## 1.1: Load the required packageslibrary(gapminder)
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(ggplot2)
1.2: Look at the gapminder dataset
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
## 1.3: Create a subset of gapminder data set.## Create gapminder_1957
gapminder_1957 <- gapminder %>%
filter(year == 1957)
## Plot a scatterplot pop on the x-axis and lifeExp on the y-axis
ggplot(gapminder_1957, aes(x = pop, y= lifeExp)) + geom_point()
## Change to put pop on the x-axis and gdpPercap on the y-axis
ggplot(gapminder_1957, aes(x = pop, y= gdpPercap)) + geom_point()
## Create a scatter plot with gdpPercap on the x-axis ## and lifeExp on the y-axis
ggplot(gapminder_1957, aes(x = gdpPercap, y= lifeExp)) + geom_point()
## Change this plot to put the x-axis on a log scale
ggplot(gapminder_1957, aes(x = pop, y= lifeExp)) + geom_point() +
scale_x_log10()
## Scatter plot comparing pop and gdpPercap,## with both axes on a log scale
ggplot(gapminder_1957, aes(x = pop, y= gdpPercap)) + geom_point() +
scale_x_log10() +
scale_y_log10()
## with color representing continent
ggplot(gapminder_1957, aes(x = pop, y= lifeExp, color = continent)) + geom_point() +
scale_x_log10()
## Add the size aesthetic to represent a country's gdpPercap
ggplot(gapminder_1957, aes(x = pop, y= lifeExp, color = continent,size = gdpPercap)) + geom_point() +
scale_x_log10()
## Scatter plot comparing pop and lifeExp, faceted by continent
ggplot(gapminder_1957, aes(x = pop, y= lifeExp)) + geom_point() +
scale_x_log10() +
facet_wrap(~continent)
## Scatter plot comparing gdpPercap and lifeExp, with color ## representing continent and size representing population, faceted by year
ggplot(gapminder, aes(x = gdpPercap, y= lifeExp, color = continent,size = pop)) + geom_point() +
scale_x_log10() +
facet_wrap(~year)
## Create a variable by_year that gets the median life expectancy## for each year
by_year <- gapminder %>%
group_by(year) %>%
summarise(medianLifeExp = median(lifeExp))
## Create a scatter plot showing the change in medianLifeExp over time
ggplot(by_year,aes(x = year, y= medianLifeExp)) +
geom_point() +
expand_limits(y = 0)
## Summarize medianGdpPercap within each continent within each year: ## by_year_continent
by_year_continent <- gapminder %>%
group_by(year, continent) %>%
summarize(medianGdpPercap = median(gdpPercap))
## `summarise()` has grouped output by 'year'. You can override using the
## `.groups` argument.
## Plot the change in medianGdpPercap in each continent over time
ggplot(by_year_continent,aes(x = year , y = medianGdpPercap,
color = continent )) +
geom_point() +
expand_limits(y = 0)
## Summarize the median GDP and median life expectancy## per continent in 2007
by_continent_2007 <- gapminder %>%
filter(year == 2007) %>%
group_by(continent) %>%
summarize(medianLifeExp = median(lifeExp),
medianGdpPercap = median(gdpPercap))
## Use a scatter plot to compare the median GDP ## and median life expectancy
ggplot(by_continent_2007, aes(x = medianLifeExp , y = medianGdpPercap, color = continent )) +
geom_point()
## Summarize the median gdpPercap by year,## then save it as by_year
by_year <- gapminder %>%
group_by(year) %>%
summarize(medianGdpPercap = median(gdpPercap))
## Create a line plot showing the change in medianGdpPercap over time
ggplot(by_year, aes(x = year , y = medianGdpPercap )) +
geom_line() +
expand_limits( y = 0)
## Summarize the median gdpPercap by year & continent,## save as by_year_continent
by_year_continent <- gapminder %>%
group_by(year, continent) %>%
summarize(medianGdpPercap = median(gdpPercap))
## `summarise()` has grouped output by 'year'. You can override using the
## `.groups` argument.
## Create a line plot showing the change in ## medianGdpPercap by continent over time
ggplot(by_year_continent, aes(x = year , y = medianGdpPercap , color = continent)) +
geom_line() +
expand_limits( y = 0)
## Summarize the median gdpPercap by continent in 1957
by_continent <- gapminder %>%
filter(year == 1957) %>%
group_by(continent) %>%
summarize(medianGdpPercap = median(gdpPercap))
## Create a bar plot showing medianGdp by continent
ggplot(by_continent , aes(x = continent , y = medianGdpPercap , )) +
geom_col() +
expand_limits( y = 0)
## Visualizing GDP per capita by country in Oceania## Filter for observations in the Oceania continent in 1957
oceania_1957 <- gapminder %>%
filter(continent == "Oceania", year == 1957)
## Filter the dataset for the year 1957. Create a new column called## pop_by_mil. Save this in a new variable called gapminder_1957
gapminder_1957 <- gapminder %>%
filter(year == 1957) %>%
mutate(pop_by_mil = pop/1000000)
## Create a histogram of population (pop_by_mil)
ggplot(gapminder_1957 , aes(x = pop_by_mil )) +
geom_histogram(bins = 50)
## Recreate the gapminder_1957 and filter for the year 1957 only
gapminder_1957 <- gapminder %>%
filter(year == 1957)
## Create a histogram of population (pop), with x on a log scale
ggplot(gapminder_1957 , aes(x = pop)) +
geom_histogram() +
scale_x_log10()
## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
## Create the gapminder_1957 and filter for the year 1957 only
gapminder_1957 <- gapminder %>%
filter(year == 1957)
## Create a boxplot comparing gdpPercap among continents
ggplot(gapminder_1957, aes(x = continent, y = gdpPercap)) +
geom_boxplot() +
scale_y_log10()
## Add a title to this graph: ## "Comparing GDP per capita across continents"
ggplot(gapminder_1957, aes(x = continent, y = gdpPercap)) +
geom_boxplot() +
scale_y_log10() +
ggtitle('Comparing GDP per capital across Continents')
