Directions

Use the force with Alita

Data for demo

Back to the spellbook

# 1. Load data

country_demo <- read.csv("country_demo_2.csv", header = TRUE)
head(country_demo, 10)

##     X     country continent year lifeExp      pop gdpPercap
## 1   1 Afghanistan      Asia 1952  28.801  8425333  779.4453
## 2   2 Afghanistan      Asia 1957  30.332  9240934  820.8530
## 3   3 Afghanistan      Asia 1962  31.997 10267083  853.1007
## 4   4 Afghanistan      Asia 1967  34.020 11537966  836.1971
## 5   5 Afghanistan      Asia 1972  36.088 13079460  739.9811
## 6   6 Afghanistan      Asia 1977  38.438 14880372  786.1134
## 7   7 Afghanistan      Asia 1982  39.854 12881816  978.0114
## 8   8 Afghanistan      Asia 1987  40.822 13867957  852.3959
## 9   9 Afghanistan      Asia 1992  41.674 16317921  649.3414
## 10 10 Afghanistan      Asia 1997  41.763 22227415  635.3414

names(country_demo)

## [1] "X"         "country"   "continent" "year"      "lifeExp"   "pop"      
## [7] "gdpPercap"

str(country_demo)

## 'data.frame':    1706 obs. of  7 variables:
##  $ X        : int  1 2 3 4 5 6 7 8 9 10 ...
##  $ country  : chr  "Afghanistan" "Afghanistan" "Afghanistan" "Afghanistan" ...
##  $ continent: chr  "Asia" "Asia" "Asia" "Asia" ...
##  $ year     : int  1952 1957 1962 1967 1972 1977 1982 1987 1992 1997 ...
##  $ lifeExp  : num  28.8 30.3 32 34 36.1 ...
##  $ pop      : int  8425333 9240934 10267083 11537966 13079460 14880372 12881816 13867957 16317921 22227415 ...
##  $ gdpPercap: num  779 821 853 836 740 ...

summary(country_demo)

##        X            country           continent              year     
##  Min.   :   1.0   Length:1706        Length:1706        Min.   :1952  
##  1st Qu.: 427.2   Class :character   Class :character   1st Qu.:1967  
##  Median : 853.5   Mode  :character   Mode  :character   Median :1982  
##  Mean   : 853.5                                         Mean   :1980  
##  3rd Qu.:1279.8                                         3rd Qu.:1997  
##  Max.   :1706.0                                         Max.   :2007  
##     lifeExp           pop              gdpPercap       
##  Min.   :23.60   Min.   :6.660e+02   Min.   :   241.2  
##  1st Qu.:48.22   1st Qu.:2.792e+06   1st Qu.:  1203.2  
##  Median :60.71   Median :7.021e+06   Median :  3534.8  
##  Mean   :59.48   Mean   :2.957e+07   Mean   :  7234.0  
##  3rd Qu.:70.85   3rd Qu.:1.957e+07   3rd Qu.:  9349.0  
##  Max.   :82.60   Max.   :1.319e+09   Max.   :113523.1

names(country_demo)[1] <- "ID"
names(country_demo)

## [1] "ID"        "country"   "continent" "year"      "lifeExp"   "pop"      
## [7] "gdpPercap"

2. Scatter plots

library(ggplot2)


ggplot(country_demo) + aes(x = gdpPercap, y = lifeExp) +
  geom_point()

Filter for year = 2007 only.

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

country_demo_2007 <- filter(country_demo,
                            year == 2007)

Using pipe to filter for year = 1977 only.

country_demo_1977 <- country_demo %>% 
  filter(year == 1977)

head(country_demo_1977, 10)

##     ID     country continent year lifeExp      pop  gdpPercap
## 1    6 Afghanistan      Asia 1977  38.438 14880372   786.1134
## 2   18     Albania    Europe 1977  68.930  2509048  3533.0039
## 3   30     Algeria    Africa 1977  58.014 17152804  4910.4168
## 4   42      Angola    Africa 1977  39.483  6162675  3008.6474
## 5   54   Argentina  Americas 1977  68.481 26983828 10079.0267
## 6   66   Australia   Oceania 1977  73.490 14074100 18334.1975
## 7   78     Austria    Europe 1977  72.170  7568430 19749.4223
## 8   90     Bahrain      Asia 1977  65.593   297410 19340.1020
## 9  102  Bangladesh      Asia 1977  46.923 80428306   659.8772
## 10 114     Belgium    Europe 1977  72.800  9821800 19117.9745

Scatter plot for year = 2007 only.

ggplot(country_demo_2007) + aes(x = gdpPercap, y = lifeExp) +
  geom_point() + ggtitle("Life expectancy and GDP per capita")

ggplot(country_demo_2007) + aes(x = lifeExp, y = gdpPercap) +
  geom_point() + ggtitle("Life expectancy and GDP per capita, 2007")

ggplot(country_demo_2007) + aes(x = pop, y = gdpPercap) +
  geom_point() + ggtitle("GDP per capita and population")

Label scatter plot Note: Think carefully (and use the force) before labelling

ggplot(country_demo_2007) + aes(x = pop, y = gdpPercap) +
  geom_point() + ggtitle("GDP per capita and population") +
  geom_text(aes(label = country),hjust = 0, vjust = 0)

library(ggrepel)
ggplot(country_demo_2007) + aes(x = pop, y = gdpPercap) +
  geom_point() + ggtitle("GDP per capita and population") +
  geom_label_repel(aes(label = country),
                 box.padding   = 0.35, 
                 point.padding = 0.5,
                 segment.color = "blue")

ggplot(country_demo_2007) + aes(x = pop, y = gdpPercap) +
  geom_point() + ggtitle("GDP per capita and population") +
  geom_label_repel(data = subset(country_demo_2007, country == "Iron City" | country == "Zalem"),
                                 aes(label = country),
                   box.padding   = 0.35, 
                   point.padding = 0.5,
                   segment.color = "blue",
                   force = 200)

ggplot(country_demo_2007) + aes(x = gdpPercap, y = lifeExp) +
  geom_point()

ggplot(country_demo_2007) + aes(x = gdpPercap, y = lifeExp) +
  geom_point() + scale_x_log10()

ggplot(country_demo_2007) + aes(x = lifeExp, y = pop) +
  geom_point()

ggplot(country_demo_2007) + aes(x = lifeExp, y = pop) +
  geom_point() + scale_y_log10()

ggplot(country_demo_2007) + aes(x = pop, y = gdpPercap) +
  geom_point() + xlab("Population") + ylab("GDP per Capita") +
  ggtitle("GDP per capita and population, 2007")

ggplot(country_demo_2007) + aes(x = pop, y = gdpPercap) +
  geom_point() + scale_x_log10() + scale_y_log10()

ggplot(country_demo) + aes(x = pop, y = gdpPercap) +
  geom_point() + xlab("Population") + ylab("GDP per Capita") +
  ggtitle("GDP per capita and population")

ggplot(country_demo) + aes(x = pop, y = gdpPercap) +
  geom_point() + xlab("Population (log scale)") + ylab("GDP per Capita (log scale") +
  ggtitle("GDP per capita and population") +
  scale_x_log10() + scale_y_log10()

library(ggpubr)
ggplot(country_demo) + aes(x = pop, y = gdpPercap) +
  geom_point(shape = 1, colour = "green") + scale_x_log10() + scale_y_log10() +
  xlab("Population (log scale)") + ylab("GDP per Capita (log scale)") +
  ggtitle("GDP per capita and population") +
  geom_smooth(method = lm) +
  stat_regline_equation(label.x = 8, label.y = 4) +
  stat_cor(method = "pearson", label.x = 8, label.y = 3.8) +
  geom_label_repel(data = subset(country_demo_2007, country == "Iron City" | country == "Zalem"),
                   aes(label = country),
                   box.padding   = 0.35, 
                   point.padding = 0.5,
                   segment.color = "blue",
                   force = 200)

## `geom_smooth()` using formula 'y ~ x'

ggplot(country_demo_2007) + aes(x = gdpPercap, y = lifeExp,
                                colour = continent) +
  geom_point()

ggplot(country_demo_2007) + aes(x = gdpPercap, y = lifeExp,
                                colour = continent) +
  geom_point() + labs(colour = "Continent") +
  scale_x_log10()

ggplot(country_demo_2007) + aes(x = gdpPercap, y = lifeExp,
                                colour = continent) +
  geom_point() + labs(colour = "Planet")

ggplot(country_demo_2007) + aes(x = gdpPercap, y = lifeExp,
                                colour = continent) +
  geom_point() + labs(colour = "Continent") +
  scale_x_log10() + ggtitle("Life expectancy and GDP per Capita, 2007") +
  xlab("GDP per capita (log scale)") +
  ylab("Life expectancy")

ggplot(country_demo_2007) + aes(x = gdpPercap, y = lifeExp,
                                colour = continent,
                                size = pop) +
  geom_point() + scale_x_log10()

ggplot(country_demo_2007) + aes(x = gdpPercap, y = lifeExp,
                                colour = continent,
                                size = pop) +
  geom_point() + scale_x_log10() + 
  labs(colour = "Continent", size = "Population") +
  ggtitle("Life expectancy and GDP per Capita, 2007") +
  xlab("GDP per capita (log scale)") +
  ylab("Life expectancy")

ggplot(country_demo_2007) + aes(x = gdpPercap, y = lifeExp,
                                colour = continent,
                                size = pop) +
  geom_point() + scale_x_log10() + 
  labs(colour = "Continent", size = "Population") +
  ggtitle("Life expectancy and GDP per Capita, 2007") +
  xlab("GDP per capita (log scale)") +
  ylab("Life expectancy") +
  geom_label_repel(data = subset(country_demo_2007, country == "Iron City" | country == "Zalem"),
                 aes(label = country),
                 box.padding   = 0.35, 
                 point.padding = 0.5,
                 segment.color = "blue",
                 force = 200,
                 size = 5)

ggplot(country_demo_2007) + aes(x = pop, y = lifeExp,
                                colour = continent,
                                size = gdpPercap) +
  geom_point() +
  scale_x_log10() +
  labs(colour = "Continent", size = "Population") +
  ggtitle("Life expectancy and population, 2007") +
  xlab("Population (log scale)") +
  ylab("Life expectancy")

ggplot(country_demo_2007) + aes(x = pop, y = lifeExp,
                                colour = continent,
                                size = gdpPercap) +
  geom_point() +
  scale_x_log10() + 
  labs(colour = "Continent", size = "Population") +
  ggtitle("Life expectancy and population, 2007") +
  xlab("Population (log scale") +
  ylab("Life expectancy") +
  facet_wrap(~ continent)

ggplot(country_demo_2007) + aes(x = pop, y = lifeExp,
                                colour = continent,
                                size = gdpPercap) +
  geom_point() +
  scale_x_log10() + 
  labs(colour = "Continent", size = "Population") +
  ggtitle("Life expectancy and population, 2007") +
  xlab("Population (log scale") +
  ylab("Life expectancy") +
  facet_wrap(~ continent) + 
  geom_label_repel(data = subset(country_demo_2007, country == "Iron City" | country == "Zalem"),
                   aes(label = country),
                   box.padding   = 0.35,
                   point.padding = 0.5,
                   segment.color = "blue",
                   force = 200,
                   size = 3)

ggplot(country_demo_2007) + aes(x = gdpPercap, y = lifeExp) +
  geom_point() + scale_x_log10() +
  facet_wrap(~ continent)

ggplot(country_demo_2007) + aes(x = gdpPercap, y = lifeExp) +
  geom_point() + scale_x_log10() +
  facet_wrap(~ continent) + xlab("GDP per capita (log scale)") +
  ylab("Life expectancy")

ggplot(country_demo) + aes(x = gdpPercap, y = lifeExp,
                           colour = continent,
                           size = pop) +
  geom_point() +
  scale_x_log10() +
  facet_wrap(~ year) +
  labs(colour = "Continent", size = "Population") +
  ggtitle("Life expectancy and GDP per capita") +
  xlab("GDP per capita (log scale)") +
  ylab("Life expectancy")

ggplot(country_demo) + aes(x = pop, y = lifeExp,
                           colour = continent,
                           size = gdpPercap) +
  geom_point() +
  scale_x_log10() +
  facet_wrap(~ year) + 
  labs(colour = "Continent", size = "GDP per capita") +
  ggtitle("Life expectancy and population") +
  xlab("Population (log scale)") +
  ylab("Life expectancy")

3. Aggregate plots

country_demo_by_year <- group_by(country_demo, year)
country_demo_by_year

## # A tibble: 1,706 x 7
## # Groups:   year [12]
##       ID country     continent  year lifeExp      pop gdpPercap
##    <int> <chr>       <chr>     <int>   <dbl>    <int>     <dbl>
##  1     1 Afghanistan Asia       1952    28.8  8425333      779.
##  2     2 Afghanistan Asia       1957    30.3  9240934      821.
##  3     3 Afghanistan Asia       1962    32.0 10267083      853.
##  4     4 Afghanistan Asia       1967    34.0 11537966      836.
##  5     5 Afghanistan Asia       1972    36.1 13079460      740.
##  6     6 Afghanistan Asia       1977    38.4 14880372      786.
##  7     7 Afghanistan Asia       1982    39.9 12881816      978.
##  8     8 Afghanistan Asia       1987    40.8 13867957      852.
##  9     9 Afghanistan Asia       1992    41.7 16317921      649.
## 10    10 Afghanistan Asia       1997    41.8 22227415      635.
## # ... with 1,696 more rows

country_demo %>%
  group_by(year) %>%
  summarise(
    mean_life_exp = mean(lifeExp),
    tot_pop = sum(as.numeric(pop)))

## `summarise()` ungrouping output (override with `.groups` argument)

## # A tibble: 12 x 3
##     year mean_life_exp    tot_pop
##    <int>         <dbl>      <dbl>
##  1  1952          49.1 2406957150
##  2  1957          51.5 2664404580
##  3  1962          53.6 2899782974
##  4  1967          55.7 3217478384
##  5  1972          57.6 3576977158
##  6  1977          59.6 3930045807
##  7  1982          61.5 4289436840
##  8  1987          63.2 4691477418
##  9  1992          64.2 5110710260
## 10  1997          65.0 5515204472
## 11  2002          65.7 5886977579
## 12  2007          67.0 6257680511

country_demo %>%
  group_by(year) %>%
  summarise(
    median_GDP_percap = median(gdpPercap),
    max_pop = max(pop)
  )

## `summarise()` ungrouping output (override with `.groups` argument)

## # A tibble: 12 x 3
##     year median_GDP_percap    max_pop
##    <int>             <dbl>      <int>
##  1  1952             1969.  556263527
##  2  1957             2173.  637408000
##  3  1962             2335.  665770000
##  4  1967             2678.  754550000
##  5  1972             3339.  862030000
##  6  1977             3799.  943455000
##  7  1982             4216. 1000281000
##  8  1987             4280. 1084035000
##  9  1992             4386. 1164970000
## 10  1997             4782. 1230075000
## 11  2002             5320. 1280400000
## 12  2007             6548. 1318683096

country_demo %>%
  group_by(year) %>%
  summarise(
    max_GDP_percap = max(gdpPercap),
    min_pop = min(pop)
  )

## `summarise()` ungrouping output (override with `.groups` argument)

## # A tibble: 12 x 3
##     year max_GDP_percap min_pop
##    <int>          <dbl>   <int>
##  1  1952        108382.   60011
##  2  1957        113523.   61325
##  3  1962         95458.   65345
##  4  1967         80895.   70787
##  5  1972        109348.   76595
##  6  1977         59265.   86796
##  7  1982         33693.   98593
##  8  1987         31541.  110812
##  9  1992         34933.  125911
## 10  1997         41283.  145608
## 11  2002         44684.  170372
## 12  2007         49357.     666

country_demo %>%
  group_by(year, continent) %>%
  summarise(
    mean_life_exp = mean(lifeExp),
    tot_pop = sum(as.numeric(pop))
  )

## `summarise()` regrouping output by 'year' (override with `.groups` argument)

## # A tibble: 60 x 4
## # Groups:   year [12]
##     year continent mean_life_exp    tot_pop
##    <int> <chr>             <dbl>      <dbl>
##  1  1952 Africa             39.1  237640501
##  2  1952 Americas           53.3  345152446
##  3  1952 Asia               46.3 1395357351
##  4  1952 Europe             64.4  418120846
##  5  1952 Oceania            69.3   10686006
##  6  1957 Africa             41.3  264837738
##  7  1957 Americas           56.0  386953916
##  8  1957 Asia               49.3 1562780599
##  9  1957 Europe             66.7  437890351
## 10  1957 Oceania            70.3   11941976
## # ... with 50 more rows

country_demo %>%
  group_by(continent, year) %>%
  summarise(
    max_life_exp = max(lifeExp),
    min_pop = min(pop)
  )

## `summarise()` regrouping output by 'continent' (override with `.groups` argument)

## # A tibble: 60 x 4
## # Groups:   continent [5]
##    continent  year max_life_exp min_pop
##    <chr>     <int>        <dbl>   <int>
##  1 Africa     1952         52.7   60011
##  2 Africa     1957         58.1   61325
##  3 Africa     1962         60.2   65345
##  4 Africa     1967         61.6   70787
##  5 Africa     1972         64.3   76595
##  6 Africa     1977         67.1   86796
##  7 Africa     1982         69.9   98593
##  8 Africa     1987         71.9  110812
##  9 Africa     1992         73.6  125911
## 10 Africa     1997         74.8  145608
## # ... with 50 more rows

country_demo_by_year_v2 <- country_demo %>%
  group_by(year) %>%
  summarise(
    tot_pop = sum(as.numeric(pop)),
    mean_life_exp = mean(lifeExp)
  )

## `summarise()` ungrouping output (override with `.groups` argument)

country_demo_by_year_v2

## # A tibble: 12 x 3
##     year    tot_pop mean_life_exp
##    <int>      <dbl>         <dbl>
##  1  1952 2406957150          49.1
##  2  1957 2664404580          51.5
##  3  1962 2899782974          53.6
##  4  1967 3217478384          55.7
##  5  1972 3576977158          57.6
##  6  1977 3930045807          59.6
##  7  1982 4289436840          61.5
##  8  1987 4691477418          63.2
##  9  1992 5110710260          64.2
## 10  1997 5515204472          65.0
## 11  2002 5886977579          65.7
## 12  2007 6257680511          67.0

ggplot(country_demo_by_year_v2) + aes(x = year,
                                       y = tot_pop) +
  geom_point()

country_demo %>%
  group_by(year) %>%
  summarise(
    tot_pop = sum(as.numeric(pop))
  ) %>%
  ggplot(aes(x = year, y = tot_pop)) +
  geom_point()

## `summarise()` ungrouping output (override with `.groups` argument)

ggplot(country_demo_by_year_v2) + aes(x = year,
                                      y = tot_pop) +
  geom_point() + expand_limits(y = 0)

country_demo_by_year_v3 <- summarise(group_by(country_demo,
                                              year, continent),
                                     tot_pop = sum(as.numeric(pop)))

## `summarise()` regrouping output by 'year' (override with `.groups` argument)

country_demo_by_year_v3

## # A tibble: 60 x 3
## # Groups:   year [12]
##     year continent    tot_pop
##    <int> <chr>          <dbl>
##  1  1952 Africa     237640501
##  2  1952 Americas   345152446
##  3  1952 Asia      1395357351
##  4  1952 Europe     418120846
##  5  1952 Oceania     10686006
##  6  1957 Africa     264837738
##  7  1957 Americas   386953916
##  8  1957 Asia      1562780599
##  9  1957 Europe     437890351
## 10  1957 Oceania     11941976
## # ... with 50 more rows

ggplot(country_demo_by_year_v3) + aes(x = year, y = tot_pop,
                                      colour = continent) +
  geom_point()

ggplot(country_demo_by_year_v3) + aes(x = year, y = tot_pop,
                                      colour = continent) +
  geom_point() + ggtitle("Total population by year") +
  xlab("Year") +
  ylab("Total population") +
  labs(colour = "Continent")

ggplot(country_demo_by_year_v3) + aes(x = year, y = tot_pop,
                                      colour = continent) +
  geom_point() + ggtitle("Total population by year") +
  xlab("Year") +
  ylab("Total population") +
  labs(colour = "Planet")

4. Line charts

names(country_demo_by_year_v2)

## [1] "year"          "tot_pop"       "mean_life_exp"

ggplot(country_demo_by_year_v2) + aes(x = year, y = tot_pop) +
  geom_line()

ggplot(country_demo_by_year_v2) + aes(x = year, y = tot_pop) +
  geom_line(linetype = 2) + expand_limits(y = 0)

ggplot(country_demo_by_year_v2) + aes(x = year, y = tot_pop) +
  geom_line() + expand_limits(y = 0) +
  ggtitle("Total population by year") +
  xlab("Year") +
  ylab("Total population")

names(country_demo_by_year_v3)

## [1] "year"      "continent" "tot_pop"

ggplot(country_demo_by_year_v3) + aes(x = year,
                                      y = tot_pop,
                                      colour = continent) + 
  geom_line(aes(linetype = continent))

ggplot(country_demo_by_year_v3) + aes(x = year,
                                      y = tot_pop,
                                      colour = continent) + 
  geom_line(aes(linetype = continent), size = 1.5) + ggtitle("Total population by year") +
  xlab("Year") +
  ylab("Total population") +
  labs(colour = "Continent")

5. Column and bar charts

country_demo_by_continent_2007 <- country_demo %>%
  filter(year == 2007) %>%
  group_by(continent) %>%
  summarise(
    tot_pop = sum(as.numeric(pop)),
    mean_life_exp = mean(lifeExp)
  )

## `summarise()` ungrouping output (override with `.groups` argument)

country_demo_by_continent_2007  

## # A tibble: 5 x 3
##   continent    tot_pop mean_life_exp
##   <chr>          <dbl>         <dbl>
## 1 Africa     929539692          54.8
## 2 Americas   905538516          73.0
## 3 Asia      3811953827          70.7
## 4 Europe     586098529          77.6
## 5 Oceania     24549947          80.7

ggplot(country_demo_by_continent_2007) + aes(x = continent,
                                             y = mean_life_exp) +
  geom_col()

ggplot(country_demo_by_continent_2007) + aes(x = continent,
                                             y = mean_life_exp) +
  geom_col() + xlab("Continent") + ylab("Mean life expectancy") +
  coord_cartesian(ylim = c(35,85))

ggplot(country_demo_by_continent_2007) + aes(x = continent,
                                             y = mean_life_exp) +
  geom_col(fill = "green", colour = "red") + xlab("Continent") + ylab("Mean life expectancy") +
  coord_cartesian(ylim = c(35,85))

ggplot(country_demo_by_year_v3) + aes(x = continent,
                                      y = tot_pop) +
  geom_col() + xlab("Continent") + ylab("Total population") +
  ggtitle("Total population by continent")

ggplot(country_demo_by_year_v3) + aes(x = continent,
                                      y = tot_pop,
                                      fill = continent) +
  geom_col() + xlab("Continent") + ylab("Total population") +
  ggtitle("Total population by continent")

ggplot(country_demo_by_year_v3) + aes(x = continent,
                                      y = tot_pop,
                                      fill = continent) +
  geom_col() + xlab("Continent") + ylab("Total population") +
  ggtitle("Total population by continent") +
  scale_fill_grey()

ggplot(country_demo_by_year_v3) + aes(x = continent,
                                      y = tot_pop,
                                      fill = continent) +
  geom_col() + xlab("Continent") + ylab("Total population") +
  ggtitle("Total population by continent") +
  scale_fill_brewer(palette = "Dark6") +
  labs(fill = "Planet")

## Warning in pal_name(palette, type): Unknown palette Dark6

ggplot(country_demo_by_year_v3) + aes(x = continent,
                                      y = tot_pop) +
  geom_col() + xlab("Continent") + ylab("Total population") +
  ggtitle("Total population by continent")+ coord_flip()

ggplot(country_demo_by_year_v3) + aes(x = continent,
                                      y = tot_pop,
                                      fill = continent) +
  geom_col() + xlab("Continent") + ylab("Total population") +
  ggtitle("Total population by continent")+ coord_flip() +
  labs(fill = "Continent")

Plot for Oceania subset

country_demo_oceania_2007 <- country_demo %>%
  filter(continent == "Oceania",
         year == 2007)

country_demo_oceania_2007

##     ID     country continent year lifeExp      pop gdpPercap
## 1   72   Australia   Oceania 2007  81.235 20434176  34435.37
## 2 1104 New Zealand   Oceania 2007  80.204  4115771  25185.01

ggplot(country_demo_oceania_2007) + aes(x = country, y = pop) +
  geom_col() + ggtitle("Population, Oceania, 2007") +
  xlab("Country") + ylab("Population")

ggplot(country_demo_oceania_2007) + aes(x = country, y = pop) +
  geom_col(fill = "yellow", colour = "dark blue") + ggtitle("Population, Oceania, 2007") +
  xlab("Country") + ylab("Population")

ggplot(country_demo_oceania_2007) + aes(x = country, y = pop) +
  geom_col(fill = "yellow", colour = "dark blue") + ggtitle("Population, Oceania, 2007") +
  xlab("Country") + ylab("Population") + coord_flip()

ggplot(country_demo_oceania_2007) + aes(x = reorder(country, pop), y = pop) +
  geom_col(fill = "yellow", colour = "dark blue") + ggtitle("Population, Oceania, 2007") +
  xlab("Country") + ylab("Population") + coord_flip()

6. Histograms

head(country_demo_2007, 10)

##     ID     country continent year lifeExp       pop  gdpPercap
## 1   12 Afghanistan      Asia 2007  43.828  31889923   974.5803
## 2   24     Albania    Europe 2007  76.423   3600523  5937.0295
## 3   36     Algeria    Africa 2007  72.301  33333216  6223.3675
## 4   48      Angola    Africa 2007  42.731  12420476  4797.2313
## 5   60   Argentina  Americas 2007  75.320  40301927 12779.3796
## 6   72   Australia   Oceania 2007  81.235  20434176 34435.3674
## 7   84     Austria    Europe 2007  79.829   8199783 36126.4927
## 8   96     Bahrain      Asia 2007  75.635    708573 29796.0483
## 9  108  Bangladesh      Asia 2007  64.062 150448339  1391.2538
## 10 120     Belgium    Europe 2007  79.441  10392226 33692.6051

ggplot(country_demo_2007) + aes(lifeExp) +
  geom_histogram()

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

ggplot(country_demo_2007) + aes(lifeExp) +
  geom_histogram(fill = "blue") + xlab("Life expectancy") +
  ylab("Count") + ggtitle("Histogram of life expectancy, 2007")

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

ggplot(country_demo_2007) + aes(lifeExp) +
  geom_histogram(fill = "blue", binwidth = 5) + xlab("Life expectancy") +
  ylab("Count") + ggtitle("Histogram of life expectancy, 2007")

ggplot(country_demo_2007) + aes(x = gdpPercap) +
  geom_histogram(fill = "Orange", colour = "blue") + xlab("GDP per capita") +
  ylab("Count") + ggtitle("Histogram of GDP per capita, 2007")

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

ggplot(country_demo_2007) + aes(x = gdpPercap) +
  geom_histogram(fill = "Orange", colour = "blue") + 
  scale_x_log10() +
  xlab("GDP per capita (log scale)") +
  ylab("Count") + ggtitle("Histogram of GDP per capita, 2007")

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

7. Boxplots

ggplot(country_demo_2007) + aes(x = continent, y = lifeExp) +
  geom_boxplot()

ggplot(country_demo_2007) + aes(x = continent, y = gdpPercap) +
  geom_boxplot()

ggplot(country_demo_2007) + aes(x = continent, y = gdpPercap,
                                fill = continent) +
  geom_boxplot() +
  labs(fill = "Alita")

ggplot(country_demo) + aes(x = continent, y = lifeExp) +
  geom_boxplot(fill = "yellow") +
  facet_wrap( ~ year) + xlab("Continent") + ylab("Life expectancy") +
  ggtitle("Life expectancy by continent and year") +
  theme(axis.text = element_text(size = 9),
        axis.title = element_text(size = 10, face = "bold"),
        strip.text.x = element_text(size = 9, face = "italic"))

8. Violin plots

names(country_demo)

## [1] "ID"        "country"   "continent" "year"      "lifeExp"   "pop"      
## [7] "gdpPercap"

Remove scientific notation

options(scipen = 999)

Basic violin plot

ggplot(country_demo_2007) + aes(factor(continent), y = gdpPercap) + 
  geom_violin()

Scale maximum width proportional to size

ggplot(country_demo_2007) + aes(factor(continent), y = gdpPercap) + 
  geom_violin(scale = "count")

Scale maximum width to 1

ggplot(country_demo_2007) + aes(factor(continent), y = gdpPercap) + 
  geom_violin(scale = "width")

Disable trim to the range of the data

ggplot(country_demo_2007) + aes(factor(continent), y = gdpPercap) + 
  geom_violin(scale = "width", trim = FALSE)

Adjusting the fit

ggplot(country_demo_2007) + aes(factor(continent), y = gdpPercap) + 
  geom_violin(adjust = 0.5, trim = FALSE)

Add colour

ggplot(country_demo_2007) + aes(factor(continent), y = gdpPercap, fill = continent) + 
  geom_violin(scale = "width", trim = FALSE) +
  ggtitle("Violin plot of GDP per capita by continent") +
  xlab("Continent") + ylab("GDP per capita") +
  labs(fill = "Continent")

Some modifications

ggplot(country_demo_2007) + aes(factor(continent), y = gdpPercap) + 
  geom_violin(scale = "width", 
              fill = "grey", colour = "#336699", trim = FALSE)

Draw quantiles

ggplot(country_demo_2007) + aes(factor(continent), y = gdpPercap) + 
  geom_violin(scale = "width", 
              fill = "grey", colour = "#336699", trim = FALSE,
              draw_quantiles = c(0.25, 0.5, 0.75))

ggplot(country_demo_2007) + aes(factor(continent), y = gdpPercap, fill = continent) + 
  geom_violin(scale = "width", trim = FALSE,
              draw_quantiles = c(0.25, 0.5, 0.75)) +
  ggtitle("Violin plot of GDP per capita by continent") +
  xlab("Continent") + ylab("GDP per capita") +
  labs(fill = "Continent")

9. Correlation plots

library(ggpubr)
ggplot(country_demo) + aes(x = pop, y = gdpPercap) +
  geom_point(shape = 1, colour = "green") + scale_x_log10() + scale_y_log10() +
  xlab("Population (log scale)") + ylab("GDP per Capita (log scale)") +
  ggtitle("GDP per capita and population") +
  geom_smooth(method = lm) +
  stat_regline_equation(label.x = 8, label.y = 4) +
  stat_cor(method = "pearson", label.x = 8, label.y = 3.8) +
  geom_label_repel(data = subset(country_demo_2007, country == "Iron City" | country == "Zalem"),
                   aes(label = country),
                   box.padding   = 0.35, 
                   point.padding = 0.5,
                   segment.color = "blue",
                   force = 200)

## `geom_smooth()` using formula 'y ~ x'

names(country_demo)

## [1] "ID"        "country"   "continent" "year"      "lifeExp"   "pop"      
## [7] "gdpPercap"

corr_matrix <- round(cor(country_demo[, c(5,6,7)]),2)
corr_matrix

##           lifeExp   pop gdpPercap
## lifeExp      1.00  0.06      0.58
## pop          0.06  1.00     -0.03
## gdpPercap    0.58 -0.03      1.00

rownames(corr_matrix) <- c("Life Expentency", "Population", "GDP per Capita")
colnames(corr_matrix) <- c("Life Expentency", "Population", "GDP per Capita")
corr_matrix

##                 Life Expentency Population GDP per Capita
## Life Expentency            1.00       0.06           0.58
## Population                 0.06       1.00          -0.03
## GDP per Capita             0.58      -0.03           1.00

library(reshape2)
corr_matrix_long <- melt(corr_matrix)
corr_matrix_long

##              Var1            Var2 value
## 1 Life Expentency Life Expentency  1.00
## 2      Population Life Expentency  0.06
## 3  GDP per Capita Life Expentency  0.58
## 4 Life Expentency      Population  0.06
## 5      Population      Population  1.00
## 6  GDP per Capita      Population -0.03
## 7 Life Expentency  GDP per Capita  0.58
## 8      Population  GDP per Capita -0.03
## 9  GDP per Capita  GDP per Capita  1.00

ggplot(data = corr_matrix_long, 
       aes(x = Var1, y = Var2, fill = value)) + 
  geom_tile() +
  ggtitle("Correlation Heat Map") +
  xlab("") + ylab("") + labs(fill = "Correlation")

ggplot(data = corr_matrix_long, 
       aes(x = Var1, y = Var2, fill = value)) + 
  geom_tile() +
  ggtitle("Correlation Heat Map") +
  xlab("") + ylab("") + labs(fill = "Correlation") +
  scale_fill_gradient(low = "white", high = "steelblue")

ggplot(data = corr_matrix_long, 
       aes(x = Var1, y = Var2, fill = value)) + 
  geom_tile() +
  ggtitle("Correlation Heat Map") +
  xlab("") + ylab("") + labs(fill = "Correlation") +
  scale_fill_gradient(low = "white", high = "black")

ggplot(data = corr_matrix_long, 
       aes(x = Var1, y = Var2, fill = value)) + 
  geom_tile() +
  ggtitle("Correlation Heat Map") +
  xlab("") + ylab("") + labs(fill = "Correlation") +
  scale_fill_gradient(low = "blue", high = "purple")

ggplot(data = corr_matrix_long, 
       aes(x = Var1, y = Var2, fill = value)) + 
  geom_tile() +
  ggtitle("Correlation Heat Map") +
  xlab("") + ylab("") + labs(fill = "Correlation") +
  scale_fill_gradient(low = "white", high = "darkgreen") +
  geom_text(aes(Var2, Var1, label = value), color = "black", size = 5)

get_lower <- function(corr_matrix) {
  corr_matrix[upper.tri(corr_matrix)] <- NA
  return(corr_matrix)
}


lower_corr_matrix <- get_lower(corr_matrix)
lower_corr_matrix

##                 Life Expentency Population GDP per Capita
## Life Expentency            1.00         NA             NA
## Population                 0.06       1.00             NA
## GDP per Capita             0.58      -0.03              1

lower_corr_matrix_long <- melt(lower_corr_matrix, na.rm = TRUE)
lower_corr_matrix_long

##              Var1            Var2 value
## 1 Life Expentency Life Expentency  1.00
## 2      Population Life Expentency  0.06
## 3  GDP per Capita Life Expentency  0.58
## 5      Population      Population  1.00
## 6  GDP per Capita      Population -0.03
## 9  GDP per Capita  GDP per Capita  1.00

ggplot(data = lower_corr_matrix_long, 
       aes(x = Var1, y = Var2, fill = value)) + 
  geom_tile() +
  ggtitle("Correlation Heat Map") +
  xlab("") + ylab("") + labs(fill = "Correlation") +
  scale_fill_gradient(low = "white", high = "darkgreen") +
  geom_text(aes(Var2, Var1, label = value), color = "black", size = 5)

ggplot(data = lower_corr_matrix_long, 
       aes(x = Var1, y = Var2, fill = value)) + 
  geom_tile() +
  ggtitle("Correlation Heat Map") +
  xlab("") + ylab("") + labs(fill = "Correlation") +
  scale_fill_gradient(low = "white", high = "darkgreen") +
  geom_text(aes(Var1, Var2, label = value), color = "black", size = 5) +
  theme_minimal() +
  theme(legend.justification = c(1, 0),
        legend.position = c(0.6, 0.8),
        legend.direction = "horizontal")

ggplot(data = lower_corr_matrix_long, 
       aes(x = Var1, y = Var2, fill = value)) + 
  geom_tile() +
  ggtitle("Correlation Heat Map") +
  xlab("") + ylab("") + labs(fill = "Correlation") +
  scale_fill_gradient(low = "white", high = "darkgreen") +
  geom_text(aes(Var1, Var2, label = value), color = "black", size = 5) +
  theme_classic() +
  theme(legend.justification = c(1, 0),
        legend.position = c(0.6, 0.8),
        legend.direction = "horizontal")

country_demo_2 <- country_demo
names(country_demo_2)

## [1] "ID"        "country"   "continent" "year"      "lifeExp"   "pop"      
## [7] "gdpPercap"

# names(country_demo_2)[5] <- "Life Expectency"
# names(country_demo_2)[6] <- "Population"
# names(country_demo_2)[7] <- "GDP per Capita"

names(country_demo_2)[5:7] <- c("Life Expectency",
                                "Population",
                                "GDP per Capita")


library(GGally)

## Registered S3 method overwritten by 'GGally':
##   method from   
##   +.gg   ggplot2

ggpairs(country_demo_2[, c(5:7)])

ggpairs(country_demo_2[, c(5:7)]) + theme_transparent()

ggpairs(country_demo_2[, c(5:7)]) + theme_update()

10. Pie Charts

library(dplyr)
country_continent <- country_demo %>% group_by(continent) %>% summarize(number = n())

## `summarise()` ungrouping output (override with `.groups` argument)

country_continent

## # A tibble: 5 x 2
##   continent number
##   <chr>      <int>
## 1 Africa       624
## 2 Americas     302
## 3 Asia         396
## 4 Europe       360
## 5 Oceania       24

pie(country_continent$number, country_continent$continent)