timeseries: Welding - Added training scripts for classification with scikit learn

[sathyendranv]

Description

timeseries: Welding - Added training scripts for classification with scikit learn

Fixes # (issue)

Any Newly Introduced Dependencies

NA

How Has This Been Tested?

NA

Checklist:

• I agree to use the APACHE-2.0 license for my code changes.
• I have not introduced any 3rd party components incompatible with APACHE-2.0.
• I have not included any company confidential information, trade secret, password or security token.
• I have performed a self-review of my code.

[Copilot]

Pull request overview

This PR updates the weld anomaly detection sample to use a scikit-learn (Intel-accelerated) classifier pipeline for inference, and adds companion training/inference scripts to generate and validate the exported model artifacts.

Changes:

• Replace CatBoost-based weld UDF inference with a joblib-loaded scikit-learn pipeline + optional explanation payload.
• Add a classification training package (training script, predictor/CLI, sample inference scripts, README, and Python requirements).
• Tighten PR workflow path filters and add log-based readiness checks after sample-app deployment.

Reviewed changes

Copilot reviewed 12 out of 16 changed files in this pull request and generated 11 comments.

Show a summary per file

File	Description
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/time-series-analytics-config/udfs/weld_anomaly_detector.py	Switch UDF inference to sklearn pipeline, add explanation + Intel offload config usage.
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/time-series-analytics-config/tick_scripts/weld_anomaly_detector.tick	Minor formatting change.
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/time-series-analytics-config/models/weld_anomaly_detector.pkl	Add exported sklearn pipeline artifact for UDF inference.
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/time-series-analytics-config/models/weld_anomaly_detector_labels.pkl	Add exported LabelEncoder artifact for decoding class indices.
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/time-series-analytics-config/models/weld_anomaly_detector.json	Add model metadata + per-class feature stats used for explanations.
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/time-series-analytics-config/models/weld_anomaly_detector.txt	Add evaluation report for the exported classifier.
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/time-series-analytics-config/config.json	Point config to the new .pkl model and set device selection.
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/classification-training/weld_defect_train.py	New training script to build/export the sklearn model artifacts.
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/classification-training/weld_defect_predict.py	New predictor class + CLI for row-by-row inference.
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/classification-training/weld_defect_inference_sample.py	New sample script for CSV/demo inference (no explanation).
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/classification-training/weld_defect_inference_sample_w_explanation.py	New sample script for CSV/demo inference including explanation block.
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/classification-training/requirements.txt	New pinned Python dependencies for training/inference scripts.
manufacturing-ai-suite/industrial-edge-insights-time-series/apps/weld-anomaly-detection/classification-training/README.md	New end-to-end documentation for training + inference usage.
.github/workflows/industrial-edge-insights-time-series-pull-request.yml	Broaden path globs and add “wait for Kapacitor tasks enabled” log checks.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.