library(ggplot2)
library(ggpubr)
library(dplyr)
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, unionModule 15a Exercise
Loading the packages needed.
Loading the dataset.
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 ...Filter for 2007 and not Oceania
gap07 <- gap |>
filter(year == 2007 & continent != "Oceania")Making some scatterplots.
ggplot(gap07, aes(x = gdpPercap, y = lifeExp, col = continent)) +
geom_point() + scale_x_log10("GDP per capita ($)") +
scale_y_continuous("Life Expectancy (yrs)") + ggtitle("GapMinder Data 2007")
ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)",
main = "GapMinder Data 2007") +
xscale("log10", .format = TRUE)
Adding labels to each/some points
ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
xlab = "GDP per capita ($)", ylab = "Life Expectancy (yrs)",
main = "GapMinder Data 2007", label = "country", repel = TRUE) +
xscale("log10", .format = TRUE)
sel_countries = c("United States", "China", "Germany")
ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)",
main = "GapMinder Data 2007", label = "country",
label.select = sel_countries, repel = TRUE) +
xscale("log10", .format = TRUE)
ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)",
main = "GapMinder Data = 2007") +
xscale("log10", .format = TRUE)
Creating a marginal histogram
library(ggExtra)
p <- ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)",
main = "GapMinder Data 2007") +
xscale("log10", .format = TRUE)
ggMarginal(p, type = "histogram")
Adding a regression line
ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
xlab = "GDP per capita ($)", ylab = "Life expectancy (yrs)",
main = "GapMinder Data 2007", add = "reg.line", conf.int = TRUE) +
xscale("log10", .format = TRUE)
Adding correlations
ggscatter(gap07, x = "gdpPercap", y = "lifeExp", col = "continent",
xlab = "GDP per capita ($)", 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")
Adding the 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))
Generating histograms
gghistogram(gap07, x = "lifeExp", main = "GapMinder Life Expectancy")Warning: Using `bins = 30` by default. Pick better value with the argument
`bins`.
gghistogram(gap07, x = "lifeExp", fill = "continent",
main = "GapMinder Life Expectancy")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`.
Generating density plots
ggdensity(gap07, x = "lifeExp", fill = "continent",
main = "GapMinder Life Expectancy", palette = "jco")
ggdensity(gap07, x = "lifeExp", fill = "continent",
main = "GapMinder Life Expectancy", palette = "jco",
facet.by = "continent")
ggdensity(gap07, x = "lifeExp", fill = "continent",
main = "GapMinder Life Expectancy", palette = "jco",
facet.by = "continent",
add = "median", rug = TRUE)
Generating violin plots
ggviolin(gap07, x = "continent", y = "lifeExp")
ggviolin(gap07, x = "continent", y = "lifeExp",
fill = "continent", palette = "jco",
add = c("boxplot", "jitter"),
ylab = "Life expectancy (yrs)")
ggviolin(gap07, x = "continent", y = "lifeExp",
fill = "continent", palette = "jco",
add = c("boxplot", "jitter"),
ylab = "Life expectancy (yrs)",
rotate = TRUE)
Generating bar plots
ggbarplot(gap07, x = "country", y = "lifeExp")
ggbarplot(gap07,
x = "country",
y = "lifeExp",
fill = "continent",
pallete = "jco",
x.text.angle = 90,
ylab = "Life expectancy (yrs)",
xlab = "Country") +
font("x.text", size = 4)
ggbarplot(gap07,
x = "country",
y = "lifeExp",
fill = "continent",
pallete = "jco",
sort.val = "desc",
sort.by.groups = FALSE,
x.text.angle = 90,
ylab = "Life expectancy (yrs)",
xlab = "Country") +
font("x.text", size = 4)
Generating 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
gap_sub <- gap |>
filter(continent %in% c("Asia", "Africa"),
year %in% c(1957, 1982, 2007))
ggboxplot(gap_sub, x = "continent", y = "lifeExp",
ylab = "Years", col = "continent", add = "jitter")
ggboxplot(gap_sub, x = "continent", y = "lifeExp",
ylab = "Years", col = "continent", add = "jitter") +
stat_compare_means(label.y = 90)
Doing 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)
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)
Comparing multiple groups
ggboxplot(gap_sub, x = "year", y = "lifeExp") +
stat_compare_means(label.y = 80, method = "anova")
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")
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")
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")