Name: Soccer Data Of Teams, Players And Shots 2018-2023
Creator: Kaggle
License: https://www.apache.org/licenses/

About this Dataset

Soccer Data Of Teams, Players And Shots 2018-2023

The data is sourced from UnderStat and ClubElo, encompassing information about teams, players, and matches from the top five European leagues (English, Spanish, Italian, French, and German) for the 2018/2019 to 2022/2023 seasons.

This dataset provides comprehensive details on each match during this period, which can be cross-referenced using unique identification keys. The ClubElo file includes the ELO ranking statistics for each team during their respective matches.

The data was obtained using proprietary algorithms that employ web scraping techniques.

I used data for my master thesis purposes to create a xG model and compare it with that proposed by UnderStat .

Tables

Clubelo

@kaggle.arkadiuszkaros_soccer_data_of_teams_players_and_shots_2018_2023.clubelo

164.34 kB
9,029 rows
5 columns

CREATE TABLE clubelo (
  "h_team" VARCHAR,
  "a_team" VARCHAR,
  "date" TIMESTAMP,
  "hometeamelo" DOUBLE,
  "awayteamelo" DOUBLE
);

Matchdata

@kaggle.arkadiuszkaros_soccer_data_of_teams_players_and_shots_2018_2023.matchdata

483.17 kB
9,029 rows
18 columns

CREATE TABLE matchdata (
  "match_id" BIGINT,
  "is_result" BOOLEAN,
  "home_team_id" BIGINT,
  "home_team" VARCHAR,
  "home_team_short" VARCHAR,
  "away_team_id" BIGINT,
  "away_team" VARCHAR,
  "away_team_short" VARCHAR,
  "home_goals" BIGINT,
  "away_goals" BIGINT,
  "home_xg" DOUBLE,
  "away_xg" DOUBLE,
  "match_datetime" TIMESTAMP,
  "forecast_win" DOUBLE,
  "forecast_draw" DOUBLE,
  "forecast_loss" DOUBLE,
  "league" VARCHAR,
  "year" BIGINT
);

Matches

@kaggle.arkadiuszkaros_soccer_data_of_teams_players_and_shots_2018_2023.matches

629.8 kB
9,029 rows
25 columns

CREATE TABLE matches (
  "id" BIGINT,
  "fid" BIGINT,
  "h" BIGINT,
  "a" BIGINT,
  "date" TIMESTAMP,
  "league_id" BIGINT,
  "season" BIGINT,
  "h_goals" BIGINT,
  "a_goals" BIGINT,
  "team_h" VARCHAR,
  "team_a" VARCHAR,
  "h_xg" DOUBLE,
  "a_xg" DOUBLE,
  "h_w" DOUBLE,
  "h_d" DOUBLE,
  "h_l" DOUBLE,
  "league" VARCHAR,
  "h_shot" BIGINT,
  "a_shot" BIGINT,
  "h_shotontarget" BIGINT,
  "a_shotontarget" BIGINT,
  "h_deep" BIGINT,
  "a_deep" BIGINT,
  "a_ppda" DOUBLE,
  "h_ppda" DOUBLE
);

Playersdata

@kaggle.arkadiuszkaros_soccer_data_of_teams_players_and_shots_2018_2023.playersdata

802.7 kB
13,669 rows
20 columns

CREATE TABLE playersdata (
  "id" BIGINT,
  "player_name" VARCHAR,
  "games" BIGINT,
  "time" BIGINT,
  "goals" BIGINT,
  "xg" DOUBLE,
  "assists" BIGINT,
  "xa" DOUBLE,
  "shots" BIGINT,
  "key_passes" BIGINT,
  "yellow_cards" BIGINT,
  "red_cards" BIGINT,
  "position" VARCHAR,
  "team_title" VARCHAR,
  "npg" BIGINT,
  "npxg" DOUBLE,
  "xgchain" DOUBLE,
  "xgbuildup" DOUBLE,
  "league" VARCHAR,
  "year" BIGINT
);

Rosters

@kaggle.arkadiuszkaros_soccer_data_of_teams_players_and_shots_2018_2023.rosters

9.21 MB
265,114 rows
23 columns

CREATE TABLE rosters (
  "id" BIGINT,
  "goals" BIGINT,
  "own_goals" BIGINT,
  "shots" BIGINT,
  "xg" DOUBLE,
  "time" BIGINT,
  "player_id" BIGINT,
  "team_id" BIGINT,
  "position" VARCHAR,
  "player" VARCHAR,
  "h_a" VARCHAR,
  "yellow_card" BIGINT,
  "red_card" BIGINT,
  "roster_in" BIGINT,
  "roster_out" BIGINT,
  "key_passes" BIGINT,
  "assists" BIGINT,
  "xa" DOUBLE,
  "xgchain" DOUBLE,
  "xgbuildup" DOUBLE,
  "positionorder" BIGINT,
  "team" VARCHAR,
  "match_id" BIGINT
);

Shots

@kaggle.arkadiuszkaros_soccer_data_of_teams_players_and_shots_2018_2023.shots

5.62 MB
226,103 rows
20 columns

CREATE TABLE shots (
  "id" BIGINT,
  "minute" BIGINT,
  "result" VARCHAR,
  "x" DOUBLE,
  "y" DOUBLE,
  "xg" DOUBLE,
  "player" VARCHAR,
  "h_a" VARCHAR,
  "player_id" BIGINT,
  "situation" VARCHAR,
  "season" BIGINT,
  "shottype" VARCHAR,
  "match_id" BIGINT,
  "h_team" VARCHAR,
  "a_team" VARCHAR,
  "h_goals" BIGINT,
  "a_goals" BIGINT,
  "date" TIMESTAMP,
  "player_assisted" VARCHAR,
  "lastaction" VARCHAR
);

Teamsdata

@kaggle.arkadiuszkaros_soccer_data_of_teams_players_and_shots_2018_2023.teamsdata

1.21 MB
18,058 rows
25 columns

CREATE TABLE teamsdata (
  "team_id" BIGINT,
  "team_title" VARCHAR,
  "match_date" TIMESTAMP,
  "home_away" VARCHAR,
  "xg" DOUBLE,
  "xga" DOUBLE,
  "npxg" DOUBLE,
  "npxga" DOUBLE,
  "ppda_att" BIGINT,
  "ppda_def" BIGINT,
  "ppda_allowed_att" BIGINT,
  "ppda_allowed_def" BIGINT,
  "deep" BIGINT,
  "deep_allowed" BIGINT,
  "scored" BIGINT,
  "missed" BIGINT,
  "xpts" DOUBLE,
  "result" VARCHAR,
  "wins" BIGINT,
  "draws" BIGINT,
  "loses" BIGINT,
  "pts" BIGINT,
  "npxgd" DOUBLE,
  "league" VARCHAR,
  "year" BIGINT
);