Data Visualiation

library(ggplot2)
data(Marriage, package = "mosaicData")

# plot the distribution of race
ggplot(Marriage, aes(x = race)) + 
  geom_bar(fill = "cornflowerblue", 
           color="black") +
  labs(x = "Race", 
       y = "Frequency", 
       title = "Participants by race")

data(mpg, package = "ggplot2")
# stacked bar chart
ggplot(mpg, 
       aes(x = class, 
           fill = drv)) + 
  geom_bar(position = "fill") +
  labs(y = "Proportion",
       title = "",
       fill = "Drive Type")

data(Salaries, package="carData")

# simple scatterplot
ggplot(Salaries, 
       aes(x = yrs.service, 
           y = salary)) +
  geom_point()

ggplot(Salaries, 
       aes(x = yrs.since.phd, 
           y = salary,
           color = rank,
           shape = sex,
           size = yrs.service)) +
  geom_point()

library(gapminder)
data(gapminder, package="gapminder")

# Select US cases
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

plotdata <- filter(gapminder, 
                   country == "United States")

# simple line plot
ggplot(plotdata, 
       aes(x = year, 
           y = pop)) +
  geom_line() 

ggplot(Salaries, 
       aes(x = rank, 
           y = salary)) +
  geom_boxplot() +
  labs(title = "Salary distribution by rank")

ggplot(mpg, aes(x = hwy)) +
  geom_histogram(fill = "cornflowerblue",
                 color = "white") +
  facet_wrap(~class, ncol = 1) +
  labs(title = "Salary histograms by rank")

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

ggplot(Salaries, aes(x = salary / 1000)) +
  geom_histogram(color = "white",
                 fill = "cornflowerblue") +
  facet_grid(sex ~ rank) +
  labs(title = "Salary histograms by sex and rank",
       x = "Salary ($1000)")

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.

plotdata <- dplyr::filter(gapminder, 
                          continent == "Americas")

ggplot(plotdata, aes(x=year, y = lifeExp)) +
  geom_line(color="grey") +
  geom_point(color="blue") +
  facet_wrap(~country)

gapminder %>%
  filter(continent == "Americas") %>%
  ggplot(aes(x=year, y = lifeExp)) +
  geom_line(color="grey") +
  geom_point(color="blue") +
  facet_wrap(~country)