Data
Lichess_Games_Dataset

Lichess_Games_Dataset

active ARFF Public Domain (CC0) Visibility: public Uploaded 06-05-2024 by Iwo Godzwon
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Description: The dataset games.csv is a comprehensive collection of chess game records, providing detailed insights into game outcomes, player ratings, moves, and opening strategies. It consists of several attributes designed to analyze game dynamics and player performance in chess matches. Attribute Description: - id: A unique identifier for each game represented by strings like 'JRpms95z'. - rated: A boolean indicating if the game was rated (True) or not. - created_at: The timestamp when the game was created, in milliseconds. - last_move_at: The timestamp for the last move made in the game. - turns: The total number of turns taken in the game. - victory_status: The method by which the game was won ('mate', 'resign', etc.). - winner: The side that won the game ('white', 'black', or 'draw'). - increment_code: Time control settings for the game, represented in a string like '7+9'. - white_id: The username of the player controlling the white pieces. - white_rating: The rating of the white player at the time of the game. - black_id: The username of the player controlling the black pieces. - black_rating: The rating of the black player at the time of the game. - moves: The sequence of moves made during the game, recorded in standard chess notation. - opening_eco: The Encyclopaedia of Chess Openings (ECO) code for the game's opening. - opening_name: The name of the opening played, like "King's Indian Defense". - opening_ply: The number of moves in the opening phase. Use Case: This dataset is invaluable for chess enthusiasts, researchers, and developers interested in developing chess-related algorithms, studying patterns and trends in game outcomes and strategies, or creating predictive models on game results based on player ratings and opening moves. It can also be used to analyze the effectiveness of different openings or to train machine learning models to forecast game outcomes from early game data.

16 features

idstring19113 unique values
0 missing
ratednominal2 unique values
0 missing
created_atstring13151 unique values
0 missing
last_move_atstring13186 unique values
0 missing
turnsnumeric211 unique values
0 missing
victory_statusnominal4 unique values
0 missing
winnernominal3 unique values
0 missing
increment_codenominal400 unique values
0 missing
white_idnominal9438 unique values
0 missing
white_ratingnumeric1516 unique values
0 missing
black_idnominal9331 unique values
0 missing
black_ratingnumeric1521 unique values
0 missing
movesstring18920 unique values
0 missing
opening_econominal365 unique values
0 missing
opening_namenominal1477 unique values
0 missing
opening_plynumeric23 unique values
0 missing

19 properties

20058
Number of instances (rows) of the dataset.
16
Number of attributes (columns) of the dataset.
Number of distinct values of the target attribute (if it is nominal).
0
Number of missing values in the dataset.
0
Number of instances with at least one value missing.
4
Number of numeric attributes.
8
Number of nominal attributes.
6.25
Percentage of binary attributes.
0
Percentage of instances having missing values.
0
Percentage of missing values.
Average class difference between consecutive instances.
25
Percentage of numeric attributes.
0
Number of attributes divided by the number of instances.
50
Percentage of nominal attributes.
Percentage of instances belonging to the most frequent class.
Number of instances belonging to the most frequent class.
Percentage of instances belonging to the least frequent class.
Number of instances belonging to the least frequent class.
1
Number of binary attributes.

0 tasks

Define a new task