Replace mock inference with real model artifacts and add input valida…

[sanikaap]

…tion

Which issue does this PR close?

• Closes Replace mock inference with real model artifacts in crop_yield_app #1704 .

Rationale for this change

The current /predict endpoint relies on np.random.uniform(...), producing random outputs instead of deterministic, model‑based predictions. This makes the feature unreliable and unsuitable for production. By loading actual trained artifacts and encoders, we ensure consistent, meaningful results and improve user trust in the system.

What changes are included in this PR?

Load trained model (xgb_crop_model.pkl) and encoders (Crop_encoder.pkl, Season_encoder.pkl, State_encoder.pkl).

Replace random inference with deterministic predictions using encoded inputs.

Add validation for unknown crop/season/state values, returning clear error messages.

[vercel]

@sanikaap is attempting to deploy a commit to the Om Roy's projects Team on Vercel.

A member of the Team first needs to authorize it.

[github-actions]

Thanks for creating a PR for your Issue! ☺️

We'll review it as soon as possible.
In the meantime, please double-check the file changes and ensure that all commits are accurate.

If there are any unresolved review comments, feel free to resolve them. 🙌🏼

[github-actions]

🎉 Congrats @sanikaap on getting your PR merged! 🙌
Thanks for the contribution — looking forward to more from you 🚀