How sanjay-n-01/aipl-data-analysis works
This repository is an IPL match-analysis and outcome-prediction project centered on a Jupyter notebook. The documented workflow is to explore historical match data, preprocess it, develop predictive models, and produce winner predictions. The README also describes supporting match and schedule data for feature engineering and visualizations across seasons and match conditions. The notebook’s implementation was not sampled, so the graph reflects only these documented capabilities and does not infer more specific code-level calls or data transfers.
Main entry points: aipl-data-analysis.ipynb Data preprocessing · train_IPL.csv.gz Historical matches · public_lb_matches.csv Match data · schedule.csv Schedule data
Components 9
Match data
- Historical matches
train_IPL.csv.gz - Match data
public_lb_matches.csv - Schedule data
schedule.csv
Analysis workflow
- Data exploration
aipl-data-analysis.ipynb - Data preprocessing
aipl-data-analysis.ipynb - Outcome modeling
aipl-data-analysis.ipynb
Prediction outputs
- Generated predictions
submission.csv - Final predictions
submission_final.csv
Other components
- Analyst
Connections 8
- Analyst → Data exploration: opens notebook
README.md - Historical matches → Data exploration: explores trends
README.md - Match data → Data preprocessing: supports features
README.md - Schedule data → Data preprocessing: supports features
README.md - Data exploration → Data preprocessing: prepares data
README.md - Data preprocessing → Outcome modeling: develops models
README.md - Outcome modeling → Generated predictions: generates predictions
README.md - Outcome modeling → Final predictions: generates predictions
README.md