Module 15a — ggpubr

library(ggplot2)
library(ggpubr)
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
gap <- read.csv("gapminderData5.csv")
str(gap)
## 'data.frame':    1704 obs. of  6 variables:
##  $ country  : chr  "Afghanistan" "Afghanistan" "Afghanistan" "Afghanistan" ...
##  $ year     : int  1952 1957 1962 1967 1972 1977 1982 1987 1992 1997 ...
##  $ pop      : num  8425333 9240934 10267083 11537966 13079460 ...
##  $ continent: chr  "Asia" "Asia" "Asia" "Asia" ...
##  $ lifeExp  : num  28.8 30.3 32 34 36.1 ...
##  $ gdpPercap: num  779 821 853 836 740 ...

Extract subset of data for the year 2007

gap07 <- gap %>% 
  filter(year == 2007 & continent != "Oceania")

Scatter plots

With ggplot

ggplot(gap07, aes(x = gdpPercap, y = lifeExp, col = continent)) + 
  geom_point() + scale_x_log10("GDP per capita ($)") + 
  scale_y_continuous("Life Expectancy (yrs)") + ggtitle("GapMinder Data 2007")

Same figure but with ggpubr

ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
          xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)", 
          main = "GapMinder Data 2007") + 
  xscale("log10", .format = TRUE)

Add country labels

ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
          xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)", 
          main = "GapMinder Data 2007", label = "country", repel = TRUE) + 
  xscale("log10", .format = TRUE)

Add just a few country labels

sel_countries = c("United States", "China", "Germany")
ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
          xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)", 
          main = "GapMinder Data 2007", label = "country", 
          label.select = sel_countries, repel = TRUE) + 
  xscale("log10", .format = TRUE)

Plot using a ‘rug’ position

ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
          xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)", 
          main = "GapMinder Data 2007") + 
  xscale("log10", .format = TRUE)

Add marginal histograms

library(ggExtra)
p <- ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
               xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)", 
               main = "GapMinder Data 2007") + 
  xscale("log10", .format = TRUE)
ggMarginal(p, type = "histogram")

Add a regression line

ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
          xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)", 
          main = "GapMinder Data 2007", add = "reg.line", conf.int = TRUE) + 
  xscale("log10", .format = TRUE)

Add correlations

ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
          xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)", 
          main = "GapMinder Data 2007", add = "reg.line", conf.int = TRUE) + 
  xscale("log10", .format = TRUE) +
  stat_cor(aes(color = continent), method = "spearman")

Add regression line equations

ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
          xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)", 
          main = "GapMinder Data 2007", add = "reg.line", conf.int = TRUE) + 
  xscale("log10", .format = TRUE) +
  stat_regline_equation(aes(color = continent))

Histograms

gghistogram(gap07, x = "lifeExp", main = "GapMinder Life Expectancy")
## Warning: Using `bins = 30` by default. Pick better value with the argument
## `bins`.

Separate the continents with color

gghistogram(gap07, x = "lifeExp", fill = "continent", 
            main = "GapMinder Life Expectancy")
## Warning: Using `bins = 30` by default. Pick better value with the argument
## `bins`.

Palettes

gghistogram(gap07, x = "lifeExp", fill = "continent", 
            main = "GapMinder Life Expectancy", palette = "npg")
## Warning: Using `bins = 30` by default. Pick better value with the argument
## `bins`.

gghistogram(gap07, x = "lifeExp", fill = "continent", 
            main = "GapMinder Life Expectancy", palette = "jco")
## Warning: Using `bins = 30` by default. Pick better value with the argument
## `bins`.

gghistogram(gap07, x = "lifeExp", fill = "continent", 
            main = "GapMinder Life Expectancy", palette = "aaas")
## Warning: Using `bins = 30` by default. Pick better value with the argument
## `bins`.

gghistogram(gap07, x = "lifeExp", fill = "continent", 
            main = "GapMinder Life Expectancy", palette = "rickandmorty")
## Warning: Using `bins = 30` by default. Pick better value with the argument
## `bins`.

Density plots

ggdensity(gap07, x = "lifeExp", fill = "continent", 
          main = "GapMinder Life Expectancy", palette = "jco")

Add a facet argument to produce multiple plots

ggdensity(gap07, x = "lifeExp", fill = "continent", 
          main = "GapMinder Life Expectancy", palette = "jco",
          facet.by = "continent")

Add a reference line and a rug plot

ggdensity(gap07, x = "lifeExp", fill = "continent", 
          main = "GapMinder Life Expectancy", palette = "jco",
          facet.by = "continent",
          add = "median", rug = TRUE)

Violin plots

ggviolin(gap07, x = "continent", y = "lifeExp")

Improve the basic violin plot

ggviolin(gap07, x = "continent", y = "lifeExp", 
         fill = "continent", palette = "jco",
         add = c("boxplot", "jitter"),
         ylab = "Life expectancy (yrs)")

Make them horizontal

ggviolin(gap07, x = "continent", y = "lifeExp", 
         fill = "continent", palette = "jco",
         add = c("boxplot", "jitter"),
         ylab = "Life expectancy (yrs)",
         rotate = TRUE)

Bar plots

ggbarplot(gap07,
          x = "country",
          y = "lifeExp")

Improve on the basic bar plot

ggbarplot(gap07,
          x = "country",
          y = "lifeExp",
          fill = "continent",
          palette = "jco",
          x.text.angle = 90,
          ylab = "Life expectancy (yrs)",
          xlab = "Country") +
  font("x.text", size = 4)

Reorder by value

ggbarplot(gap07,
          x = "country",
          y = "lifeExp",
          fill = "continent",
          palette = "jco",
          sort.val = "desc",
          sort.by.groups = FALSE,
          x.text.angle = 90,
          ylab = "Life expectancy (yrs)",
          xlab = "Country") +
  font("x.text", size = 4)

Dot plots

ggdotchart(gap07,
           x = "country",
           y = "lifeExp",
           color = "continent",
           palette = "jco",
           sorting = "descending",
           rotate = TRUE,
           group = "continent",
           add = "segments",
           ylab = "Life expectancy (yrs)",
           xlab = "Country") +
  font("y.text", size = 4)

Adding comparisons to plots

Making a new subset with just data from Africa and Asia

gap_sub = gap %>% 
  filter(continent %in% c("Asia", "Africa"),
         year %in% c(1957, 1982, 2007))

Make a boxplot

ggboxplot(gap_sub, x = "continent", y = "lifeExp", 
          ylab = "Years", col = "continent", add = "jitter")

Test if mean life expectancy differs between Africa and Asia

ggboxplot(gap_sub, x = "continent", y = "lifeExp", 
          ylab = "Years", col = "continent", add = "jitter") + 
  stat_compare_means(label.y = 90)

Use a t-test instead

ggboxplot(gap_sub, x = "continent", y = "lifeExp", 
          ylab = "Years", col = "continent", add = "jitter") + 
  stat_compare_means(method = "t.test", label.y = 90)

Make multiple box plots by year

ggboxplot(gap_sub, x = "continent", y = "lifeExp", 
          ylab = "Years", col = "continent", add = "jitter", facet.by = "year") + 
  stat_compare_means(method = "t.test", label.y = 90)

Multiple groups by year and use ANOVA

ggboxplot(gap_sub, x = "year", y = "lifeExp") + 
  stat_compare_means(label.y = 80, method = "anova")

Pairwise comparison

comps = list( c('1957', '1982'), 
              c('1957', '2007'), 
              c('1982', '2007'))
comps
## [[1]]
## [1] "1957" "1982"
## 
## [[2]]
## [1] "1957" "2007"
## 
## [[3]]
## [1] "1982" "2007"
ggboxplot(gap_sub, x = "year", y = "lifeExp", ylab = "Years") + 
  stat_compare_means(method = "t.test", comparisons = comps, 
                     bracket.size = .6, size = 4)

ggboxplot(gap_sub, x = "year", y = "lifeExp", ylab = "Years") + 
  stat_compare_means(method = "t.test", comparisons = comps, 
                     bracket.size = .6, size = 4) + 
  stat_compare_means(label.y = 110, method = "anova")

ggboxplot(gap_sub, x = "year", y = "lifeExp", ylab = "Years", facet.by = "continent") + 
  stat_compare_means(method = "t.test", comparisons = comps, 
                     bracket.size = .6, size = 4) + 
  stat_compare_means(label.y = 110, method = "anova")

Compare to a reference year (1957)

ggboxplot(gap_sub, x = "year", y = "lifeExp", ylab = "Years", facet.by = "continent") + 
  stat_compare_means(method = "t.test", ref.group = "1957") + 
  stat_compare_means(label.y = 110, method = "anova")

Fix the overlap

ggboxplot(gap_sub, x = "year", y = "lifeExp", ylab = "Years", facet.by = "continent") + 
  stat_compare_means(label = "p.signif", method = "t.test",
                     ref.group = "1957") + 
  stat_compare_means(label.y = 110, method = "anova")

Scatter plots

ggscatter(gap07, x = "gdpPercap", y = "lifeExp", 
          xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)", 
          main = "GapMinder Data 2007",
          add = "reg.line") + 
  xscale("log10", .format = TRUE)

ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
          xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)", 
          main = "GapMinder Data 2007") + 
  xscale("log10", .format = TRUE)