cartegena-may-2024

R You Ready

for interactive learning

flipbookr

Evangeline Reynolds, Garrick Aden-Buie, and Emi Tanaka
adapted for quarto by Kieran Healy

learnr

Garrick Aden-Buie, Barret Schloerke, JJ Allaire, and Alexander Rossell Hayes

exams

https://www.r-exams.org/

Achim Zeileis, Nikolaus Umlauf, and Friedrich Leisch

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021)   #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es

# A tibble: 380 × 18
   league season match_id isResult home_id home_team home_abbr away_id away_team
   <chr>  <chr>  <chr>    <lgl>    <chr>   <chr>     <chr>     <chr>   <chr>    
 1 La_li… 2021/… 17136    TRUE     146     Valencia  VAL       142     Getafe   
 2 La_li… 2021/… 17138    TRUE     239     Mallorca  MAL       153     Real Bet…
 3 La_li… 2021/… 17139    TRUE     261     Cadiz     CAD       151     Levante  
 4 La_li… 2021/… 17137    TRUE     157     Osasuna   OSA       141     Espanyol 
 5 La_li… 2021/… 17140    TRUE     158     Alaves    ALA       150     Real Mad…
 6 La_li… 2021/… 17141    TRUE     152     Celta Vi… CEL       143     Atletico…
 7 La_li… 2021/… 17142    TRUE     148     Barcelona BAR       140     Real Soc…
 8 La_li… 2021/… 17143    TRUE     138     Sevilla   SEV       145     Rayo Val…
 9 La_li… 2021/… 17144    TRUE     154     Villarre… VIL       155     Granada  
10 La_li… 2021/… 17145    TRUE     207     Elche     ELC       147     Athletic…
# ℹ 370 more rows
# ℹ 9 more variables: away_abbr <chr>, home_goals <dbl>, away_goals <dbl>,
#   home_xG <dbl>, away_xG <dbl>, datetime <chr>, forecast_win <dbl>,
#   forecast_draw <dbl>, forecast_loss <dbl>

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022")

# A tibble: 198 × 18
   league season match_id isResult home_id home_team home_abbr away_id away_team
   <chr>  <chr>  <chr>    <lgl>    <chr>   <chr>     <chr>     <chr>   <chr>    
 1 La_li… 2021/… 17323    TRUE     142     Getafe    GET       150     Real Mad…
 2 La_li… 2021/… 17316    TRUE     207     Elche     ELC       155     Granada  
 3 La_li… 2021/… 17320    TRUE     143     Atletico… ATL       145     Rayo Val…
 4 La_li… 2021/… 17319    TRUE     158     Alaves    ALA       140     Real Soc…
 5 La_li… 2021/… 17321    TRUE     153     Real Bet… BET       152     Celta Vi…
 6 La_li… 2021/… 17322    TRUE     239     Mallorca  MAL       148     Barcelona
 7 La_li… 2021/… 17318    TRUE     154     Villarre… VIL       151     Levante  
 8 La_li… 2021/… 17325    TRUE     157     Osasuna   OSA       147     Athletic…
 9 La_li… 2021/… 17324    TRUE     261     Cadiz     CAD       138     Sevilla  
10 La_li… 2021/… 17329    TRUE     151     Levante   LEV       239     Mallorca 
# ℹ 188 more rows
# ℹ 9 more variables: away_abbr <chr>, home_goals <dbl>, away_goals <dbl>,
#   home_xG <dbl>, away_xG <dbl>, datetime <chr>, forecast_win <dbl>,
#   forecast_draw <dbl>, forecast_loss <dbl>

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG)

# A tibble: 198 × 6
   home_team       away_team      home_goals away_goals home_xG away_xG
   <chr>           <chr>               <dbl>      <dbl>   <dbl>   <dbl>
 1 Getafe          Real Madrid             1          0   0.900   0.913
 2 Elche           Granada                 0          0   1.45    0.966
 3 Atletico Madrid Rayo Vallecano          2          0   1.98    0.104
 4 Alaves          Real Sociedad           1          1   1.54    1.38 
 5 Real Betis      Celta Vigo              0          2   0.889   1.87 
 6 Mallorca        Barcelona               0          1   0.989   1.62 
 7 Villarreal      Levante                 5          0   4.19    0.423
 8 Osasuna         Athletic Club           1          3   0.522   2.49 
 9 Cadiz           Sevilla                 0          1   0.239   1.28 
10 Levante         Mallorca                2          0   1.32    1.17 
# ℹ 188 more rows

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team")

# A tibble: 396 × 6
   home_goals away_goals home_xG away_xG home      team           
        <dbl>      <dbl>   <dbl>   <dbl> <chr>     <chr>          
 1          1          0   0.900   0.913 home_team Getafe         
 2          1          0   0.900   0.913 away_team Real Madrid    
 3          0          0   1.45    0.966 home_team Elche          
 4          0          0   1.45    0.966 away_team Granada        
 5          2          0   1.98    0.104 home_team Atletico Madrid
 6          2          0   1.98    0.104 away_team Rayo Vallecano 
 7          1          1   1.54    1.38  home_team Alaves         
 8          1          1   1.54    1.38  away_team Real Sociedad  
 9          0          2   0.889   1.87  home_team Real Betis     
10          0          2   0.889   1.87  away_team Celta Vigo     
# ℹ 386 more rows

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG)

# A tibble: 396 × 6
   team            home      home_goals away_goals home_xG away_xG
   <chr>           <chr>          <dbl>      <dbl>   <dbl>   <dbl>
 1 Getafe          home_team          1          0   0.900   0.913
 2 Real Madrid     away_team          1          0   0.900   0.913
 3 Elche           home_team          0          0   1.45    0.966
 4 Granada         away_team          0          0   1.45    0.966
 5 Atletico Madrid home_team          2          0   1.98    0.104
 6 Rayo Vallecano  away_team          2          0   1.98    0.104
 7 Alaves          home_team          1          1   1.54    1.38 
 8 Real Sociedad   away_team          1          1   1.54    1.38 
 9 Real Betis      home_team          0          2   0.889   1.87 
10 Celta Vigo      away_team          0          2   0.889   1.87 
# ℹ 386 more rows

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG))

# A tibble: 396 × 7
   team            home      home_goals away_goals home_xG away_xG  excess
   <chr>           <chr>          <dbl>      <dbl>   <dbl>   <dbl>   <dbl>
 1 Getafe          home_team          1          0   0.900   0.913  0.100 
 2 Real Madrid     away_team          1          0   0.900   0.913 -0.913 
 3 Elche           home_team          0          0   1.45    0.966 -1.45  
 4 Granada         away_team          0          0   1.45    0.966 -0.966 
 5 Atletico Madrid home_team          2          0   1.98    0.104  0.0190
 6 Rayo Vallecano  away_team          2          0   1.98    0.104 -0.104 
 7 Alaves          home_team          1          1   1.54    1.38  -0.541 
 8 Real Sociedad   away_team          1          1   1.54    1.38  -0.381 
 9 Real Betis      home_team          0          2   0.889   1.87  -0.889 
10 Celta Vigo      away_team          0          2   0.889   1.87   0.128 
# ℹ 386 more rows

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG)) |>
  group_by(team)

# A tibble: 396 × 7
# Groups:   team [20]
   team            home      home_goals away_goals home_xG away_xG  excess
   <chr>           <chr>          <dbl>      <dbl>   <dbl>   <dbl>   <dbl>
 1 Getafe          home_team          1          0   0.900   0.913  0.100 
 2 Real Madrid     away_team          1          0   0.900   0.913 -0.913 
 3 Elche           home_team          0          0   1.45    0.966 -1.45  
 4 Granada         away_team          0          0   1.45    0.966 -0.966 
 5 Atletico Madrid home_team          2          0   1.98    0.104  0.0190
 6 Rayo Vallecano  away_team          2          0   1.98    0.104 -0.104 
 7 Alaves          home_team          1          1   1.54    1.38  -0.541 
 8 Real Sociedad   away_team          1          1   1.54    1.38  -0.381 
 9 Real Betis      home_team          0          2   0.889   1.87  -0.889 
10 Celta Vigo      away_team          0          2   0.889   1.87   0.128 
# ℹ 386 more rows

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG)) |>
  group_by(team) |>
  summarise(excess = mean(excess) |> round(3))

# A tibble: 20 × 2
   team            excess
   <chr>            <dbl>
 1 Alaves          -0.244
 2 Athletic Club   -0.144
 3 Atletico Madrid  0.275
 4 Barcelona        0.107
 5 Cadiz           -0.185
 6 Celta Vigo      -0.048
 7 Elche            0.093
 8 Espanyol        -0.001
 9 Getafe           0.139
10 Granada         -0.092
11 Levante         -0.121
12 Mallorca        -0.159
13 Osasuna         -0.182
14 Rayo Vallecano  -0.476
15 Real Betis       0.067
16 Real Madrid     -0.301
17 Real Sociedad   -0.706
18 Sevilla          0.013
19 Valencia        -0.013
20 Villarreal      -0.132

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG)) |>
  group_by(team) |>
  summarise(excess = mean(excess) |> round(3)) |>
  ungroup()

# A tibble: 20 × 2
   team            excess
   <chr>            <dbl>
 1 Alaves          -0.244
 2 Athletic Club   -0.144
 3 Atletico Madrid  0.275
 4 Barcelona        0.107
 5 Cadiz           -0.185
 6 Celta Vigo      -0.048
 7 Elche            0.093
 8 Espanyol        -0.001
 9 Getafe           0.139
10 Granada         -0.092
11 Levante         -0.121
12 Mallorca        -0.159
13 Osasuna         -0.182
14 Rayo Vallecano  -0.476
15 Real Betis       0.067
16 Real Madrid     -0.301
17 Real Sociedad   -0.706
18 Sevilla          0.013
19 Valencia        -0.013
20 Villarreal      -0.132

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG)) |>
  group_by(team) |>
  summarise(excess = mean(excess) |> round(3)) |>
  ungroup() |>
  arrange(excess |> desc())

# A tibble: 20 × 2
   team            excess
   <chr>            <dbl>
 1 Atletico Madrid  0.275
 2 Getafe           0.139
 3 Barcelona        0.107
 4 Elche            0.093
 5 Real Betis       0.067
 6 Sevilla          0.013
 7 Espanyol        -0.001
 8 Valencia        -0.013
 9 Celta Vigo      -0.048
10 Granada         -0.092
11 Levante         -0.121
12 Villarreal      -0.132
13 Athletic Club   -0.144
14 Mallorca        -0.159
15 Osasuna         -0.182
16 Cadiz           -0.185
17 Alaves          -0.244
18 Real Madrid     -0.301
19 Rayo Vallecano  -0.476
20 Real Sociedad   -0.706

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG)) |>
  group_by(team) |>
  summarise(excess = mean(excess) |> round(3)) |>
  ungroup() |>
  arrange(excess |> desc()) |>
  left_join(teams_meta, by = join_by(team == team_name))

# A tibble: 20 × 4
   team            excess season    url                                         
   <chr>            <dbl> <chr>     <chr>                                       
 1 Atletico Madrid  0.275 2022/2023 https://understat.com/team/Atletico_Madrid/…
 2 Getafe           0.139 2022/2023 https://understat.com/team/Getafe/2022      
 3 Barcelona        0.107 2022/2023 https://understat.com/team/Barcelona/2022   
 4 Elche            0.093 2022/2023 https://understat.com/team/Elche/2022       
 5 Real Betis       0.067 2022/2023 https://understat.com/team/Real_Betis/2022  
 6 Sevilla          0.013 2022/2023 https://understat.com/team/Sevilla/2022     
 7 Espanyol        -0.001 2022/2023 https://understat.com/team/Espanyol/2022    
 8 Valencia        -0.013 2022/2023 https://understat.com/team/Valencia/2022    
 9 Celta Vigo      -0.048 2022/2023 https://understat.com/team/Celta_Vigo/2022  
10 Granada         -0.092 <NA>      <NA>                                        
11 Levante         -0.121 <NA>      <NA>                                        
12 Villarreal      -0.132 2022/2023 https://understat.com/team/Villarreal/2022  
13 Athletic Club   -0.144 2022/2023 https://understat.com/team/Athletic_Club/20…
14 Mallorca        -0.159 2022/2023 https://understat.com/team/Mallorca/2022    
15 Osasuna         -0.182 2022/2023 https://understat.com/team/Osasuna/2022     
16 Cadiz           -0.185 2022/2023 https://understat.com/team/Cadiz/2022       
17 Alaves          -0.244 <NA>      <NA>                                        
18 Real Madrid     -0.301 2022/2023 https://understat.com/team/Real_Madrid/2022 
19 Rayo Vallecano  -0.476 2022/2023 https://understat.com/team/Rayo_Vallecano/2…
20 Real Sociedad   -0.706 2022/2023 https://understat.com/team/Real_Sociedad/20…

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG)) |>
  group_by(team) |>
  summarise(excess = mean(excess) |> round(3)) |>
  ungroup() |>
  arrange(excess |> desc()) |>
  left_join(teams_meta, by = join_by(team == team_name)) |>
  drop_na()

# A tibble: 17 × 4
   team            excess season    url                                         
   <chr>            <dbl> <chr>     <chr>                                       
 1 Atletico Madrid  0.275 2022/2023 https://understat.com/team/Atletico_Madrid/…
 2 Getafe           0.139 2022/2023 https://understat.com/team/Getafe/2022      
 3 Barcelona        0.107 2022/2023 https://understat.com/team/Barcelona/2022   
 4 Elche            0.093 2022/2023 https://understat.com/team/Elche/2022       
 5 Real Betis       0.067 2022/2023 https://understat.com/team/Real_Betis/2022  
 6 Sevilla          0.013 2022/2023 https://understat.com/team/Sevilla/2022     
 7 Espanyol        -0.001 2022/2023 https://understat.com/team/Espanyol/2022    
 8 Valencia        -0.013 2022/2023 https://understat.com/team/Valencia/2022    
 9 Celta Vigo      -0.048 2022/2023 https://understat.com/team/Celta_Vigo/2022  
10 Villarreal      -0.132 2022/2023 https://understat.com/team/Villarreal/2022  
11 Athletic Club   -0.144 2022/2023 https://understat.com/team/Athletic_Club/20…
12 Mallorca        -0.159 2022/2023 https://understat.com/team/Mallorca/2022    
13 Osasuna         -0.182 2022/2023 https://understat.com/team/Osasuna/2022     
14 Cadiz           -0.185 2022/2023 https://understat.com/team/Cadiz/2022       
15 Real Madrid     -0.301 2022/2023 https://understat.com/team/Real_Madrid/2022 
16 Rayo Vallecano  -0.476 2022/2023 https://understat.com/team/Rayo_Vallecano/2…
17 Real Sociedad   -0.706 2022/2023 https://understat.com/team/Real_Sociedad/20…

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG)) |>
  group_by(team) |>
  summarise(excess = mean(excess) |> round(3)) |>
  ungroup() |>
  arrange(excess |> desc()) |>
  left_join(teams_meta, by = join_by(team == team_name)) |>
  drop_na() |>
  slice(c(1:4, 15:17))

# A tibble: 7 × 4
  team            excess season    url                                          
  <chr>            <dbl> <chr>     <chr>                                        
1 Atletico Madrid  0.275 2022/2023 https://understat.com/team/Atletico_Madrid/2…
2 Getafe           0.139 2022/2023 https://understat.com/team/Getafe/2022       
3 Barcelona        0.107 2022/2023 https://understat.com/team/Barcelona/2022    
4 Elche            0.093 2022/2023 https://understat.com/team/Elche/2022        
5 Real Madrid     -0.301 2022/2023 https://understat.com/team/Real_Madrid/2022  
6 Rayo Vallecano  -0.476 2022/2023 https://understat.com/team/Rayo_Vallecano/20…
7 Real Sociedad   -0.706 2022/2023 https://understat.com/team/Real_Sociedad/2022

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG)) |>
  group_by(team) |>
  summarise(excess = mean(excess) |> round(3)) |>
  ungroup() |>
  arrange(excess |> desc()) |>
  left_join(teams_meta, by = join_by(team == team_name)) |>
  drop_na() |>
  slice(c(1:4, 15:17)) |>
  gt()

team	excess	season	url
Atletico Madrid	0.275	2022/2023	https://understat.com/team/Atletico_Madrid/2022
Getafe	0.139	2022/2023	https://understat.com/team/Getafe/2022
Barcelona	0.107	2022/2023	https://understat.com/team/Barcelona/2022
Elche	0.093	2022/2023	https://understat.com/team/Elche/2022
Real Madrid	-0.301	2022/2023	https://understat.com/team/Real_Madrid/2022
Rayo Vallecano	-0.476	2022/2023	https://understat.com/team/Rayo_Vallecano/2022
Real Sociedad	-0.706	2022/2023	https://understat.com/team/Real_Sociedad/2022

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG)) |>
  group_by(team) |>
  summarise(excess = mean(excess) |> round(3)) |>
  ungroup() |>
  arrange(excess |> desc()) |>
  left_join(teams_meta, by = join_by(team == team_name)) |>
  drop_na() |>
  slice(c(1:4, 15:17)) |>
  gt() |>
  cols_label(team = "Team",
             excess = "Goal Excess",
             season = "Season",
             url = "Club Website")

Team	Goal Excess	Season	Club Website
Atletico Madrid	0.275	2022/2023	https://understat.com/team/Atletico_Madrid/2022
Getafe	0.139	2022/2023	https://understat.com/team/Getafe/2022
Barcelona	0.107	2022/2023	https://understat.com/team/Barcelona/2022
Elche	0.093	2022/2023	https://understat.com/team/Elche/2022
Real Madrid	-0.301	2022/2023	https://understat.com/team/Real_Madrid/2022
Rayo Vallecano	-0.476	2022/2023	https://understat.com/team/Rayo_Vallecano/2022
Real Sociedad	-0.706	2022/2023	https://understat.com/team/Real_Sociedad/2022

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG)) |>
  group_by(team) |>
  summarise(excess = mean(excess) |> round(3)) |>
  ungroup() |>
  arrange(excess |> desc()) |>
  left_join(teams_meta, by = join_by(team == team_name)) |>
  drop_na() |>
  slice(c(1:4, 15:17)) |>
  gt() |>
  cols_label(team = "Team",
             excess = "Goal Excess",
             season = "Season",
             url = "Club Website") |>
  cols_align(align = "center")

Team	Goal Excess	Season	Club Website
Atletico Madrid	0.275	2022/2023	https://understat.com/team/Atletico_Madrid/2022
Getafe	0.139	2022/2023	https://understat.com/team/Getafe/2022
Barcelona	0.107	2022/2023	https://understat.com/team/Barcelona/2022
Elche	0.093	2022/2023	https://understat.com/team/Elche/2022
Real Madrid	-0.301	2022/2023	https://understat.com/team/Real_Madrid/2022
Rayo Vallecano	-0.476	2022/2023	https://understat.com/team/Rayo_Vallecano/2022
Real Sociedad	-0.706	2022/2023	https://understat.com/team/Real_Sociedad/2022

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG)) |>
  group_by(team) |>
  summarise(excess = mean(excess) |> round(3)) |>
  ungroup() |>
  arrange(excess |> desc()) |>
  left_join(teams_meta, by = join_by(team == team_name)) |>
  drop_na() |>
  slice(c(1:4, 15:17)) |>
  gt() |>
  cols_label(team = "Team",
             excess = "Goal Excess",
             season = "Season",
             url = "Club Website") |>
  cols_align(align = "center") |>
  tab_options(column_labels.background.color = "cornflowerblue",
              table.font.names = "Caveat",
              table.font.style = "oblique",
              table.font.size = 24,
              column_labels.font.weight = "bold",
              column_labels.vlines.width = 2,
              column_labels.vlines.color = "darkblue",
              column_labels.vlines.style = "solid",
              table_body.vlines.width = 2,
              table_body.hlines.width = 2,
              table_body.vlines.color = "darkblue",
              table_body.vlines.style = "solid"
  )

Team	Goal Excess	Season	Club Website
Atletico Madrid	0.275	2022/2023	https://understat.com/team/Atletico_Madrid/2022
Getafe	0.139	2022/2023	https://understat.com/team/Getafe/2022
Barcelona	0.107	2022/2023	https://understat.com/team/Barcelona/2022
Elche	0.093	2022/2023	https://understat.com/team/Elche/2022
Real Madrid	-0.301	2022/2023	https://understat.com/team/Real_Madrid/2022
Rayo Vallecano	-0.476	2022/2023	https://understat.com/team/Rayo_Vallecano/2022
Real Sociedad	-0.706	2022/2023	https://understat.com/team/Real_Sociedad/2022

flipbookr Runthrough

#es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |  #es <- understat_league_match_results(league = "La liga", season_start_year = 2021) |> as_tibble
es |>
  filter(year(datetime) == "2022") |>
  select(home_team, away_team, home_goals, away_goals, home_xG, away_xG) |>
  pivot_longer(-c(home_goals, away_goals, home_xG, away_xG), names_to = "home", values_to = "team") |>
  select(team, home, home_goals, away_goals, home_xG, away_xG) |>
  mutate(excess = ifelse(home == "home_team", home_goals - home_xG, away_goals - away_xG)) |>
  group_by(team) |>
  summarise(excess = mean(excess) |> round(3)) |>
  ungroup() |>
  arrange(excess |> desc()) |>
  left_join(teams_meta, by = join_by(team == team_name)) |>
  drop_na() |>
  slice(c(1:4, 15:17)) |>
  gt() |>
  cols_label(team = "Team",
             excess = "Goal Excess",
             season = "Season",
             url = "Club Website") |>
  cols_align(align = "center") |>
  tab_options(column_labels.background.color = "cornflowerblue",
              table.font.names = "Caveat",
              table.font.style = "oblique",
              table.font.size = 24,
              column_labels.font.weight = "bold",
              column_labels.vlines.width = 2,
              column_labels.vlines.color = "darkblue",
              column_labels.vlines.style = "solid",
              table_body.vlines.width = 2,
              table_body.hlines.width = 2,
              table_body.vlines.color = "darkblue",
              table_body.vlines.style = "solid"
  )

Team	Goal Excess	Season	Club Website
Atletico Madrid	0.275	2022/2023	https://understat.com/team/Atletico_Madrid/2022
Getafe	0.139	2022/2023	https://understat.com/team/Getafe/2022
Barcelona	0.107	2022/2023	https://understat.com/team/Barcelona/2022
Elche	0.093	2022/2023	https://understat.com/team/Elche/2022
Real Madrid	-0.301	2022/2023	https://understat.com/team/Real_Madrid/2022
Rayo Vallecano	-0.476	2022/2023	https://understat.com/team/Rayo_Vallecano/2022
Real Sociedad	-0.706	2022/2023	https://understat.com/team/Real_Sociedad/2022

flipbookr Runthrough

ggplot()

flipbookr Runthrough

ggplot() +
geom_sf(data=oceans_moll.sf, fill="#cce6ff")

flipbookr Runthrough

ggplot() +
geom_sf(data=oceans_moll.sf, fill="#cce6ff") +
geom_sf(data=world_sf |> st_transform(crs="+proj=moll"),
aes(fill = NAME), show.legend = FALSE)

flipbookr Runthrough

ggplot() +
geom_sf(data=oceans_moll.sf, fill="#cce6ff") +
geom_sf(data=world_sf |> st_transform(crs="+proj=moll"),
aes(fill = NAME), show.legend = FALSE) +
scale_fill_manual(values = rep(paletteer_d("MexBrewer::Naturaleza", n=7), 35))

flipbookr Runthrough

ggplot() +
geom_sf(data=oceans_moll.sf, fill="#cce6ff") +
geom_sf(data=world_sf |> st_transform(crs="+proj=moll"),
aes(fill = NAME), show.legend = FALSE) +
scale_fill_manual(values = rep(paletteer_d("MexBrewer::Naturaleza", n=7), 35)) +
scale_fill_manual(values = rep(paletteer_d("palettetown::crobat", n=7), 35))

flipbookr Runthrough

ggplot() +
geom_sf(data=oceans_moll.sf, fill="#cce6ff") +
geom_sf(data=world_sf |> st_transform(crs="+proj=moll"),
aes(fill = NAME), show.legend = FALSE) +
scale_fill_manual(values = rep(paletteer_d("MexBrewer::Naturaleza", n=7), 35)) +
scale_fill_manual(values = rep(paletteer_d("palettetown::crobat", n=7), 35)) +
scale_fill_manual(values = rep(paletteer_d("lisa::JosefAlbers", n=5), 50))

flipbookr Runthrough

ggplot() +
geom_sf(data=oceans_moll.sf, fill="#cce6ff") +
geom_sf(data=world_sf |> st_transform(crs="+proj=moll"),
aes(fill = NAME), show.legend = FALSE) +
scale_fill_manual(values = rep(paletteer_d("MexBrewer::Naturaleza", n=7), 35)) +
scale_fill_manual(values = rep(paletteer_d("palettetown::crobat", n=7), 35)) +
scale_fill_manual(values = rep(paletteer_d("lisa::JosefAlbers", n=5), 50)) +
scale_fill_manual(values = rep(my_cols, 35))

flipbookr Runthrough

ggplot() +
geom_sf(data=oceans_moll.sf, fill="#cce6ff") +
geom_sf(data=world_sf |> st_transform(crs="+proj=moll"),
aes(fill = NAME), show.legend = FALSE) +
scale_fill_manual(values = rep(paletteer_d("MexBrewer::Naturaleza", n=7), 35)) +
scale_fill_manual(values = rep(paletteer_d("palettetown::crobat", n=7), 35)) +
scale_fill_manual(values = rep(paletteer_d("lisa::JosefAlbers", n=5), 50)) +
scale_fill_manual(values = rep(my_cols, 35)) +
theme_void()

flipbookr Runthrough

ggplot() +
geom_sf(data=oceans_moll.sf, fill="#cce6ff") +
geom_sf(data=world_sf |> st_transform(crs="+proj=moll"),
aes(fill = NAME), show.legend = FALSE) +
scale_fill_manual(values = rep(paletteer_d("MexBrewer::Naturaleza", n=7), 35)) +
scale_fill_manual(values = rep(paletteer_d("palettetown::crobat", n=7), 35)) +
scale_fill_manual(values = rep(paletteer_d("lisa::JosefAlbers", n=5), 50)) +
scale_fill_manual(values = rep(my_cols, 35)) +
theme_void()

Advantages of `flipbookr`

follows philosophy of tidyverse and ggplot
empasises use of the pipe, |>
good coding practice
- every line does one job and one job only

Limitations of `flipbookr`

really only useful for coding
the #ROTATE option is a little picky
careful not to use it too much

Mechanics of `flipbookr`

install.package("flipbookr")
- works in rmarkdown
remotes::install_github("kjhealy/flipbookr@quarto")
- for quarto need the keiranjhealy version

make an r chunk of your code with options:
- #| label: my_chunk_name
- #| echo: false
- #| eval: false
below this, have inline r code using chunq_reveal(chunk_name = "my_chunk_name")
- automatically gives two-column side-by-side format
can set how lines are revealed
- normally does it line by line (break_type = "auto")
- #BREAK to specify where to stop
- #ROTATE to cycle between lines of code

`learnr`

Advantages of `learnr`

typically take a quiz after 20 & 40 minutes of lecture
- do this every time, students like the rhythm
can do any topic, not just computing
giving hints is very useful

Disadvantages

can’t build randomness into questions
I can’t see feedback/answers from students
is a bit flaky with quarto-style chunks
need to publish on a shinyapps server

Mechanics of `learnr`

3 step process
1. create a quarto document to make a shiny app
2. upload this on to a server such as shinyapps.io
3. incorporate this within lecture slides

1. Making `learnr` app

make a quarto document with the following yaml

    ---
    title: "My Exciting learnr Quiz"
    output: learnr::tutorial
    runtime: shiny_prerendered
    execute:
      echo: false
      warning: false
      message: false
    ---

include a blank coding space with a code chunk headed like this:

    {r quiz_question, exercise=TRUE, exercise.eval = TRUE}

include a hint with a code chunk headed like this:

    {r quiz_question-hint-1}

can add MCQ’s and checkbox quizzes using quiz() and question()

quiz(
  question("What is the capital city of France?",
    answer("Berlin"),
    answer("Bordeaux"),
    answer("Paris", correct = TRUE),
    answer("Rome")
  ),
  question("Which of the following are volcanoes?",
    answer("Kilamanjaro", correct = TRUE),
    answer("Everest"),
    answer("Etna", correct = TRUE),
    answer("Rainier", correct = TRUE)
  )
)

2. Upload to a shiny server

3. Add to lecture

Add code chunk with:

    xaringanExtra::embed_xaringan(url = "https://eugene-hickey.shinyapps.io/my-learnr-example/", ratio = "16:9")

`exams`

Advantages of `exams`

part of academic hosting platform (moodle, blackboard, canvas, etc)
weekly ten question quiz
- get three attempts
- done in students time
- they get instant feedback
works for all subject matter
can build in randomisation
get marks back to lecturer

Disadvantages of `exams`

works best for moodle, not sure how good with other VLE’s
interactivity is tricky
less production ready than other tools

Mechanics of `exams`

6 step process
1. Generate data and solutions
2. Create question text for student
3. Create student feedback
4. Generate meta-information
5. Use exams package to make moodle-xml
6. Upload this xml to moodle
best to start with r exams templates

1. Generate Data

{r data generation, echo = FALSE, results = "hide", 
message=FALSE, warning=FALSE}
library(tidyverse)
library(exams)
library(gt)
set.seed(42)
ok <- FALSE
while(!ok){
  x1 <- sample(1:20, 3)
  x2 <- sample(1:20, 3)
  my_soln <- x1 * x2
  ok <- !(sum(duplicated(my_soln)))
}
my_table <- tibble(
  x1 = x1, x2 = x2, 
  my_answers = c("##ANSWER1##", "##ANSWER2##", "##ANSWER3##")
  )

note, .Rmd file with no yamlheader.

2. Question Text

Question
========
In the table below, multiply _Value 1_ by _Value 2_ 
and type the answer in _Result_:

my_table |> 
  gt() |>  
  cols_label(x1 = "Value 1",
             x2 = "Value 2",
             my_answers = "Result")

3. Feedback

Solution
========
Use "Value 1" $\times$ "Value 2" to get result. 
The answers should be `r my_soln`.

4. Meta-Information

Meta-information
================
extype: cloze
exsolution: `r paste(my_soln, collapse = "|")`
exclozetype: num|num|num
exname: exams_example
extol: 0.05
exextra[numwidth,logical]: TRUE

5. Make Moodle XML

exams2moodle(file = "exams-example.Rmd", n = 100)

this will make a file called moodlequiz.xml with 100 exemplars of the quiz with different input values.

6. Upload to moodle

Thank you!

{{< fa solid blog >}}	www.fizzics.ie/
{{< fa brands orcid >}}	0000-0001-9813-9323
{{< fa brands mastodon >}}	@eugene100hickey
{{< fa brands twitter >}}	@eugene100hickey
{{< fa brands github >}}	eugene100hickey.github.io/

Figure 1

Summary

R has some great packages for teaching
we looked at three here:
- flipbookr for walking through code chunks
- learnr for producing little test questions in the middle of a lecture
- exams for producing assessments to be run online

flipbookr

learnr

exams

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

flipbookr Runthrough

Advantages of flipbookr

Limitations of flipbookr

Mechanics of flipbookr

learnr

Advantages of learnr

Disadvantages

Mechanics of learnr

1. Making learnr app

2. Upload to a shiny server

3. Add to lecture

exams

Advantages of exams

Disadvantages of exams

Mechanics of exams

1. Generate Data

2. Question Text

3. Feedback

4. Meta-Information

5. Make Moodle XML

6. Upload to moodle

Summary

Advantages of `flipbookr`

Limitations of `flipbookr`

Mechanics of `flipbookr`

`learnr`

Advantages of `learnr`

Mechanics of `learnr`

1. Making `learnr` app

`exams`

Advantages of `exams`

Disadvantages of `exams`

Mechanics of `exams`