Chess

These are results of chess games. Each node is a chess player, and a directed edge represents a game, with the white player having an outgoing edge and the black player having an ingoing edge. The weight of the edge represents the outcome (+1 white won, 0 draw, −1 black won). The dataset is anonymous: the identity of the players is unknown, and timestamps are approximate. Timestamps are given to a one month precision, and may have been shifted towards the future by an unknown amount.

Metadata

CodeCH
Internal namechess
NameChess
Data sourcehttps://www.kaggle.com/c/chess/data
AvailabilityDataset is available for download
Consistency checkDataset passed all tests
Category
Interaction network
Dataset timestamp 1998 ⋯ 2008
Node meaningPlayer
Edge meaningGame
Network formatUnipartite, directed
Edge typeSigned, possibly weighted, multiple edges
Temporal data Edges are annotated with timestamps
ReciprocalContains reciprocal edges
Directed cyclesContains directed cycles
LoopsDoes not contain loops
Skew-symmetry Inverted edges can be interpreted as negated edges
Zero weights Edges may have weight zero
Snapshot Is a snapshot and likely to not contain all data

Statistics

Size n =7,301
Volume m =65,053
Unique edge count m̿ =34,564
Loop count l =0
Wedge count s =2,588,788
Claw count z =16,498,559
Cross count x =272,731,448
Triangle count t =108,595
Square count q =324,301
4-Tour count T4 =6,216,178
Maximum degree dmax =280
Maximum outdegree d+max =152
Maximum indegree dmax =140
Average degree d =17.820 3
Fill p =0.000 741 048
Average edge multiplicity m̃ =1.882 10
Size of LCC N =7,115
Size of LSCC Ns =4,738
Relative size of LSCC Nrs =0.648 952
Diameter δ =13
50-Percentile effective diameter δ0.5 =3.392 21
90-Percentile effective diameter δ0.9 =4.831 00
Median distance δM =4
Mean distance δm =3.949 93
Gini coefficient G =0.590 957
Relative edge distribution entropy Her =0.928 663
Power law exponent γ =1.617 64
Tail power law exponent γt =3.071 00
Tail power law exponent with p γ3 =3.071 00
p-value p =0.000 00
Outdegree tail power law exponent with p γ3,o =3.061 00
Outdegree p-value po =0.000 00
Indegree tail power law exponent with p γ3,i =3.061 00
Indegree p-value pi =0.000 00
Degree assortativity ρ =+0.306 204
Degree assortativity p-value pρ =0.000 00
In/outdegree correlation ρ± =+0.805 364
Clustering coefficient c =0.125 845
Spectral norm α =18.856 4
Operator 2-norm ν =13.746 3
Cyclic eigenvalue π =3.192 15
Algebraic connectivity a =0.085 875 0
Reciprocity y =0.071 345 9
Non-bipartivity bA =0.652 749
Normalized non-bipartivity bN =0.051 195 9
Spectral bipartite frustration bK =0.002 148 26
Negativity ζ =0.419 222
Algebraic conflict ξ =0.076 742 9
Triadic conflict τ =0.493 546
Spectral signed frustration φ =0.001 957 64

Plots

Fruchterman–Reingold graph drawing

Degree distribution

Cumulative degree distribution

Lorenz curve

Spectral distribution of the adjacency matrix

Spectral distribution of the normalized adjacency matrix

Spectral distribution of the Laplacian

Spectral graph drawing based on the adjacency matrix

Spectral graph drawing based on the Laplacian

Spectral graph drawing based on the normalized adjacency matrix

Degree assortativity

Zipf plot

Hop distribution

Double Laplacian graph drawing

Delaunay graph drawing

In/outdegree scatter plot

Item rating evolution

Edge weight/multiplicity distribution

Clustering coefficient distribution

Average neighbor degree distribution

Temporal distribution

Temporal hop distribution

Diameter/density evolution

Signed temporal distribution

Rating class evolution

SynGraphy

Inter-event distribution

Node-level inter-event distribution

Matrix decompositions plots

Downloads

References

[1] Jérôme Kunegis. KONECT – The Koblenz Network Collection. In Proc. Int. Conf. on World Wide Web Companion, pages 1343–1350, 2013. [ http ]