神刀安全网

Analyzing Golden State Warriors' passing network using GraphFrames in Spark

Databricks recently announced GraphFrames , awesome Spark extension to implement graph processing using DataFrames.

I performed graph analysis and visualized beautiful ball movement network of Golden State Warriors using rich data provided by NBA.com’s stats

Pass network of Warriors

### Passes received & made The league’s MVP Stephen Curry received the most passes and the team’s MVP Draymond Green provides the most passes.We’ve seen most of the offense start with their pick & roll or Curry’s off-ball cuts with Green as a pass provider.

via GIPHY

inDegree

id inDegree
CurryStephen 3993
GreenDraymond 3123
ThompsonKlay 2276
LivingstonShaun 1925
IguodalaAndre 1814
BarnesHarrison 1241
BogutAndrew 1062
BarbosaLeandro 946
SpeightsMarreese 826
ClarkIan 692
RushBrandon 685
EzeliFestus 559
McAdooJames Michael 182
VarejaoAnderson 67
LooneyKevon 22

##### outDegree

id outDegree
GreenDraymond 3841
CurryStephen 3300
IguodalaAndre 1896
LivingstonShaun 1878
BogutAndrew 1660
ThompsonKlay 1460
BarnesHarrison 1300
SpeightsMarreese 795
RushBrandon 772
EzeliFestus 765
BarbosaLeandro 758
ClarkIan 597
McAdooJames Michael 261
VarejaoAnderson 94
LooneyKevon 36

Label Propagation

Label Propagation is an algorithm to find communities in a graph network.The algorithm nicely classifies players into backcourt and frontcourt without providing label!

name label
Thompson, Klay 3
Barbosa, Leandro 3
Curry, Stephen 3
Clark, Ian 3
Livingston, Shaun 3
Rush, Brandon 7
Green, Draymond 7
Speights, Marreese 7
Bogut, Andrew 7
McAdoo, James Michael 7
Iguodala, Andre 7
Varejao, Anderson 7
Ezeli, Festus 7
Looney, Kevon 7
Barnes, Harrison 7

Pagerank

PageRank can detect important nodes (players in this case) in a network.

It’s no surprise that Stephen Curry, Draymond Green and Klay Thompson are the top three.

The algoritm detects Shaun Livingston and Andre Iguodala play key roles in the Warriors’ passing games.

name pagerank
Curry, Stephen 2.17
Green, Draymond 1.99
Thompson, Klay 1.34
Livingston, Shaun 1.29
Iguodala, Andre 1.21
Barnes, Harrison 0.86
Bogut, Andrew 0.77
Barbosa, Leandro 0.72
Speights, Marreese 0.66
Clark, Ian 0.59
Rush, Brandon 0.57
Ezeli, Festus 0.48
McAdoo, James Michael 0.27
Varejao, Anderson 0.19
Looney, Kevon 0.16

Everything together

Here is a network visualization using the results of above.

  • Node size: pagerank
  • Node color: community
  • Link width: passes received & made

Workflow

## Calling API

I used the endpoint playerdashptpass and saved data for all the players in the team into local JSON files.

The data is about who passed how many times in 2015-16 season

# GSW player IDs playerids = [201575,201578,2738,202691,101106,2760,2571,203949,203546, 203110,201939,203105,2733,1626172,203084]  # Calling API and store the results as JSON for playerid in playerids:     os.system('curl "http://stats.nba.com/stats/playerdashptpass?'         'DateFrom=&'         'DateTo=&'         'GameSegment=&'         'LastNGames=0&'         'LeagueID=00&'         'Location=&'         'Month=0&'         'OpponentTeamID=0&'         'Outcome=&'         'PerMode=Totals&'         'Period=0&'         'PlayerID={playerid}&'         'Season=2015-16&'         'SeasonSegment=&'         'SeasonType=Regular+Season&'         'TeamID=0&'         'VsConference=&'         'VsDivision=" > {playerid}.json'.format(playerid=playerid))

JSON -> Panda’s DataFrame

Then I combined all the individual JSON files into a single DataFrame for later aggregation.

raw = pd.DataFrame() for playerid in playerids:     with open("{playerid}.json".format(playerid=playerid)) as json_file:         parsed = json.load(json_file)['resultSets'][0]         raw = raw.append(             pd.DataFrame(parsed['rowSet'], columns=parsed['headers']))  raw = raw.rename(columns={'PLAYER_NAME_LAST_FIRST': 'PLAYER'})  raw['id'] = raw['PLAYER'].str.replace(', ', '')

Prepare vertices and edges

You need a special data format for GraphFrames in Spark, vertices and edges.

Vertices are lis of nodes and IDs in a graph.

Edges are the relathionship of the nodes.

You can pass additional features like weight but I couldn’t find out a way to utilize there features well in later analysis. A workaround I took below is brute force and not even a proper graph operation but works (suggestions/comments are very welcome).

# Make raw vertices pandas_vertices = raw[['PLAYER', 'id']].drop_duplicates() pandas_vertices.columns = ['name', 'id']  # Make raw edges pandas_edges = pd.DataFrame() for passer in raw['id'].drop_duplicates():     for receiver in raw[(raw['PASS_TO'].isin(raw['PLAYER'])) &      (raw['id'] == passer)]['PASS_TO'].drop_duplicates():         pandas_edges = pandas_edges.append(pd.DataFrame(          {'passer': passer, 'receiver': receiver          .replace(  ', ', '')},           index=range(int(raw[(raw['id'] == passer) &           (raw['PASS_TO'] == receiver)]['PASS'].values))))  pandas_edges.columns = ['src', 'dst']

Graph analysis

Bring the local vertices and edges to Spark and let it spark.

vertices = sqlContext.createDataFrame(pandas_vertices) edges = sqlContext.createDataFrame(pandas_edges)  # Analysis part g = GraphFrame(vertices, edges) print("vertices") g.vertices.show() print("edges") g.edges.show() print("inDegrees") g.inDegrees.sort('inDegree', ascending=False).show() print("outDegrees") g.outDegrees.sort('outDegree', ascending=False).show() print("degrees") g.degrees.sort('degree', ascending=False).show() print("labelPropagation") g.labelPropagation(maxIter=5).show() print("pageRank") g.pageRank(resetProbability=0.15, tol=0.01).vertices.sort(     'pagerank', ascending=False).show()

Visualise the network

When you run gsw_passing_network.py in my github repo, you have passes.csv , groups.csv and size.csv in your working directory.

I used networkD3 package in R to make a cool interactive D3 chart.

library(networkD3)  setwd('/Users/yuki/Documents/code_for_blog/gsw_passing_network') passes <- read.csv("passes.csv") groups <- read.csv("groups.csv") size <- read.csv("size.csv")  passes$source <- as.numeric(as.factor(passes$PLAYER))-1 passes$target <- as.numeric(as.factor(passes$PASS_TO))-1 passes$PASS <- passes$PASS/50  groups$nodeid <- groups$name groups$name <- as.numeric(as.factor(groups$name))-1 groups$group <- as.numeric(as.factor(groups$label))-1 nodes <- merge(groups,size[-1],by="id") nodes$pagerank <- nodes$pagerank^2*100   forceNetwork(Links = passes,              Nodes = nodes,              Source = "source",              fontFamily = "Arial",              colourScale = JS("d3.scale.category10()"),              Target = "target",              Value = "PASS",              NodeID = "nodeid",              Nodesize = "pagerank",              linkDistance = 350,              Group = "group",               opacity = 0.8,              fontSize = 16,              zoom = TRUE,              opacityNoHover = TRUE)

Code

The full codes are available on github .

转载本站任何文章请注明:转载至神刀安全网,谢谢神刀安全网 » Analyzing Golden State Warriors' passing network using GraphFrames in Spark

分享到:更多 ()

评论 抢沙发

  • 昵称 (必填)
  • 邮箱 (必填)
  • 网址
分享按钮