Skip to content

Data analysis of Starcraft II replays . Visualization and classification models

License

Notifications You must be signed in to change notification settings

NoviceYin/Starcraft_2_Data_Analysis

 
 

Repository files navigation

GitHub issues GitHub issues GitHub issues GitHub issues

Starcraft II Data Analysis

In this repository you might find

The goal of this data exploration is to understand more about Starcraft II Gameplay Thourgh data in order to extract metrics that could identify good players from bad Ones, correlation and hierarchy of features in Starcraft II gameplay and visualizations That could add value to current personal #pysc2 research regarding fairness , games and agent design

Data visualization, including

  • Dendogram and heat maps (visual clustering)
  • Correlation Matrix
  • Correlogram
  • Radar chart
  • Density

Data exploration, including models

  • PCA
  • KMeans Clustering
  • Feedforward Network

Resources for analytics

MSC

https://github.com/wuhuikai/MSC

GGtracker

http://ggtracker.com/landing_tour

Starcraft2 Replay Analysis

https://github.com/IBM/starcraft2-replay-analysis

sc2reader

https://github.com/GraylinKim/sc2reader

Papers

## Predicting Win/Loss Records using Starcraft 2 Replay Data http://snap.stanford.edu/class/cs224w-2010/proj2010/31_final_project.pdf

An Analysis on the Rush Strategies of the Real-Time Strategy Game StarCraft-II

https://kaigi.org/jsai/webprogram/2017/pdf/446.pdf

Using Logistic Regression to Analyze the Balance of a Game: The case of StarCraft-II TM

https://arxiv.org/abs/1105.0755

Master Maker : Understanding Gaming Skill through Practice and Habit from Gameplay Behavior

http://thomas-zimmermann.com/publications/files/huang-topics-2017.pdf

DataSets

https://www.kaggle.com/alimbekovkz/starcraft-ii-matches-history/data

kudos : Michael Park

About

Data analysis of Starcraft II replays . Visualization and classification models

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%