Introduction to ggplot2

data(CPS85 , package = "mosaicData")

ggplot

The Geom function waiting for the data to be plotted, mapping is placed in aes

# specify dataset and mapping
library(ggplot2)
ggplot(data = CPS85,
       mapping = aes(x = exper, y = wage))

geoms

Geoms are the points, lines, bars, etc… that go on the graph.

# add points
ggplot(data = CPS85,
       mapping = aes(x = exper, y = wage)) +
  geom_point()

# delete outlier
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(CPS85, wage < 40)

# redraw scatterplot
ggplot(data = plotdata,
       mapping = aes(x = exper, y = wage)) +
  geom_point()

# make points blue, larger, and semi-transparent
ggplot(data = plotdata,
       mapping = aes(x = exper, y = wage)) +
  geom_point(color = "cornflowerblue",
             alpha = .7,
             size = 3)

# add a line of best fit.
ggplot(data = plotdata,
       mapping = aes(x = exper, y = wage)) +
  geom_point(color = "cornflowerblue",
             alpha = .7,
             size = 3) +
  geom_smooth(method = "lm")

grouping

Grouping can make it so you can plot muluitple different types of data with different color shapes and sizes.

# indicate sex using color
ggplot(data = plotdata,
       mapping = aes(x = exper, 
                     y = wage,
                     color = sex)) +
  geom_point(alpha = .7,
             size = 3) +
  geom_smooth(method = "lm", 
              se = FALSE, 
              size = 1.5)

scales

The scaling function allow you to modify the mapping of a plot.

# modify the x and y axes and specify the colors to be used
ggplot(data = plotdata,
       mapping = aes(x = exper, 
                     y = wage,
                     color = sex)) +
  geom_point(alpha = .7,
             size = 3) +
  geom_smooth(method = "lm", 
              se = FALSE, 
              size = 1.5) +
  scale_x_continuous(breaks = seq(0, 60, 10)) +
  scale_y_continuous(breaks = seq(0, 30, 5),
                     label = scales::dollar) +
  scale_color_manual(values = c("indianred3", 
                                "cornflowerblue"))

facets

Facets re make a graph so that each level is presented.

# reproduce plot for each level of job sector
ggplot(data = plotdata,
       mapping = aes(x = exper, 
                     y = wage,
                     color = sex)) +
  geom_point(alpha = .7) +
  geom_smooth(method = "lm", 
              se = FALSE) +
  scale_x_continuous(breaks = seq(0, 60, 10)) +
  scale_y_continuous(breaks = seq(0, 30, 5),
                     label = scales::dollar) +
  scale_color_manual(values = c("indianred3", 
                                "cornflowerblue")) +
  facet_wrap(~sector)

labels

Make the graphs easy to interpret and know the key elements of the graph.

# add informative labels
ggplot(data = plotdata,
       mapping = aes(x = exper, 
                     y = wage,
                     color = sex)) +
  geom_point(alpha = .7) +
  geom_smooth(method = "lm", 
              se = FALSE) +
  scale_x_continuous(breaks = seq(0, 60, 10)) +
  scale_y_continuous(breaks = seq(0, 30, 5),
                     label = scales::dollar) +
  scale_color_manual(values = c("indianred3", 
                                "cornflowerblue")) +
  facet_wrap(~sector) +
  labs(title = "Relationship between wages and experience",
       subtitle = "Current Population Survey",
       caption = "source: http://mosaic-web.org/",
       x = " Years of Experience",
       y = "Hourly Wage",
       color = "Gender")

themes

Themes help you fine tune the graphs so that the graphs look appealing. EX color, font, grid lines, legend etc…

# use a minimalist theme
ggplot(data = plotdata,
       mapping = aes(x = exper, 
                     y = wage,
                     color = sex)) +
  geom_point(alpha = .6) +
  geom_smooth(method = "lm", 
              se = FALSE) +
  scale_x_continuous(breaks = seq(0, 60, 10)) +
  scale_y_continuous(breaks = seq(0, 30, 5),
                     label = scales::dollar) +
  scale_color_manual(values = c("indianred3", 
                                "cornflowerblue")) +
  facet_wrap(~sector) +
  labs(title = "Relationship between wages and experience",
       subtitle = "Current Population Survey",
       caption = "source: http://mosaic-web.org/",
       x = " Years of Experience",
       y = "Hourly Wage",
       color = "Gender") +
  theme_minimal()