DRAFT pgxmine experiments

[aviously25]

Name of the PR

♻️ Current Situation & Problem

Link any open issues or pull requests (PRs) related to this PR. Please ensure that all non-trivial PRs are first tracked and discussed in an existing GitHub issue or discussion.

• Is this a bug fix, an enhancement, or a new feature?
• Does this PR address performance issues (e.g., model inference time, memory efficiency) or improve ML pipeline performance?

⚙️ Release Notes

Add a bullet point summary of the feature, model improvements, or algorithmic changes, along with possible migration guides if this is a breaking change.

• If this is a model-related PR (e.g., training, fine-tuning, evaluation), list any significant changes to architecture or hyperparameters.
• Include relevant code snippets, examples of the new ML features, or links to updated documentation (if it appends or changes any model/data pipeline interfaces).

📚 Documentation

• Update any relevant sections in your project’s ML pipeline, preprocessing steps, or model design docs.
• Document the reasoning behind model architecture decisions, changes to data augmentation, or hyperparameter tuning.
• If introducing a new model or ML workflow, please include a high-level overview and references to any related papers or resources.

📈 Model Metrics & Performance

Detail the performance improvements, new metrics used, or model evaluation changes.

• Attach relevant model performance results (e.g., accuracy, F1 scores, AUC-ROC, precision-recall) from training and evaluation, including a comparison to the baseline.
• Mention the datasets used for testing and whether results are reproducible across different seeds.
• If applicable, include an ablation study summary or model explainability techniques used (e.g., SHAP, LIME).

✅ Testing

Please ensure that the PR meets the testing requirements set by CodeCov and that new functionality is appropriately tested.

• Have you added unit tests for any new functions or methods?
• If contributing new ML functionality, include tests for model training and evaluation pipelines.
• Mention how edge cases (e.g., missing data, model convergence issues) are handled and tested.

🛠️ Training & Environment Setup

If the contribution involves model training or modifications to the ML pipeline:

• Mention the hardware setup (e.g., GPU/TPU) and software (frameworks, versions) required for reproducibility.
• Include detailed instructions for running the model training or evaluation (data pipeline scripts, ML framework setups).

📝 Code of Conduct & Contributing Guidelines

By submitting this pull request, you agree to follow our Coding Guidelines:

• I agree to follow the Coding Guidelines.