimal() +
labs(
title = "Population Growth: U.S. vs. Greece",
x = "Year",
y = "Population",
color = "Country"
) +
scale_y_continuous(labels = scales::comma)
## 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.
# showing population trends
countries <- c("United States", "Greece")
gapminder %>%
filter(country %in% countries) %>%
ggplot(aes(x = year, y = pop)) +
geom_line(aes(color = country), size = 1.2) +
geom_point(aes(color = country), size = 3, shape = 21, fill = "white") +
facet_wrap(~ country, scales = "free_y") +
scale_color_manual(values = c("United States" = "#1f77b4", "Greece" = "#e15759")) +
scale_y_continuous(labels = comma) +
theme_minimal(base_size = 14) +
labs(
title = "Population Trends (1952–2007)",
subtitle = "United States vs. Greece (Faceted by Country)",
x = "Year",
y = "Population",
color = "Country"
) +
theme(
plot.title = element_text(face = "bold", size = 18),
plot.subtitle = element_text(size = 13),
axis.title = element_text(face = "bold"),
strip.text = element_text(face = "bold", size = 14),
legend.position = "none"
)
#Population with log scale following direct labeling
countries <- c("United States", "Greece")
gapminder %>%
filter(country %in% countries) %>%
ggplot(aes(x = year, y = pop, group = country, color = country)) +
geom_line(size = 1.2) +
geom_point(size = 2) +
geom_text_repel(
data = . %>% group_by(country) %>% filter(year == max(year)),
aes(label = country),
nudge_x = 1,
direction = "y",
hjust = 0,
segment.color = NA,
size = 5
) +
scale_y_log10(labels = comma) +
theme_minimal(base_size = 14) +
labs(
title = "Population Over Time (Log Scale)",
subtitle = "Direct labeling for clarity (Wilke, 20.2)",
x = "Year",
y = "Population (log scale)"
) +
theme(legend.position = "none")
# comparison in log scale
countries <- c("United States", "Greece")
gapminder %>%
filter(country %in% countries) %>%
group_by(country) %>%
mutate(pop_indexed = pop / first(pop)) %>%
ggplot(aes(x = year, y = pop_indexed, color = country)) +
geom_line(size = 1.2) +
geom_point(size = 2) +
geom_text_repel(
data = . %>% filter(year == max(year)),
aes(label = country),
nudge_x = 1,
direction = "y",
hjust = 0,
segment.color = NA,
size = 5
) +
scale_y_log10(labels = label_number(accuracy = 0.01)) +
theme_minimal(base_size = 14) +
labs(
title = "Relative Population Growth (Log Scale)",
subtitle = "Population indexed to 1952 = 1",
x = "Year",
y = "Population Growth (relative to 1952)"
) +
theme(legend.position = "none")
# make a bubble plot for the year 2007
gapminder %>%
filter(year == 2007) %>%
arrange(pop) %>%
ggplot(aes(x = gdpPercap, y = lifeExp, size = pop, color = continent)) +
geom_point(alpha = 0.7) +
scale_x_log10() +
scale_size(range = c(1, 20), name = "Population") +
theme_minimal(base_size = 14) +
labs(
title = "Bubble Plot: Life Expectancy vs. GDP Per Capita (2007)",
x = "GDP Per Capita (Log Scale)",
y = "Life Expectancy",
color = "Continent"
)
# Animated over Time
ggplot(gapminder, aes(x = gdpPercap, y = lifeExp,
size = pop, color = continent)) +
geom_point(alpha = 0.7, show.legend = TRUE) +
scale_x_log10() +
scale_size(range = c(2, 12), name = "Population") +
scale_y_continuous(limits = c(20, 90)) +
theme_minimal(base_size = 14) +
labs(
title = 'Life Expectancy vs. GDP per Capita',
subtitle = 'Year: {frame_time}',
x = 'GDP per Capita (log scale)',
y = 'Life Expectancy',
color = 'Continent'
) +
transition_time(year) +
ease_aes('linear') +
enter_fade() + exit_fade()
# Split Frames by continent
gapminder %>%
ggplot(aes(x = gdpPercap, y = lifeExp,
size = pop, color = continent)) +
geom_point(alpha = 0.7, show.legend = FALSE) +
scale_x_log10() +
scale_size(range = c(2, 12)) +
facet_wrap(~ continent) +
theme_minimal(base_size = 14) +
labs(
title = "Animated Bubble Plot by Continent",
subtitle = "Year: {frame_time}",
x = "GDP per Capita (log scale)",
y = "Life Expectancy"
) +
transition_time(year) +
ease_aes("linear") +
enter_fade() +
exit_fade()
