Notes D

Making plots with ggplot2: barplots and scatterplots`

Author

EMW

Published

December 31, 2022

library(tidyverse)
#Import the can_lang dataset from last class

#can_lang <- read.csv("can_lang.csv")

#OR
can_lang <- read.csv("https://raw.githubusercontent.com/ttimbers/canlang/master/inst/extdata/can_lang.csv")

Recall our last example:

ten_lang <- can_lang %>% 
  filter(category == "Aboriginal languages") %>%
  arrange(by=desc(mother_tongue)) %>%
  select(language, mother_tongue) %>%
  slice(1:10)

ggplot: barplots with geom_bar

ggplot(ten_lang, aes(x = language, y = mother_tongue)) +
  geom_bar(stat = "identity")

Is there any improvements we could make to this graph?

To better view text

ggplot(ten_lang, aes(x = language, y = mother_tongue)) +
  geom_bar(stat = "identity") +  
  coord_flip()

#OR

ggplot(ten_lang, aes(x = mother_tongue, y = language)) +
  geom_bar(stat = "identity")

Labels, Colors, and Themes

ggplot(ten_lang, aes(x = mother_tongue, y = reorder(language, mother_tongue))) +
  geom_bar(fill="lightblue", stat = "identity") + 
  ylab("Language") +
  xlab("Mother Tongue (Number of Canadian Residents)") + 
  ggtitle("Ten Aboriginal Languages Most Often \n Reported by Canadian Residents \n as Their Mother Tongue") + 
  theme_minimal()

ggplot: scatterplot with geom_point

ggplot(can_lang, aes(x=most_at_home, y=mother_tongue)) +
  geom_point()

With labels

ggplot(can_lang, aes(x = most_at_home, y = mother_tongue)) +
  geom_point() +
  xlab("Language spoken most at home \n (number of Canadian residents)") +
  ylab("Mother tongue \n (number of Canadian residents)") +
  theme(text = element_text(size = 12))

Axis transformations

library(scales)
ggplot(can_lang, aes(x = most_at_home, y = mother_tongue)) +
  geom_point() +
  xlab("Language spoken most at home \n (number of Canadian residents)") +
  ylab("Mother tongue \n (number of Canadian residents)") +
  theme(text = element_text(size = 12)) +
  scale_x_log10(labels = label_comma()) +
  scale_y_log10(labels = label_comma())

mutate to create new columns

can_lang <- can_lang %>%
  mutate(
    mother_tongue_percent = (mother_tongue / 35151728) * 100,
    most_at_home_percent = (most_at_home / 35151728) * 100
  )

Scatterplot with percents

ggplot(can_lang, aes(x = most_at_home_percent, y = mother_tongue_percent)) +
  geom_point() +
  xlab("Language spoken most at home \n (percentage of Canadian residents)") +
  ylab("Mother tongue \n (percentage of Canadian residents)") +
  theme(text = element_text(size = 12)) +
  scale_x_log10(labels = comma) +
  scale_y_log10(labels = comma)

Scatterplot with Percents and Colors

ggplot(can_lang, aes(x = most_at_home_percent, 
                     y = mother_tongue_percent, 
                     color = category, shape=category)) +
  geom_point() +
  xlab("Language spoken most at home \n (percentage of Canadian residents)") +
  ylab("Mother tongue \n (percentage of Canadian residents)") +
  theme(text = element_text(size = 12),
        legend.position = "top",
        legend.direction = "vertical") +
  scale_x_log10(labels = comma) +
  scale_y_log10(labels = comma)