kevinkyi's picture
Add README.md
66de98a verified
|
raw
history blame
1.54 kB
metadata
library_name: autogluon
pipeline_tag: tabular-classification
license: mit
tags:
  - automl
  - tabular
  - autogluon
  - sklearn
model_name: Football Elite Classifier  AutoML (AutoGluon Tabular)
language:
  - en

Football Elite Classifier — AutoML (AutoGluon Tabular)

Task: Binary classification — predict Elite (0/1) from tabular receiver stats.

Dataset

  • Source: <classmate name + HF dataset link if public>
  • Split: Stratified Train/Test = 80/20 on the original split.
  • Features: ['Tgt', 'Rec', 'Yds', 'YBC_per_R', 'YAC_per_R', 'ADOT', 'Drop_pct', 'Rat']
  • Target: Elite (0/1)
  • Preprocessing: Identifier columns dropped (e.g., Player). Numeric coercion; rows with NA removed.

Training (AutoML)

  • Framework: AutoGluon Tabular
  • Preset: best_quality
  • Time budget: 300s
  • Seed: 42
  • Eval metric: F1 (binary)
  • Notes: AutoGluon performs model selection, ensembling, and stacking automatically.

Results (Held-out Test)

{
  "accuracy": 0.8333333333333334,
  "f1": 0.8
}


## Limitations & Ethics
- Correlations do not imply causation; labels may reflect selection bias.
- Out-of-distribution players/contexts may reduce performance.
- Intended for coursework, not for real personnel decisions.

## License
- Code & weights: <MIT/Apache-2.0 or course-required license>

## Acknowledgments
AutoML with [AutoGluon Tabular].
Trained in Google Colab.
GenAI tools assisted with boilerplate and doc structure.
James Kramers hugging face dataset