How ananyo-sen-b2530066/distributed-gaming-analytics works
This is a Flask-based Counter-Strike player analytics app. A user submits player stats and chooses prediction or statistical analysis; Flask builds per-player Ray tasks, waits for results, and renders them. A separate training path transforms the CSV dataset and trains target-specific Random Forest models. The README documents Ray workers and local worker-side model loading; those deployment details are shown as documented capabilities, while unsampled templates and task internals limit further call-level detail.
Main entry points: app.py Flask routes · ray_tasks.py Ray task logic · train_model.py Model training · index.html Input form
Components 14
Web interface
- Input form
templates/index.html - Flask routes
app.py - Results view
templates/result.html
Distributed analytics
- Ray cluster
- Ray workers
- Ray task logic
ray_tasks.py - Player prediction
ray_tasks.py - Statistical analysis
ray_tasks.py - Dataset averages
ray_tasks.py
Model training
- Model training
train_model.py - Prediction models
Player data
- Dataset transform
utils.py - Player dataset
data/cs2_dataset.csv
Other components
- Player
Connections 17
- Player → Input form: enters stats
README.md - Input form → Flask routes: submits form
- Flask routes → Ray cluster: initializes
app.py - Flask routes → Ray task logic: dispatches tasks
app.py - Ray task logic → Player prediction: runs prediction
ray_tasks.py - Ray task logic → Statistical analysis: runs analysis
ray_tasks.py - Flask routes → Results view: renders results
app.py - Flask routes → Ray cluster: waits for results
app.py - Ray cluster → Ray workers: schedules tasks
README.md - Ray workers → Player prediction: executes remotely
README.md - Ray workers → Statistical analysis: executes remotely
README.md - Ray task logic → Dataset averages: initializes averages
ray_tasks.py - Statistical analysis → Dataset averages: uses averages
ray_tasks.py - Model training → Dataset transform: loads transformed data
train_model.py - Dataset transform → Player dataset: reads CSV
utils.py - Model training → Prediction models: writes models
train_model.py - Player prediction → Prediction models: loads local model
README.md