feat: Validation Split & MLflow Tracking (fixes #22)

[verdhanyash]

Fixes

Closes: #22

Type of Change

• Bug fix
• New feature
• Documentation / Refactor
• Math / Logic correction

Description

Implemented validation split and MLflow tracking for monitoring model generalization performance.

Changes:

• Added validation_split: float = 0.2 parameter to Model.train() method
• Split data into training and validation sets after preprocessing (shuffled, seed-reproducible)
• Compute validation loss per-epoch inside the existing Rust progress_callback — training loop stays entirely in Rust, preserving optimizer state and avoiding FFI overhead
• Added _calculate_validation_loss() method supporting both classification (cross-entropy) and regression (MSE)
• Extended Rust bindings with forward() method to expose raw model outputs for validation loss calculation
• Updated save_model() to log both loss and val_loss metrics to MLflow with epoch steps
• Added input validation for validation_split parameter range
• Stored val_loss_history on model instance, initialized in __init__() and load()

Key architectural decisions (addressing PR #62 feedback):

• Training loop remains 100% in Rust — rust_model.train() called exactly once
• Optimizer state (Adam moments, SGD) is never reset between epochs
• Validation loss computed in the existing progress_callback (no extra FFI overhead)
• Data shuffled before split using np.random.default_rng(seed) for reproducibility

Result: MLflow dashboard now displays overlapping train/validation loss curves for monitoring overfitting and generalization.

How Has This Been Tested?

• Unit Tests: Created and ran test_validation_split.py with 8 tests covering classification, regression, edge cases, seed reproducibility, and MLflow logging
• Smoke Testing: Verified end-to-end with mock datasets — progress bar shows both Train Loss and Val Loss
• Integration: Confirmed Rust core forward() method works correctly with Python API
• Existing Tests: All 46 pytest tests pass (38 existing + 8 new, zero regressions)

Screenshots / Logs

Contribution Context

• I am contributing through the SWOC program.

[github-actions]

Thank you for opening this PR! Our automated system is currently verifying the PR requirements.
Internal Discussion: Discord

[github-actions]

Validation Successful!

This pull request has been verified and linked to issue #22. The system is now synchronizing metadata from the referenced issue. Kindly await maintainer review of your changes.

[github-actions]

Validation Successful!

This pull request has been verified and linked to issue #22. The system is now synchronizing metadata from the referenced issue. Kindly await maintainer review of your changes.

[github-actions]

Validation Successful!

This pull request has been verified and linked to issue #22. The system is now synchronizing metadata from the referenced issue. Kindly await maintainer review of your changes.

[github-actions]

Validation Successful!

This pull request has been verified and linked to issue #22. The system is now synchronizing metadata from the referenced issue. Kindly await maintainer review of your changes.

[github-actions]

Validation Successful!

This pull request has been verified and linked to issue #22. The system is now synchronizing metadata from the referenced issue. Kindly await maintainer review of your changes.

[github-actions]

Validation Successful!

This pull request has been verified and linked to issue #22. The system is now synchronizing metadata from the referenced issue. Kindly await maintainer review of your changes.

[github-actions]

Validation Successful!

This pull request has been verified and linked to issue #22. The system is now synchronizing metadata from the referenced issue. Kindly await maintainer review of your changes.

[Aamod007]

Good Work @verdhanyash