senaye2003/soccer-spark-analysis

How senaye2003/soccer-spark-analysis works

This repository is a PySpark soccer-event analysis project. Its main workflow loads StatsBomb match/event data, shapes it into Spark datasets, persists events and match metadata, then runs analytical queries; separate entry points provide shot-to-goal ML and a simulated Structured Streaming demonstration. The graph reflects the README’s documented analytical scope, while the excerpts show implementation details primarily for ingestion, queries, ML, and streaming; documented but unimplemented capabilities are shown without speculative call edges.

Main entry points: transformations.py Query Runner · ml_pipeline.py ML Runner · streaming.py Streaming Runner · ingestion.py Ingestion Job

Components 23

Ingestion

Ingestion Job src/ingestion.py
Event Dataset src/ingestion.py
Match Dimension src/ingestion.py
Ingestion EDA src/ingestion.py

Batch Analysis

Query Runner src/transformations.py
Shot Efficiency src/transformations.py
Team Comparison src/transformations.py
Passing Analysis src/transformations.py
Event Trends src/transformations.py
Match Goal Join src/transformations.py
Passing Networks src
Pressure Analysis src

Shot Modeling

ML Runner src/ml_pipeline.py
Shot Features src/ml_pipeline.py
Goal Classifier src/ml_pipeline.py
Model Metrics src/ml_pipeline.py
Player Role Clustering src

Streaming Demo

Streaming Runner src/streaming.py
Simulated Feed src/streaming.py
Team Aggregation src/streaming.py
Console Output src/streaming.py

Other components

Analyst
StatsBomb Open Data

Connections 26

Analyst → Ingestion Job: runs README.md
StatsBomb Open Data → Ingestion Job: provides data src/ingestion.py
Ingestion Job → Ingestion EDA: runs src/ingestion.py
Ingestion Job → Event Dataset: writes src/ingestion.py
Ingestion Job → Match Dimension: writes src/ingestion.py
Analyst → Query Runner: runs README.md
Query Runner → Event Dataset: reads src/transformations.py
Query Runner → Match Dimension: reads src/transformations.py
Query Runner → Shot Efficiency: runs src/transformations.py
Query Runner → Team Comparison: runs src/transformations.py
Query Runner → Passing Analysis: runs src/transformations.py
Query Runner → Event Trends: runs src/transformations.py
Query Runner → Match Goal Join: runs src/transformations.py
Analyst → ML Runner: runs
ML Runner → Event Dataset: reads src/ml_pipeline.py
ML Runner → Shot Features: derives src/ml_pipeline.py
ML Runner → Goal Classifier: trains src/ml_pipeline.py
ML Runner → Model Metrics: reports src/ml_pipeline.py
Analyst → Streaming Runner: runs
Streaming Runner → Event Dataset: reads src/streaming.py
Streaming Runner → Simulated Feed: writes src/streaming.py
Streaming Runner → Team Aggregation: aggregates src/streaming.py
Streaming Runner → Console Output: writes src/streaming.py
Analyst → Passing Networks: seeks
Analyst → Pressure Analysis: seeks
Analyst → Player Role Clustering: seeks

Drawn by GitDiagram on November 14, 2026 from the repository's file tree, README and source files. Read as Markdown ·