#install.packages("tidyverse")
#install.packages("dslabs")
#install.packages("ggridges")
library(ggridges)
library(tidyverse)
## -- Attaching packages --------------------------------------- tidyverse 1.3.1 --
## v ggplot2 3.3.5 v purrr 0.3.4
## v tibble 3.1.6 v dplyr 1.0.8
## v tidyr 1.2.0 v stringr 1.4.0
## v readr 2.1.2 v forcats 0.5.1
## -- Conflicts ------------------------------------------ tidyverse_conflicts() --
## x dplyr::filter() masks stats::filter()
## x dplyr::lag() masks stats::lag()
library(dslabs)
data(gapminder)
gapminder %>% as_tibble()
## # A tibble: 10,545 x 9
## country year infant_mortality life_expectancy fertility population gdp
## <fct> <int> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 Albania 1960 115. 62.9 6.19 1636054 NA
## 2 Algeria 1960 148. 47.5 7.65 11124892 1.38e10
## 3 Angola 1960 208 36.0 7.32 5270844 NA
## 4 Antigua~ 1960 NA 63.0 4.43 54681 NA
## 5 Argenti~ 1960 59.9 65.4 3.11 20619075 1.08e11
## 6 Armenia 1960 NA 66.9 4.55 1867396 NA
## 7 Aruba 1960 NA 65.7 4.82 54208 NA
## 8 Austral~ 1960 20.3 70.9 3.45 10292328 9.67e10
## 9 Austria 1960 37.3 68.8 2.7 7065525 5.24e10
## 10 Azerbai~ 1960 NA 61.3 5.57 3897889 NA
## # ... with 10,535 more rows, and 2 more variables: continent <fct>,
## # region <fct>
filter(gapminder, year == 1962) %>%
ggplot(aes(fertility, life_expectancy)) +
geom_point()
filter(gapminder, year == 1962) %>%
ggplot( aes(fertility, life_expectancy, color = continent)) +
geom_point()
filter(gapminder, year ==2012) %>%
ggplot(aes(fertility, life_expectancy)) +
geom_point()
filter(gapminder, year == 2012) %>%
ggplot( aes(fertility, life_expectancy, color = continent)) +
geom_point()
filter(gapminder, year%in%c(1962, 2012)) %>%
ggplot(aes(fertility, life_expectancy, col = continent)) +
geom_point() +
facet_grid(continent~year)
filter(gapminder, year%in%c(1962, 2012)) %>%
ggplot(aes(fertility, life_expectancy, col = continent,shape=continent )) +
geom_point() +
facet_grid(. ~ year)
years <- c(1962, 1980, 1990, 2000, 2012)
continents <- c("Europe", "Asia")
gapminder %>%
filter(year %in% years & continent %in% continents) %>%
ggplot( aes(fertility, life_expectancy, col = continent)) +
geom_point() +
facet_wrap(~year)
#This plot clearly shows how most Asian countries have improved at a much faster rate than European ones
filter(gapminder, year%in%c(1962, 2012)) %>%
ggplot(aes(fertility, life_expectancy, col = continent)) +
geom_point() +
facet_wrap(. ~ year, scales = "free")
gapminder %>%
filter(country == "China") %>%
ggplot(aes(year, fertility)) +
geom_point()
## Warning: Removed 1 rows containing missing values (geom_point).
gapminder %>%
filter(country == "United States") %>%
ggplot(aes(year, fertility)) +
geom_line()
## Warning: Removed 1 row(s) containing missing values (geom_path).
countries <- c("South Korea","Germany")
gapminder %>% filter(country %in% countries) %>%
ggplot(aes(year,fertility)) +
geom_line()
## Warning: Removed 2 row(s) containing missing values (geom_path).
#bad example
countries <- c("South Korea","Germany")
gapminder %>% filter(country %in% countries & !is.na(fertility)) %>%
ggplot(aes(year, fertility, group = country)) +
geom_line()
gapminder %>% filter(country %in% countries & !is.na(fertility)) %>%
ggplot(aes(year,fertility, col = country)) +
geom_line()
countries1 <- c("South Korea","Germany","United States","China")
gapminder %>% filter(country %in% countries1 & !is.na(fertility)) %>%
ggplot(aes(year,fertility, col = country)) +
geom_line()
labels <- data.frame(country = countries, x = c(1975,1965), y = c(60,72))
gapminder %>%
filter(country %in% countries) %>%
ggplot(aes(year, life_expectancy, col = country)) +
geom_line() +
geom_text(data = labels, aes(x, y, label = country), size = 5) +
theme(legend.position = "none")
gapminder <- gapminder %>% mutate(dollars_per_day = gdp/population/365)
past_year <- 1970
gapminder %>%
filter(year == past_year & !is.na(gdp)) %>%
ggplot(aes(dollars_per_day)) +
geom_histogram(binwidth = 1, color = "black")
past_year <- 2002
gapminder %>%
filter(year == past_year & !is.na(gdp)) %>%
ggplot(aes(dollars_per_day)) +
geom_histogram(binwidth = 1, color = "black")
gapminder %>%
filter(year == past_year & !is.na(gdp)) %>%
ggplot(aes(log2(dollars_per_day))) +
geom_histogram(binwidth = 1, color = "black")
#this provides a close-up of the mid to lower income countries
gapminder %>%
filter(year == past_year & !is.na(gdp)) %>%
mutate(region = reorder(region, dollars_per_day, FUN = median)) %>%
ggplot(aes(dollars_per_day, region)) +
geom_point() +
scale_x_continuous(trans = "log2")
gapminder <- gapminder %>%
mutate(group = case_when(
region %in% c("Western Europe", "Northern Europe","Southern Europe",
"Northern America",
"Australia and New Zealand") ~ "West",
region %in% c("Eastern Asia", "South-Eastern Asia") ~ "East Asia",
region %in% c("Caribbean", "Central America",
"South America") ~ "Latin America",
continent == "Africa" &
region != "Northern Africa" ~ "Sub-Saharan",
TRUE ~ "Others"))
gapminder <- gapminder %>%
mutate(group = factor(group, levels = c("Others", "Latin America",
"East Asia", "Sub-Saharan",
"West")))
gapminder %>%
filter(year == past_year & !is.na(gdp)) %>%
ggplot(aes(group, dollars_per_day)) +
geom_boxplot() +
scale_y_continuous(trans = "log2") +
xlab("") +
theme(axis.text.x = element_text(angle = 90, hjust = 1))
p <- gapminder %>%
filter(year == past_year & !is.na(gdp)) %>%
ggplot(aes(group, dollars_per_day)) +
geom_boxplot() +
scale_y_continuous(trans = "log2") +
xlab("") +
theme(axis.text.x = element_text(angle = 90, hjust = 1))
p
p + geom_point(alpha = 0.5)
library(ggridges)
p <- gapminder %>%
filter(year == past_year & !is.na(dollars_per_day)) %>%
ggplot(aes(dollars_per_day, group)) +
scale_x_continuous(trans = "log2")
p + geom_density_ridges()
## Picking joint bandwidth of 0.737
p + geom_density_ridges(jittered_points = TRUE)
## Picking joint bandwidth of 0.737
p + geom_density_ridges(jittered_points = TRUE,
position = position_points_jitter(height = 0),
point_shape = '|', point_size = 3,
point_alpha = 1, alpha = 0.7)
## Picking joint bandwidth of 0.737
past_year <- 1970
present_year <- 2010
years <- c(past_year, present_year)
gapminder %>%
filter(year %in% years & !is.na(gdp)) %>%
mutate(west = ifelse(group == "West", "West", "Developing")) %>%
ggplot(aes(dollars_per_day)) +
geom_histogram(binwidth = 1, color = "black") +
scale_x_continuous(trans = "log2") +
facet_grid(year ~ west)
country_list_1 <- gapminder %>%
filter(year == past_year & !is.na(dollars_per_day)) %>%
pull(country)
country_list_2 <- gapminder %>%
filter(year == present_year & !is.na(dollars_per_day)) %>%
pull(country)
country_list <- intersect(country_list_1, country_list_2)
gapminder %>%
filter(year %in% years & country %in% country_list) %>%
ggplot(aes(group, dollars_per_day)) +
geom_boxplot() +
theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
scale_y_continuous(trans = "log2") +
xlab("") +
facet_grid(. ~ year)
gapminder %>%
filter(year %in% years & country %in% country_list) %>%
mutate(year = factor(year)) %>%
ggplot(aes(group, dollars_per_day, fill = year)) +
geom_boxplot() +
theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
scale_y_continuous(trans = "log2") +
xlab("")
gapminder %>%
filter(year %in% years & country %in% country_list) %>%
mutate(group = ifelse(group == "West", "West", "Developing")) %>%
ggplot(aes(dollars_per_day, fill = group)) +
scale_x_continuous(trans = "log2") +
geom_density(alpha = 0.2) +
facet_grid(year ~ .)
gapminder %>%
filter(year %in% years & country %in% country_list) %>%
group_by(year) %>%
mutate(weight = population/sum(population)*2) %>%
ungroup() %>%
ggplot(aes(dollars_per_day, fill = group)) +
scale_x_continuous(trans = "log2", limit = c(0.125, 300)) +
geom_density(alpha = 0.2, bw = 0.75, position = "stack") +
facet_grid(year ~ .)
