Sap Hana Ml
- Updated May 19, 2026
- AndreaFusar/https-github.com-secondsky-sap-skills
sap-hana-ml is an agent skill for developers and small teams shipping analytics on SAP HANA who need procedural guidance for the official Python hana-ml client. It targets the moment you are wiring in-database machine learning: connecting with ConnectionContext, shaping data as HANA DataFrames, choosing PAL or APL algorithms, and running classification, regression, clustering, or time-series workloads without exporting sensitive rows to a separate GPU farm. The skill also covers AutoML exploration, gradient boosting, SHAP-style interpretation, and storing models back in HANA so scoring stays close to transactional data. Use it when your product roadmap includes embedded predictions, operational forecasting, or customer scoring inside an SAP-centric stack and you want your coding agent to follow consistent patterns for SQLScript-adjacent ML rather than generic scikit-learn snippets that ignore HANA constraints.
Key points
- Covers hana-ml ConnectionContext and HANA DataFrame workflows for in-database ML
- Documents PAL and APL algorithm families for classification, regression, clustering, and time series (including ARIMA)
- Supports AutoML, gradient boosting, SHAP explainability, and model persistence in HANA
- Oriented to predictive analytics pipelines that stay on SAP HANA instead of external training clusters
- Python-first skill aligned with SAP HANA, SQL, and HDI/cloud database contexts
Sap Hana Ml by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
/plugin marketplace add AndreaFusar/https-github.com-secondsky-sap-skills/plugin install sap-hana-ml@sap-skillsAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Last updated | May 19, 2026 |
|---|---|
| Repository | AndreaFusar/https-github.com-secondsky-sap-skills ↗ |
What it does
Train, score, and persist ML models inside SAP HANA from Python without pulling large datasets out of the database.
Files
SAP HANA Machine Learning Python Client (hana-ml) development skill. Use when: Building ML solutions with SAP HANA's in-database machine learning using Python hana-ml library for PAL/APL algorithms, DataFrame operations, AutoML, model persistence, and visualization. Keywords: hana-ml, SAP HANA, machine learning, PAL, APL, predictive analytics, HANA DataFrame, ConnectionContext, classification, regression, clustering, time series, ARIMA, gradient boosting, AutoML, SHAP, model storage
sap-hana-ml
Source: ./plugins/sap-hana-ml
{ "name": "sap-hana-ml", "source": "./plugins/sap-hana-ml", "license": "GPL-3.0", "version": "2.2.0", "category": "hana", "keywords": [ "cloud", "database", "hana", "hdi", "python", "sap", "sap-hana-ml", "sql", "sqlscript" ], "description": "SAP HANA Machine Learning Python Client (hana-ml) development skill. Use when: Building ML solutions with SAP HANA's in-database machine learning using Python hana-ml library for PAL/APL algorithms, DataFrame operations, AutoML, model persistence, and visualization. Keywords: hana-ml, SAP HANA, machine learning, PAL, APL, predictive analytics, HANA DataFrame, ConnectionContext, classification, regression, clustering, time series, ARIMA, gradient boosting, AutoML, SHAP, model storage" }
Related skills
Microsoft FoundryDeploy, evaluate, and continuously improve Microsoft Foundry agents from a single agent interface.490k1.3k
Ai Research ReproductionOrchestrate trustworthy, auditable reproduction of deep learning repositories directly from their READMEs.176k511Run TrainSafely execute selected deep learning training commands with standardized evidence capture.176k511Explore RunSafely run isolated exploratory experiments with clear recording and conservative selection before committing changes.176k511Paper Context ResolverFetch precise reproduction-critical details like dataset splits, preprocessing steps, or evaluation protocols from the original academic paper when the repo README leav141k511Repo Intake And PlanScan unfamiliar AI research repositories and receive a minimal, trustworthy reproduction target before investing significant time.140k511