Pagerank for Tennis Tournament Wins

GSQL Graph Schema
#1

Hi. I am new to TigerGraph. I would like to create a simple schema that enables me to find the PageRank of each tennis player based on their wins. If I create a simple schema with player as the vertex and has_won as the edge that points from one player to another, then it appears that matches between the same two players on different dates are not loaded. This makes sense as the edge is a duplicate. The data set I am using has 1085 WTA players and ~35K matches (edges). When I load the data set into the above mentioned schema only ~25K matches (edges) are created.

Do you have a recommendation on a graph schema I should use instead? Thanks!

1 Like
#2

@kevin is the data Public? Anyway you can share a sample of the data or at a minimum the column names / descriptions? Would love to help you out on the modeling!

Cheers

#3

Hi @Jon_Herke. The data is from http://www.tennis-data.co.uk/alldata.php under WTA Women’s Tour. I can send you the source files I used if helpful. Below is a sample:

players.csv (vertex data):

name,gender
Abanda F.,F
Abdala N.,F
Abduraimova N.,F
Abdurakhimova A.,F
Abramovic I.,F
Abramovic M.,F
Adamczak M.,F
Afinogenova K.,F
Ahn K.,F

matches.csv (edge data):

name,opp,tournament,date,round,rank,rank_opp,round_total,round_num,rank_rel,rank_rel_opp,round_expected
Abanda F.,Zheng S.,Rogers Cup,2016-07-26,1st Round,274,74,6,1,35,28,1
Abanda F.,Barthel M.,Coupe Banque Nationale,2016-09-14,1st Round,201,114,5,1,8,4,3
Abanda F.,Andrianjafitrimo T.,French Open,2017-05-29,1st Round,195,269,7,1,51,54,2
Abanda F.,Nara K.,Wimbledon,2017-07-03,1st Round,142,94,7,1,62,44,2
Abanda F.,Linette M.,Western & Southern Financial Group Women’s Open,2017-08-15,1st Round,133,84,6,1,29,26,2
Abanda F.,Muhammad A.,Coupe Banque Nationale,2017-09-13,1st Round,122,144,5,1,5,7,3
Abanda F.,Lepchenko V.,Coupe Banque Nationale,2017-09-14,2nd Round,122,74,5,2,4,1,4
Abanda F.,Flipkens K.,Rogers Cup,2018-08-08,1st Round,191,47,6,1,21,19,2
Abanda F.,Martincova T.,Coupe Banque Nationale,2018-09-12,1st Round,196,240,5,1,11,12,2
Abanda F.,Kovinic D.,Chicago Women’s Opeen,2021-08-22,1st Round,361,65,5,1,10,3,2
Abduraimova N.,Tsurenko L.,Tashkent Open,2009-09-22,1st Round,867,249,5,1,24,21,1
Abduraimova N.,Arruabarrena L.,Tashkent Open,2014-09-09,1st Round,189,72,5,1,18,2,1
Abduraimova N.,Panova A.,Tashkent Open,2014-09-10,2nd Round,189,133,5,2,12,10,2
Abduraimova N.,Amanmuradova A.,Tashkent Open,2014-09-11,Quarterfinals,189,324,5,3,6,8,3
Abduraimova N.,Martic P.,Tashkent Open,2015-09-29,1st Round,227,128,5,1,23,16,1
Abduraimova N.,Ferrando C.,Guangzhou Open,2016-09-20,1st Round,176,322,5,1,14,20,2

1 Like
#4

Hi Kevin! Thanks for the share! Did you see this about tennis and graph? It’s different than yours but I wanted to share! :slight_smile:

Learning Three Dimensional Tennis Shots Using Graph Convolutional Networks:

Abstract

Human movement analysis is very often applied to sport, which has seen great achievements in assessing an athlete’s progress, giving further training tips and in movement recognition. In tennis, there are two basic shots: forehand and backhand, which are performed during all matches and training sessions. Recognition of these movements is important in the quantitative analysis of a tennis game. In this paper, the authors propose using Spatial-Temporal Graph Neural Networks (ST-GCN) to challenge the above task. Recognition of the shots is performed on the basis of images obtained from 3D tennis movements (forehands and backhands) recorded by the Vicon motion capture system (Oxford Metrics Ltd, Oxford, UK), where both the player and the racket were recorded. Two methods of putting data into the ST-GCN network were compared: with and without fuzzying of data. The obtained results confirm that the use of fuzzy input graphs for ST-GCNs is a better tool for recognition of forehand and backhand tennis shots relative to graphs without fuzzy input.

#5

Also, Kevin, per your question about them not loading, when you mapped the data, did you map the data file to the edges, too? Or did you just map the data to the vertices? If you follow this article below, Steps 13 on, it will show you how to map the data and point it to the vertices and the edges. Identify Top Customers with TigerGraph Supply Chain Starter Kit:
Please let me know if you have more questions!

1 Like