Update R package documentation

R/award_winners.R

@@ -10,7 +10,7 @@
 #' per award per tournament. Some awards are shared by multiple players. It
 #' indicates the name of the award, the player(s) who won the award, the team
 #' of the player(s) who won the award, and whether the award was shared. There
-#' are 12 variables and 133 observations.
+#' are 12 variables and 200 observations.
 #' 
 #' @format A data frame with 12 variables:
 #' \describe{

R/bookings.R

@@ -12,7 +12,7 @@
 #' booking, the player who was booked, whether the booking was a yellow card
 #' or a red card, whether the card was a second yellow card, and whether the
 #' player was sent off as a result of the booking. There are 26 variables and
-#' 2466 observations.
+#' 3178 observations.
 #' 
 #' @format A data frame with 26 variables:
 #' \describe{

R/goals.R

@@ -11,8 +11,8 @@
 #' team of the player who scored the goal (to account for own goals), minute
 #' of the goal, and whether the goal was scored in the run of play by the
 #' opposition, was an own goal, or was a penalty. This dataset does not
-#' include converted penalties in a penalty shootout. There are 27 variables
-#' and 2548 observations.
+#' include converted penalties in a penalty shootout. There are 26 variables
+#' and 3637 observations.
 #' 
 #' @format A data frame with 27 variables:
 #' \describe{

R/group_standings.R

@@ -13,7 +13,7 @@
 #' matches played, the number of wins, the number of losses, the number of
 #' draws, the number of goals for, the number of goals against, the goal
 #' difference, the total number of points earned, and whether the team
-#' advanced out of the group. There are 19 variables and 458 observations.
+#' advanced out of the group. There are 19 variables and 626 observations.
 #' 
 #' @format A data frame with 19 variables:
 #' \describe{

R/host_countries.R

@@ -9,7 +9,7 @@
 #' This dataset records all host countries. There is one observation per host
 #' country per tournament. A tournament can have multiple host countries. It
 #' indicates the performance of each host country (the furthest stage
-#' reached). There are 7 variables and 22 observations.
+#' reached). There are 7 variables and 31 observations.
 #' 
 #' @format A data frame with 7 variables:
 #' \describe{

R/manager_appearances.R

@@ -8,7 +8,7 @@
 #' 
 #' This dataset records all manager appearances. There is one observation per
 #' manager per team per match per tournament. There are some teams that have
-#' co-managers. There are 17 variables and 1842 observations.
+#' co-managers. There are 17 variables and 2538 observations.
 #' 
 #' @format A data frame with 17 variables:
 #' \describe{

R/manager_appointments.R

@@ -8,7 +8,7 @@
 #' 
 #' This dataset records all manager appointments. There is one observation per
 #' manager per team per tournament. There are some teams that have
-#' co-managers. There are 10 variables and 469 observations.
+#' co-managers. There are 10 variables and 637 observations.
 #' 
 #' @format A data frame with 10 variables:
 #' \describe{

R/managers.R

@@ -8,10 +8,10 @@
 #' 
 #' This dataset records all managers who have participated in a World Cup
 #' match. There is one observation per manager. It includes their name, their
-#' home country, and a link to their Wikipedia page, if they have one. There
-#' are 6 variables and 357 observations.
+#' sex, their home country, and a link to their Wikipedia page, if they have
+#' one. There are 7 variables and 475 observations.
 #' 
-#' @format A data frame with 6 variables:
+#' @format A data frame with 7 variables:
 #' \describe{
 #' \item{key_id}{\code{integer}. The unique ID number for the observation.}
 #' \item{manager_id}{\code{text}. The unique ID number for the manager. Has
@@ -20,6 +20,8 @@
 #' the manager's family name, and then by the manager's given name.}
 #' \item{family_name}{\code{text}. The family name of the manager.}
 #' \item{given_name}{\code{text}. The given name of the manager.}
+#' \item{female}{\code{boolean}. Whether the manager is female. Coded \code{1}
+#' if the manager is female and \code{0} if the manager is male.}
 #' \item{country_name}{\code{text}. The name of the manager's home country.}
 #' \item{manager_wikipedia_link}{\code{text}. The Wikipedia link for the
 #' manager.}

R/matches.R

@@ -13,7 +13,7 @@
 #' extra time, whether there was a penalty shootout, the number of penalties
 #' scored in the shootout (if applicable), the result of the match (home team
 #' win, away team win, draw, replayed), and the winner (if applicable). There
-#' are 37 variables and 900 observations.
+#' are 38 variables and 1248 observations.
 #' 
 #' @format A data frame with 37 variables:
 #' \describe{

R/penalty_kicks.R

@@ -10,7 +10,7 @@
 #' There is one observation per penalty kick. This dataset does not include
 #' attempted penalty kicks during matches. It indicates minute of each kick,
 #' the player who took the kick, and whether the penalty was converted. There
-#' are 19 variables and 279 observations.
+#' are 19 variables and 396 observations.
 #' 
 #' @format A data frame with 19 variables:
 #' \describe{

R/player_appearances.R

@@ -10,10 +10,10 @@
 #' observation per player per team per match per tournament. It includes
 #' players who play in the match, including players who are in the starting
 #' eleven and players who come in as substitutes. FIFA match reports do not
-#' include information about substitutions before 1970. There are 22 variables
-#' and 18623 observations.
+#' include information about substitutions before 1970. There are 21 variables
+#' and 27432 observations.
 #' 
-#' @format A data frame with 22 variables:
+#' @format A data frame with 21 variables:
 #' \describe{
 #' \item{key_id}{\code{integer}. The unique ID number for the observation.}
 #' \item{tournament_id}{\code{text}. The unique ID number for the tournament.
@@ -22,7 +22,7 @@
 #' \item{match_id}{\code{text}. The unique ID number for the match. References
 #' \code{match_id} in the \code{matches} dataset.}
 #' \item{match_name}{\code{text}. The name of the match.}
-#' \item{date}{\code{date}. The date of the match in the format
+#' \item{match_date}{\code{date}. The date of the match in the format
 #' \code{YYYY-MM-DD}.}
 #' \item{stage_name}{\code{enum}. The stage of the tournament in which the
 #' match occurred. The possible values are: \code{first round}, \code{second
@@ -51,8 +51,6 @@
 #' \code{1} if the player started the match and \code{0} otherwise.}
 #' \item{substitute}{\code{boolean}. Whether the player was a substitute.
 #' Coded \code{1} if the player was a substitute and \code{0} otherwise.}
-#' \item{captain}{\code{boolean}. Whether the player was the captain of the
-#' team. Coded \code{1} if the player was the captain and \code{0} otherwise.}
 #' }
 "player_appearances"
 

R/players.R

@@ -8,12 +8,12 @@
 #' 
 #' This dataset records all players who have participated in a World Cup
 #' match, including players on the bench. There is one observation per player.
-#' It includes their name, their birth date, and a link to their Wikipedia
-#' page, if they have one. Note that it does not include their team, as a
-#' small number of players represent different countries in different
-#' tournaments. There are 12 variables and 7907 observations.
+#' It includes their name, their birth date, their sex, and a link to their
+#' Wikipedia page, if they have one. Note that it does not include their team,
+#' as a small number of players represent different countries in different
+#' tournaments. There are 13 variables and 10401 observations.
 #' 
-#' @format A data frame with 12 variables:
+#' @format A data frame with 13 variables:
 #' \describe{
 #' \item{key_id}{\code{integer}. The unique ID number for the observation.}
 #' \item{player_id}{\code{text}. The unique ID number for the player. Has the
@@ -23,6 +23,8 @@
 #' \item{given_name}{\code{text}. The given name of the player.}
 #' \item{birth_date}{\code{date}. The birth date of the player in the format
 #' \code{YYYY-MM-DD}.}
+#' \item{female}{\code{boolean}. Whether the player is female. Coded \code{1}
+#' if the player is female and \code{0} if the player is male.}
 #' \item{goal_keeper}{\code{boolean}. Whether the player was a goal keeper.
 #' Coded \code{1} if the player was a goal keeper and \code{0} otherwise.}
 #' \item{defender}{\code{boolean}. Whether the player was a defender. Coded

R/qualified_teams.R

@@ -8,7 +8,7 @@
 #' 
 #' This dataset records all qualified teams. There is one observation per team
 #' per tournament. It includes the tournament, the team, and the performance
-#' of each team (the furthest stage reached). There are 8 variables and 457
+#' of each team (the furthest stage reached). There are 8 variables and 625
 #' observations.
 #' 
 #' @format A data frame with 8 variables:

R/referee_appearances.R

@@ -7,7 +7,7 @@
 #' Referee appearances
 #' 
 #' This dataset records all referee appearances. There is one observation per
-#' referee per match per tournament. There are 15 variables and 900
+#' referee per match per tournament. There are 15 variables and 1248
 #' observations.
 #' 
 #' @format A data frame with 15 variables:

R/referee_appointments.R

@@ -9,7 +9,7 @@
 #' This dataset records all referee appointments. There is one observation per
 #' referee per tournament. This dataset only includes the main referee, not
 #' assistant referees, fourth officials, or video assistant referees.There are
-#' 10 variables and 511 observations.
+#' 10 variables and 668 observations.
 #' 
 #' @format A data frame with 10 variables:
 #' \describe{

R/referees.R

@@ -8,10 +8,10 @@
 #' 
 #' This dataset records all referees who have participated in a World Cup
 #' match. There is one observation per referee. It includes their name, their
-#' home country, their confederation, and a link to their Wikipedia page, if
-#' they have one. There are 9 variables and 380 observations.
+#' sex, their home country, their confederation, and a link to their Wikipedia
+#' page, if they have one. There are 10 variables and 493 observations.
 #' 
-#' @format A data frame with 9 variables:
+#' @format A data frame with 10 variables:
 #' \describe{
 #' \item{key_id}{\code{integer}. The unique ID number for the observation.}
 #' \item{referee_id}{\code{text}. The unique ID number for the referee. Has
@@ -20,6 +20,8 @@
 #' the referee's family name, and then by the referee's given name.}
 #' \item{family_name}{\code{text}. The family name of the referee.}
 #' \item{given_name}{\code{text}. The given name of the referee.}
+#' \item{female}{\code{boolean}. Whether the referee is female. Coded \code{1}
+#' if the referee is female and \code{0} if the referee is male.}
 #' \item{country_name}{\code{text}. The name of the referee's home country.}
 #' \item{confederation_id}{\code{text}. The unique ID number for the
 #' confederation. References \code{confederation_id} in the

R/squads.R

@@ -10,7 +10,7 @@
 #' observation per player per team per tournament. It includes the position of
 #' each player, the shirt number of each player (from 1954), the current club
 #' of each player, and a link to the Wikipedia page for the club, if it has
-#' one. There are 12 variables and 10142 observations.
+#' one. There are 14 variables and 13843 observations.
 #' 
 #' @format A data frame with 12 variables:
 #' \describe{

R/stadiums.R

@@ -9,7 +9,7 @@
 #' This dataset records all stadiums that have hosted a World Cup match. There
 #' is one observation per stadium. It includes the country and city of the
 #' stadium, the approximate capacity of the stadium, and the link to the
-#' Wikipedia pages for the city and the stadium. There are 8 variables and 185
+#' Wikipedia pages for the city and the stadium. There are 8 variables and 240
 #' observations.
 #' 
 #' @format A data frame with 8 variables:

R/substitutions.R

@@ -10,7 +10,7 @@
 #' not include information about substitutions before 1970. There is one
 #' observation per player per substitution. It indicates the minute of the
 #' substitution, the player who went off, and the player who came on. There
-#' are 24 variables and 6464 observations.
+#' are 24 variables and 10222 observations.
 #' 
 #' @format A data frame with 24 variables:
 #' \describe{

R/team_appearances.R

@@ -10,8 +10,8 @@
 #' team per match per tournament. It includes whether the team is the home
 #' team or the away team, the number of goals for and against, the goal
 #' difference, whether there was a penalty shootout, penalties for and against
-#' (if applicable), and whether the team wins, loses, or draws. There are 36
-#' variables and 1800 observations.
+#' (if applicable), and whether the team wins, loses, or draws. There are 37
+#' variables and 2496 observations.
 #' 
 #' @format A data frame with 36 variables:
 #' \describe{

R/teams.R

@@ -8,10 +8,13 @@
 #' 
 #' This dataset records all teams who have participated in a World Cup match.
 #' There is one observation per team. It includes the 3-letter ISO code for
-#' each country and information about each country's national federation and
-#' FIFA confederation. There are 11 variables and 84 observations.
+#' each country, whether the country's men's and women's team have qualified
+#' for a tournament, the name of the country's national federation, the
+#' country's FIFA confederation, and links to the Wikipedia pages for their
+#' men's and women's teams, if the team has qualified for a tournament. There
+#' are 14 variables and 88 observations.
 #' 
-#' @format A data frame with 11 variables:
+#' @format A data frame with 14 variables:
 #' \describe{
 #' \item{key_id}{\code{integer}. The unique ID number for the observation.}
 #' \item{team_id}{\code{text}. The unique ID number for the team. Has the
@@ -20,6 +23,10 @@
 #' team's name.}
 #' \item{team_name}{\code{text}. The name of the team.}
 #' \item{team_code}{\code{text}. The 3-letter code for the team.}
+#' \item{mens_team}{\code{boolean}. Whether the country's men's team has
+#' qualified for a tournament.}
+#' \item{womens_team}{\code{boolean}. Whether the country's women's team has
+#' qualified for a tournament.}
 #' \item{federation_name}{\code{text}. The name of the team's federation.}
 #' \item{region_name}{\code{text}. The name of the region that the country is
 #' located in.}
@@ -29,7 +36,12 @@
 #' \item{confederation_name}{\code{text}. The name of the confederation.}
 #' \item{confederation_code}{\code{text}. The abbreviation for the
 #' confederation.}
-#' \item{team_wikipedia_link}{\code{text}. The Wikipedia link for the team.}
+#' \item{mens_team_wikipedia_link}{\code{text}. The Wikipedia link for
+#' country's men's team. Coded \code{not applicable} if the country's men's
+#' team has not qualified for a tournament.}
+#' \item{womens_team_wikipedia_link}{\code{text}. The Wikipedia link for
+#' country's women's team. Coded \code{not applicable} if the country's
+#' women's team has not qualified for a tournament.}
 #' \item{federation_wikipedia_link}{\code{text}. The Wikipedia link of the
 #' team's federation.}
 #' }

R/tournament_stages.R

@@ -13,7 +13,7 @@
 #' of the stage, and how many matches there were in the stage, how many teams
 #' participated in each stage, how many games were scheduled, how many replays
 #' there were, how many walkovers there were, and how many playoffs there
-#' were. There are 16 observations and 107 observations.
+#' were. There are 16 observations and 155 observations.
 #' 
 #' @format A data frame with 16 variables:
 #' \describe{

R/tournament_standings.R

@@ -10,7 +10,7 @@
 #' observation per position per tournament. The top four teams are ranked. In
 #' most tournaments, these are the winner of the final, the loser of the
 #' final, the winner of the third-place match, and the loser of the
-#' third-place match. There are 7 variables and 84 observations.
+#' third-place match. There are 7 variables and 120 observations.
 #' 
 #' @format A data frame with 7 variables:
 #' \describe{

R/tournaments.R

@@ -9,7 +9,7 @@
 #' This dataset records all World Cup tournaments. There is one observation
 #' per tournament. It includes the host of the tournament, the winner of the
 #' tournament, the start and end dates of the tournament, and information
-#' about the format of the tournament. There are 18 variables and 21
+#' about the format of the tournament. There are 18 variables and 30
 #' observations.
 #' 
 #' @format A data frame with 18 variables: