R for Data Science

Import data

# excel filer
games <- read_excel("../00_data/MyData_charts.xlsx")
games

## # A tibble: 988 × 15
##     year country city    stage home_team away_team home_score away_score outcome
##    <dbl> <chr>   <chr>   <chr> <chr>     <chr>          <dbl>      <dbl> <chr>  
##  1  1930 Uruguay Montev… Grou… France    Mexico             4          1 H      
##  2  1930 Uruguay Montev… Grou… Belgium   United S…          0          3 A      
##  3  1930 Uruguay Montev… Grou… Brazil    Yugoslav…          1          2 A      
##  4  1930 Uruguay Montev… Grou… Peru      Romania            1          3 A      
##  5  1930 Uruguay Montev… Grou… Argentina France             1          0 H      
##  6  1930 Uruguay Montev… Grou… Chile     Mexico             3          0 H      
##  7  1930 Uruguay Montev… Grou… Bolivia   Yugoslav…          0          4 A      
##  8  1930 Uruguay Montev… Grou… Paraguay  United S…          0          3 A      
##  9  1930 Uruguay Montev… Grou… Uruguay   Peru               1          0 H      
## 10  1930 Uruguay Montev… Grou… Argentina Mexico             6          3 H      
## # ℹ 978 more rows
## # ℹ 6 more variables: win_conditions <chr>, winning_team <chr>,
## #   losing_team <chr>, date <dttm>, month <chr>, dayofweek <chr>

Select colums

select(games, home_team, home_score, away_team, away_score) %>%
    
    #arrange home score
    arrange(desc(home_score))

## # A tibble: 988 × 4
##    home_team    home_score away_team     away_score
##    <chr>             <dbl> <chr>              <dbl>
##  1 <NA>                177 <NA>                  NA
##  2 Hungary              10 El Salvador            1
##  3 Hungary               9 South Korea            0
##  4 Yugoslavia            9 Zaire                  0
##  5 Germany               8 Saudi Arabia           0
##  6 Italy                 7 United States          1
##  7 Brazil                7 Sweden                 1
##  8 West Germany          7 Turkey                 2
##  9 France                7 Paraguay               3
## 10 Portugal              7 North Korea            0
## # ℹ 978 more rows

Add columns

mutate(games,
       difference = home_score - away_score) %>%
    
    #Select home team, away team, home score, away score and difference
    select(home_team: away_score, difference, winning_team)

## # A tibble: 988 × 6
##    home_team away_team     home_score away_score difference winning_team 
##    <chr>     <chr>              <dbl>      <dbl>      <dbl> <chr>        
##  1 France    Mexico                 4          1          3 France       
##  2 Belgium   United States          0          3         -3 United States
##  3 Brazil    Yugoslavia             1          2         -1 Yugoslavia   
##  4 Peru      Romania                1          3         -2 Romania      
##  5 Argentina France                 1          0          1 Argentina    
##  6 Chile     Mexico                 3          0          3 Chile        
##  7 Bolivia   Yugoslavia             0          4         -4 Yugoslavia   
##  8 Paraguay  United States          0          3         -3 United States
##  9 Uruguay   Peru                   1          0          1 Uruguay      
## 10 Argentina Mexico                 6          3          3 Argentina    
## # ℹ 978 more rows

Group by

games %>% 
# Remove missing values
    filter(!is.na(home_team)) %>%
    filter(!is.na(home_score)) %>%
    select(home_team, home_score) %>%
    group_by(home_team) 

## # A tibble: 900 × 2
## # Groups:   home_team [81]
##    home_team home_score
##    <chr>          <dbl>
##  1 France             4
##  2 Belgium            0
##  3 Brazil             1
##  4 Peru               1
##  5 Argentina          1
##  6 Chile              3
##  7 Bolivia            0
##  8 Paraguay           0
##  9 Uruguay            1
## 10 Argentina          6
## # ℹ 890 more rows

Plot

games %>% 
# Remove missing values
    filter(!is.na(home_team)) %>%
    filter(!is.na(home_score)) %>%
    select(home_team, home_score) %>%
    group_by(home_team) %>%
    
     # Plot
    ggplot(mapping = aes(x = home_team, y = home_score)) +
    geom_bar(stat = "identity") +
    labs(x = "X-axis label", y = "Y-axis label") +
    theme(axis.text.x = element_text(angle = 90, hjust= 1, size = 5))