introduction to the Tidyvese

Quarto

Quarto enables you to weave together content and executable code into a finished document. To learn more about Quarto see https://quarto.org.

Running Code

When you click the Render button a document will be generated that includes both content and the output of embedded code. You can embed code like this:

library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.1
✔ ggplot2   3.4.4     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.0
✔ purrr     1.0.2     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(gapminder)
library(ggplot2)
library(dplyr)
library(skimr)

#Show the data

gapminder

# A tibble: 1,704 × 6
   country     continent  year lifeExp      pop gdpPercap
   <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
 1 Afghanistan Asia       1952    28.8  8425333      779.
 2 Afghanistan Asia       1957    30.3  9240934      821.
 3 Afghanistan Asia       1962    32.0 10267083      853.
 4 Afghanistan Asia       1967    34.0 11537966      836.
 5 Afghanistan Asia       1972    36.1 13079460      740.
 6 Afghanistan Asia       1977    38.4 14880372      786.
 7 Afghanistan Asia       1982    39.9 12881816      978.
 8 Afghanistan Asia       1987    40.8 13867957      852.
 9 Afghanistan Asia       1992    41.7 16317921      649.
10 Afghanistan Asia       1997    41.8 22227415      635.
# ℹ 1,694 more rows

#Filter

gamp_2007 <- gapminder %>%
  filter (year == 2007)

gamp_usa <- gapminder %>%
  filter (country == "United States")
gamp_usa

# A tibble: 12 × 6
   country       continent  year lifeExp       pop gdpPercap
   <fct>         <fct>     <int>   <dbl>     <int>     <dbl>
 1 United States Americas   1952    68.4 157553000    13990.
 2 United States Americas   1957    69.5 171984000    14847.
 3 United States Americas   1962    70.2 186538000    16173.
 4 United States Americas   1967    70.8 198712000    19530.
 5 United States Americas   1972    71.3 209896000    21806.
 6 United States Americas   1977    73.4 220239000    24073.
 7 United States Americas   1982    74.6 232187835    25010.
 8 United States Americas   1987    75.0 242803533    29884.
 9 United States Americas   1992    76.1 256894189    32004.
10 United States Americas   1997    76.8 272911760    35767.
11 United States Americas   2002    77.3 287675526    39097.
12 United States Americas   2007    78.2 301139947    42952.

gamp_usa_2007 <- gapminder %>%
  filter (year == 2007, country == "United States")
gamp_usa_2007

# A tibble: 1 × 6
  country       continent  year lifeExp       pop gdpPercap
  <fct>         <fct>     <int>   <dbl>     <int>     <dbl>
1 United States Americas   2007    78.2 301139947    42952.

gamp_china_2002 <- gapminder %>%
  filter (year == 2002, country == "China")

# The Arrange verp

gapminder %>%
  arrange(desc(gdpPercap))

# A tibble: 1,704 × 6
   country   continent  year lifeExp     pop gdpPercap
   <fct>     <fct>     <int>   <dbl>   <int>     <dbl>
 1 Kuwait    Asia       1957    58.0  212846   113523.
 2 Kuwait    Asia       1972    67.7  841934   109348.
 3 Kuwait    Asia       1952    55.6  160000   108382.
 4 Kuwait    Asia       1962    60.5  358266    95458.
 5 Kuwait    Asia       1967    64.6  575003    80895.
 6 Kuwait    Asia       1977    69.3 1140357    59265.
 7 Norway    Europe     2007    80.2 4627926    49357.
 8 Kuwait    Asia       2007    77.6 2505559    47307.
 9 Singapore Asia       2007    80.0 4553009    47143.
10 Norway    Europe     2002    79.0 4535591    44684.
# ℹ 1,694 more rows

gapminder %>%
  filter (year == 2007) %>%
  arrange(desc(gdpPercap))

# A tibble: 142 × 6
   country          continent  year lifeExp       pop gdpPercap
   <fct>            <fct>     <int>   <dbl>     <int>     <dbl>
 1 Norway           Europe     2007    80.2   4627926    49357.
 2 Kuwait           Asia       2007    77.6   2505559    47307.
 3 Singapore        Asia       2007    80.0   4553009    47143.
 4 United States    Americas   2007    78.2 301139947    42952.
 5 Ireland          Europe     2007    78.9   4109086    40676.
 6 Hong Kong, China Asia       2007    82.2   6980412    39725.
 7 Switzerland      Europe     2007    81.7   7554661    37506.
 8 Netherlands      Europe     2007    79.8  16570613    36798.
 9 Canada           Americas   2007    80.7  33390141    36319.
10 Iceland          Europe     2007    81.8    301931    36181.
# ℹ 132 more rows

gapminder %>%
  arrange(desc(lifeExp))

# A tibble: 1,704 × 6
   country          continent  year lifeExp       pop gdpPercap
   <fct>            <fct>     <int>   <dbl>     <int>     <dbl>
 1 Japan            Asia       2007    82.6 127467972    31656.
 2 Hong Kong, China Asia       2007    82.2   6980412    39725.
 3 Japan            Asia       2002    82   127065841    28605.
 4 Iceland          Europe     2007    81.8    301931    36181.
 5 Switzerland      Europe     2007    81.7   7554661    37506.
 6 Hong Kong, China Asia       2002    81.5   6762476    30209.
 7 Australia        Oceania    2007    81.2  20434176    34435.
 8 Spain            Europe     2007    80.9  40448191    28821.
 9 Sweden           Europe     2007    80.9   9031088    33860.
10 Israel           Asia       2007    80.7   6426679    25523.
# ℹ 1,694 more rows

# The mutate verp

gapminder %>%
  mutate(pop = pop /1000000) %>%
  arrange (desc(pop))

# A tibble: 1,704 × 6
   country continent  year lifeExp   pop gdpPercap
   <fct>   <fct>     <int>   <dbl> <dbl>     <dbl>
 1 China   Asia       2007    73.0 1319.     4959.
 2 China   Asia       2002    72.0 1280.     3119.
 3 China   Asia       1997    70.4 1230.     2289.
 4 China   Asia       1992    68.7 1165.     1656.
 5 India   Asia       2007    64.7 1110.     2452.
 6 China   Asia       1987    67.3 1084.     1379.
 7 India   Asia       2002    62.9 1034.     1747.
 8 China   Asia       1982    65.5 1000.      962.
 9 India   Asia       1997    61.8  959      1459.
10 China   Asia       1977    64.0  943.      741.
# ℹ 1,694 more rows

# Jdp per capita by pop

gapminder %>%
  mutate (gdp = gdpPercap * pop) %>%
  filter(year == 2007)%>%
  arrange (desc(gdp))

# A tibble: 142 × 7
   country        continent  year lifeExp        pop gdpPercap     gdp
   <fct>          <fct>     <int>   <dbl>      <int>     <dbl>   <dbl>
 1 United States  Americas   2007    78.2  301139947    42952. 1.29e13
 2 China          Asia       2007    73.0 1318683096     4959. 6.54e12
 3 Japan          Asia       2007    82.6  127467972    31656. 4.04e12
 4 India          Asia       2007    64.7 1110396331     2452. 2.72e12
 5 Germany        Europe     2007    79.4   82400996    32170. 2.65e12
 6 United Kingdom Europe     2007    79.4   60776238    33203. 2.02e12
 7 France         Europe     2007    80.7   61083916    30470. 1.86e12
 8 Brazil         Americas   2007    72.4  190010647     9066. 1.72e12
 9 Italy          Europe     2007    80.5   58147733    28570. 1.66e12
10 Mexico         Americas   2007    76.2  108700891    11978. 1.30e12
# ℹ 132 more rows

# life expectancy by months

gapminder %>%
  mutate (lifeExp = lifeExp * 12)

# A tibble: 1,704 × 6
   country     continent  year lifeExp      pop gdpPercap
   <fct>       <fct>     <int>   <dbl>    <int>     <dbl>
 1 Afghanistan Asia       1952    346.  8425333      779.
 2 Afghanistan Asia       1957    364.  9240934      821.
 3 Afghanistan Asia       1962    384. 10267083      853.
 4 Afghanistan Asia       1967    408. 11537966      836.
 5 Afghanistan Asia       1972    433. 13079460      740.
 6 Afghanistan Asia       1977    461. 14880372      786.
 7 Afghanistan Asia       1982    478. 12881816      978.
 8 Afghanistan Asia       1987    490. 13867957      852.
 9 Afghanistan Asia       1992    500. 16317921      649.
10 Afghanistan Asia       1997    501. 22227415      635.
# ℹ 1,694 more rows

# add a new coulmn for life expectancy in months

gapminder %>%
  mutate (lifeExp_months = lifeExp * 12)

# A tibble: 1,704 × 7
   country     continent  year lifeExp      pop gdpPercap lifeExp_months
   <fct>       <fct>     <int>   <dbl>    <int>     <dbl>          <dbl>
 1 Afghanistan Asia       1952    28.8  8425333      779.           346.
 2 Afghanistan Asia       1957    30.3  9240934      821.           364.
 3 Afghanistan Asia       1962    32.0 10267083      853.           384.
 4 Afghanistan Asia       1967    34.0 11537966      836.           408.
 5 Afghanistan Asia       1972    36.1 13079460      740.           433.
 6 Afghanistan Asia       1977    38.4 14880372      786.           461.
 7 Afghanistan Asia       1982    39.9 12881816      978.           478.
 8 Afghanistan Asia       1987    40.8 13867957      852.           490.
 9 Afghanistan Asia       1992    41.7 16317921      649.           500.
10 Afghanistan Asia       1997    41.8 22227415      635.           501.
# ℹ 1,694 more rows

# use filter, murtate and arrange

gapminder %>%
  filter (year == 2007) %>%
  mutate (lifeExpMopnths = lifeExp * 12) %>%
  arrange (desc(lifeExpMopnths))

# A tibble: 142 × 7
   country          continent  year lifeExp       pop gdpPercap lifeExpMopnths
   <fct>            <fct>     <int>   <dbl>     <int>     <dbl>          <dbl>
 1 Japan            Asia       2007    82.6 127467972    31656.           991.
 2 Hong Kong, China Asia       2007    82.2   6980412    39725.           986.
 3 Iceland          Europe     2007    81.8    301931    36181.           981.
 4 Switzerland      Europe     2007    81.7   7554661    37506.           980.
 5 Australia        Oceania    2007    81.2  20434176    34435.           975.
 6 Spain            Europe     2007    80.9  40448191    28821.           971.
 7 Sweden           Europe     2007    80.9   9031088    33860.           971.
 8 Israel           Asia       2007    80.7   6426679    25523.           969.
 9 France           Europe     2007    80.7  61083916    30470.           968.
10 Canada           Americas   2007    80.7  33390141    36319.           968.
# ℹ 132 more rows

# Visualizing data with ggplot

gapmidner_2007 <- gapminder %>%
  filter (year == 2007)
gapmidner_2007

# A tibble: 142 × 6
   country     continent  year lifeExp       pop gdpPercap
   <fct>       <fct>     <int>   <dbl>     <int>     <dbl>
 1 Afghanistan Asia       2007    43.8  31889923      975.
 2 Albania     Europe     2007    76.4   3600523     5937.
 3 Algeria     Africa     2007    72.3  33333216     6223.
 4 Angola      Africa     2007    42.7  12420476     4797.
 5 Argentina   Americas   2007    75.3  40301927    12779.
 6 Australia   Oceania    2007    81.2  20434176    34435.
 7 Austria     Europe     2007    79.8   8199783    36126.
 8 Bahrain     Asia       2007    75.6    708573    29796.
 9 Bangladesh  Asia       2007    64.1 150448339     1391.
10 Belgium     Europe     2007    79.4  10392226    33693.
# ℹ 132 more rows

library(ggplot2)
ggplot (gapminder, aes(x = gdpPercap, y = lifeExp))+
  geom_point()

gapminder <- gapminder
ggplot (gapminder, aes(x = gdpPercap, y = lifeExp))+
  geom_point()+
  scale_x_log10()

#Log scale for x axis

ggplot (gamp_2007, aes ( x= gdpPercap, y = lifeExp))+
  geom_point()+
  scale_x_log10()

gapminder_1952 <- gapminder %>%
  filter (year == 1952)

  ggplot (gapminder_1952, aes (x = lifeExp, y = gdpPercap, color = continent,
                               size = pop))+
  geom_point()+
  scale_x_log10()+
  scale_y_log10()+
    facet_wrap(~continent)

skimmed_data <- skim(gapminder)
print(skimmed_data)

── Data Summary ────────────────────────
                           Values   
Name                       gapminder
Number of rows             1704     
Number of columns          6        
_______________________             
Column type frequency:              
  factor                   2        
  numeric                  4        
________________________            
Group variables            None     

── Variable type: factor ───────────────────────────────────────────────────────
  skim_variable n_missing complete_rate ordered n_unique
1 country               0             1 FALSE        142
2 continent             0             1 FALSE          5
  top_counts                            
1 Afg: 12, Alb: 12, Alg: 12, Ang: 12    
2 Afr: 624, Asi: 396, Eur: 360, Ame: 300

── Variable type: numeric ──────────────────────────────────────────────────────
  skim_variable n_missing complete_rate       mean          sd      p0       p25
1 year                  0             1     1980.         17.3  1952      1966. 
2 lifeExp               0             1       59.5        12.9    23.6      48.2
3 pop                   0             1 29601212.  106157897.  60011   2793664  
4 gdpPercap             0             1     7215.       9857.    241.     1202. 
        p50        p75         p100 hist 
1    1980.      1993.        2007   ▇▅▅▅▇
2      60.7       70.8         82.6 ▁▆▇▇▇
3 7023596.  19585222.  1318683096   ▇▁▁▁▁
4    3532.      9325.      113523.  ▇▁▁▁▁

gapminder %>%
  summarize(medianlifeExp = median(lifeExp))

# A tibble: 1 × 1
  medianlifeExp
          <dbl>
1          60.7

view(gapminder)

gapminder %>%
  filter(year == 1957) %>%
  summarize (medianLifeExp = median(lifeExp))

# A tibble: 1 × 1
  medianLifeExp
          <dbl>
1          48.4

gapminder %>%
  filter (year == 1957) %>%
  summarize (medianLifeExp = median(lifeExp),
             maxLifeExp = max(lifeExp),
             minLifeExp = min(lifeExp),
             meanLifeExp = mean(lifeExp))

# A tibble: 1 × 4
  medianLifeExp maxLifeExp minLifeExp meanLifeExp
          <dbl>      <dbl>      <dbl>       <dbl>
1          48.4       73.5       30.3        51.5

#groub_by verp

median_by_years <- gapminder %>%
  group_by(year) %>%
  summarize(medianLifeExp = median(lifeExp),
            max_lifeExp = max(lifeExp),
            min_lifeExp = min(lifeExp),
            mean_lifeExp = mean(lifeExp)) %>%
  arrange(year)

ggplot (median_by_years, aes(x = year, y = medianLifeExp, color = year))+
  geom_point()+
  geom_line()+
  labs(title = "Median Life Expectancy by Year",
       x = "Year",
       y = "Median Life Expectancy")+
  theme_minimal()+
  theme(legend.position = "none")+
  scale_x_continuous(breaks = seq(1952, 2007, 10))

medina_lifeExp_2007_continat <- gapminder %>%
  filter (year == 2007) %>%
  group_by (continent) %>%
  summarize (medianLifeExp = median(lifeExp),
             max_lifeExp = max(lifeExp),
             min_lifeExp = min(lifeExp),
             mean_lifeExp = mean(lifeExp))
ggplot (medina_lifeExp_2007_continat, aes(x = continent, y= medianLifeExp))+
  geom_col()+
  labs(title = "Median Life Expectancy by Continent in 2007",
       x = "Continent",
       y = "Median Life Expectancy")+
  theme(legend.position = "none")

# group by year and continent

year_and_continet <- gapminder %>%
  group_by (year, continent)%>%
  summarize (medianLifeExp = median(lifeExp),
             max_lifeExp = max(lifeExp),
             min_lifeExp = min(lifeExp),
             mean_lifeExp = mean(lifeExp))

`summarise()` has grouped output by 'year'. You can override using the
`.groups` argument.

ggplot (year_and_continet, aes(x= year, y= medianLifeExp, color = continent))+
  geom_point(size = 3.5)+
  expand_limits(y = 0)+
  scale_x_log10()+
  geom_line(size = 1.5)+
  labs(title = "Median Life Expectancy by Year and Continent",
       x = "Year",
       y = "Median Life Expectancy")+
  theme_minimal()+
  theme(legend.position = "bottom")

Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
ℹ Please use `linewidth` instead.

per_capita_and_lifeExp <- gapminder %>%
group_by (year) %>%
summarize (medianLifeExp = median(lifeExp),
            maxGdp = max(gdpPercap))

gapminder %>%
filter (year == 1957) %>%
  group_by(continent) %>%
summarize (medianLifeExp = median(lifeExp),
        maxGdpPercap = max(gdpPercap))

# A tibble: 5 × 3
  continent medianLifeExp maxGdpPercap
  <fct>             <dbl>        <dbl>
1 Africa             40.6        5487.
2 Americas           56.1       14847.
3 Asia               48.3      113523.
4 Europe             67.6       17909.
5 Oceania            70.3       12247.

by_year_continent <- gapminder %>%
group_by (year, continent) %>%
summarize (medianLifeExp = median(lifeExp),
        medianGdpPercap = median(gdpPercap))

`summarise()` has grouped output by 'year'. You can override using the
`.groups` argument.

# Plot the change in medianGdpPercap in each continent over time
ggplot(by_year_continent, aes (x= year, y= medianLifeExp, color = continent))+
geom_point(size = 2.5)+
theme_minimal()+
expand_limits(y = 0)